Development of a Personal Guide Robot That Leads a Guest Hand-in-Hand While Keeping a Distance

This paper proposes a novel tour guide robot, "ASAHI ReBorn", which can lead a guest by hand one-on-one while maintaining a proper distance from the guest. The robot uses a stretchable arm interface to hold the guest's hand and adjusts its speed according to the guest's pace. The robot also follows a given guide path accurately using the Robot Side method, a robot navigation method that follows a pre-defined path quickly and accurately. In addition, a control method is introduced that limits the angular velocity of the robot to avoid the robot's quick turn while guiding the guest. We evaluated the performance and usability of the proposed robot through experiments and user studies. The tour-guiding experiment revealed that the proposed method that keeps distance between the robot and the guest using the stretchable arm enables the guests to look around the exhibits compared with the condition where the robot moved at a constant velocity.

Improved Hybrid Model for Obstacle Detection and Avoidance in Robot Operating System Framework (Rapidly Exploring Random Tree and Dynamic Windows Approach)

The integration of machine learning and robotics brings promising potential to tackle the application challenges of mobile robot navigation in industries. The real-world environment is highly dynamic and unpredictable, with increasing necessities for efficiency and safety. This demands a multi-faceted approach that combines advanced sensing, robust obstacle detection, and avoidance mechanisms for an effective robot navigation experience. While hybrid methods with default robot operating system (ROS) navigation stack have demonstrated significant results, their performance in real time and highly dynamic environments remains a challenge. These environments are characterized by continuously changing conditions, which can impact the precision of obstacle detection systems and efficient avoidance control decision-making processes. In response to these challenges, this paper presents a novel solution that combines a rapidly exploring random tree (RRT)-integrated ROS navigation stack and a pre-trained YOLOv7 object detection model to enhance the capability of the developed work on the NAV-YOLO system. The proposed approach leveraged the high accuracy of YOLOv7 obstacle detection and the efficient path-planning capabilities of RRT and dynamic windows approach (DWA) to improve the navigation performance of mobile robots in real-world complex and dynamically changing settings. Extensive simulation and real-world robot platform experiments were conducted to evaluate the efficiency of the proposed solution. The result demonstrated a high-level obstacle avoidance capability, ensuring the safety and efficiency of mobile robot navigation operations in aviation environments.

Kinematic Analysis and Application to Control Logic Development for RHex Robot Locomotion

This study explores the kinematic model of the popular RHex hexapod robots which have garnered considerable interest for their locomotion capabilities. We study the influence of tripod trajectory parameters on the RHex robot's movement, aiming to craft a precise kinematic model that enhances walking mechanisms. This model serves as a cornerstone for refining robot control strategies, enabling tailored performance enhancements or specific motion patterns. Validation conducted on a bespoke test bed confirms the model's efficacy in predicting spatial movements, albeit with minor deviations due to motor load variations and control system dynamics. In particular, the derived kinematic framework offers valuable insights for advancing control logic, particularly navigating in flat terrains, thereby broadening the RHex robot's application spectrum.

Enhancing Stability and Performance in Mobile Robot Path Planning with PMR-Dueling DQN Algorithm

Path planning for mobile robots in complex circumstances is still a challenging issue. This work introduces an improved deep reinforcement learning strategy for robot navigation that combines dueling architecture, Prioritized Experience Replay, and shaped Rewards. In a grid world and two Gazebo simulation environments with static and dynamic obstacles, the Dueling Deep Q-Network with Modified Rewards and Prioritized Experience Replay (PMR-Dueling DQN) algorithm is compared against Q-learning, DQN, and DDQN in terms of path optimality, collision avoidance, and learning speed. To encourage the best routes, the shaped Reward function takes into account target direction, obstacle avoidance, and distance. Prioritized replay concentrates training on important events while a dueling architecture separates value and advantage learning. The results show that the PMR-Dueling DQN has greatly increased convergence speed, stability, and overall performance across conditions. In both grid world and Gazebo environments the PMR-Dueling DQN achieved higher cumulative rewards. The combination of deep reinforcement learning with reward design, network architecture, and experience replay enables the PMR-Dueling DQN to surpass traditional approaches for robot path planning in complex environments.

A Planar Multi-Inertial Navigation Strategy for Autonomous Systems for Signal-Variable Environments

The challenge of precise dynamic positioning for mobile robots is addressed through the development of a multi-inertial navigation system (M-INSs). The inherent cumulative sensor errors prevalent in traditional single inertial navigation systems (INSs) under dynamic conditions are mitigated by a novel algorithm, integrating multiple INS units in a predefined planar configuration, utilizing fixed distances between the units as invariant constraints. An extended Kalman filter (EKF) is employed to significantly enhance the positioning accuracy. Dynamic experimental validation of the proposed 3INS EKF algorithm reveals a marked improvement over individual INS units, with the positioning errors reduced and stability increased, resulting in an average accuracy enhancement rate exceeding 60%. This advancement is particularly critical for mobile robot applications that demand high precision, such as autonomous driving and disaster search and rescue. The findings from this study not only demonstrate the potential of M-INSs to improve dynamic positioning accuracy but also to provide a new research direction for future advancements in robotic navigation systems.

Design and experiments with a SLAM system for low-density canopy environments in greenhouses based on an improved Cartographer framework

To address the problem that the low-density canopy of greenhouse crops affects the robustness and accuracy of simultaneous localization and mapping (SLAM) algorithms, a greenhouse map construction method for agricultural robots based on multiline LiDAR was investigated. Based on the Cartographer framework, this paper proposes a map construction and localization method based on spatial downsampling. Taking suspended tomato plants planted in greenhouses as the research object, an adaptive filtering point cloud projection (AF-PCP) SLAM algorithm was designed. Using a wheel odometer, 16-line LiDAR point cloud data based on adaptive vertical projections were linearly interpolated to construct a map and perform high-precision pose estimation in a greenhouse with a low-density canopy environment. Experiments were carried out in canopy environments with leaf area densities (LADs) of 2.945-5.301 m2/m3. The results showed that the AF-PCP SLAM algorithm increased the average mapping area of the crop rows by 155.7% compared with that of the Cartographer algorithm. The mean error and coefficient of variation of the crop row length were 0.019 m and 0.217%, respectively, which were 77.9% and 87.5% lower than those of the Cartographer algorithm. The average maximum void length was 0.124 m, which was 72.8% lower than that of the Cartographer algorithm. The localization experiments were carried out at speeds of 0.2 m/s, 0.4 m/s, and 0.6 m/s. The average relative localization errors at these speeds were respectively 0.026 m, 0.029 m, and 0.046 m, and the standard deviation was less than 0.06 m. Compared with that of the track deduction algorithm, the average localization error was reduced by 79.9% with the proposed algorithm. The results show that our proposed framework can map and localize robots with precision even in low-density canopy environments in greenhouses, demonstrating the satisfactory capability of the proposed approach and highlighting its promising applications in the autonomous navigation of agricultural robots.

LeGO-LOAM-FN: An Improved Simultaneous Localization and Mapping Method Fusing LeGO-LOAM, Faster_GICP and NDT in Complex Orchard Environments

To solve the problem of cumulative errors when robots build maps in complex orchard environments due to their large scene size, similar features, and unstable motion, this study proposes a loopback registration algorithm based on the fusion of Faster Generalized Iterative Closest Point (Faster_GICP) and Normal Distributions Transform (NDT). First, the algorithm creates a K-Dimensional tree (KD-Tree) structure to eliminate the dynamic obstacle point clouds. Then, the method uses a two-step point filter to reduce the number of feature points of the current frame used for matching and the number of data used for optimization. It also calculates the matching degree of normal distribution probability by meshing the point cloud, and optimizes the precision registration using the Hessian matrix method. In the complex orchard environment with multiple loopback events, the root mean square error and standard deviation of the trajectory of the LeGO-LOAM-FN algorithm are 0.45 m and 0.26 m which are 67% and 73% higher than those of the loopback registration algorithm in the Lightweight and Ground-Optimized LiDAR Odometry and Mapping on Variable Terrain (LeGO-LOAM), respectively. The study proves that this method effectively reduces the influence of the cumulative error, and provides technical support for intelligent operation in the orchard environment.

Autonomous Driving of Mobile Robots in Dynamic Environments Based on Deep Deterministic Policy Gradient: Reward Shaping and Hindsight Experience Replay

In this paper, we propose a reinforcement learning-based end-to-end learning method for the autonomous driving of a mobile robot in a dynamic environment with obstacles. Applying two additional techniques for reinforcement learning simultaneously helps the mobile robot in finding an optimal policy to reach the destination without collisions. First, the multifunctional reward-shaping technique guides the agent toward the goal by utilizing information about the destination and obstacles. Next, employing the hindsight experience replay technique to address the experience imbalance caused by the sparse reward problem assists the agent in finding the optimal policy. We validated the proposed technique in both simulation and real-world environments. To assess the effectiveness of the proposed method, we compared experiments for five different cases.

A Safe Heuristic Path-Planning Method Based on a Search Strategy

In industrial production, it is very difficult to make a robot plan a safe, collision-free, smooth path with few inflection points. Therefore, this paper presents a safe heuristic path-planning method based on a search strategy. This method first expands the scope of the search node, then calculates the node state based on the search strategy, including whether it is a normal or dangerous state, and calculates the danger coefficient of the corresponding point to select the path with a lower danger coefficient. At the same time, the optimal boundary is obtained by incorporating the environmental facilities, and the optimal path between the starting point, the optimal boundary point and the end point is obtained. Compared to the traditional A-star algorithm, this method achieved significant improvements in various aspects such as path length, execution time, and path smoothness. Specifically, it reduced path length by 2.89%, decreased execution time by 13.98%, and enhanced path smoothness by 93.17%. The resulting paths are more secure and reliable, enabling robots to complete their respective tasks with reduced power consumption, thereby mitigating the drain on robot batteries.

Path Planning of a Mobile Robot for a Dynamic Indoor Environment Based on an SAC-LSTM Algorithm

This paper proposes an improved Soft Actor-Critic Long Short-Term Memory (SAC-LSTM) algorithm for fast path planning of mobile robots in dynamic environments. To achieve continuous motion and better decision making by incorporating historical and current states, a long short-term memory network (LSTM) with memory was integrated into the SAC algorithm. To mitigate the memory depreciation issue caused by resetting the LSTM's hidden states to zero during training, a burn-in training method was adopted to boost the performance. Moreover, a prioritized experience replay mechanism was implemented to enhance sampling efficiency and speed up convergence. Based on the SAC-LSTM framework, a motion model for the Turtlebot3 mobile robot was established by designing the state space, action space, reward function, and overall planning process. Three simulation experiments were conducted in obstacle-free, static obstacle, and dynamic obstacle environments using the ROS platform and Gazebo9 software. The results were compared with the SAC algorithm. In all scenarios, the SAC-LSTM algorithm demonstrated a faster convergence rate and a higher path planning success rate, registering a significant 10.5 percentage point improvement in the success rate of reaching the target point in the dynamic obstacle environment. Additionally, the time taken for path planning was shorter, and the planned paths were more concise.

Using Interoperability between Mobile Robot and KNX Technology for Occupancy Monitoring in Smart Home Care

It is important for older and disabled people who live alone to be able to cope with the daily challenges of living at home. In order to support independent living, the Smart Home Care (SHC) concept offers the possibility of providing comfortable control of operational and technical functions using a mobile robot for operating and assisting activities to support independent living for elderly and disabled people. This article presents a unique proposal for the implementation of interoperability between a mobile robot and KNX technology in a home environment within SHC automation to determine the presence of people and occupancy of occupied spaces in SHC using measured operational and technical variables (to determine the quality of the indoor environment), such as temperature, relative humidity, light intensity, and CO2 concentration, and to locate occupancy in SHC spaces using magnetic contacts monitoring the opening/closing of windows and doors by indirectly monitoring occupancy without the use of cameras. In this article, a novel method using nonlinear autoregressive Neural Networks (NN) with exogenous inputs and nonlinear autoregressive is used to predict the CO2 concentration waveform to transmit the information from KNX technology to mobile robots for monitoring and determining the occupancy of people in SHC with better than 98% accuracy.

Path Planning of a Mobile Delivery Robot Operating in a Multi-Story Building Based on a Predefined Navigation Tree

Planning the path of a mobile robot that must transport and deliver small packages inside a multi-story building is a problem that requires a combination of spatial and operational information, such as the location of origin and destination points and how to interact with elevators. This paper presents a solution to this problem, which has been formulated under the following assumptions: (1) the map of the building's floors is available; (2) the position of all origin and destination points is known; (3) the mobile robot has sensors to self-localize on the floors; (4) the building is equipped with remotely controlled elevators; and (5) all doors expected in a delivery route will be open. We start by defining a static navigation tree describing the weighted paths in a multi-story building. We then proceed to describe how this navigation tree can be used to plan the route of a mobile robot and estimate the total length of any delivery route using Dijkstra's algorithm. Finally, we show simulated routing results that demonstrate the effectiveness of this proposal when applied to an autonomous delivery robot operating in a multi-story building.

SafeCrowdNav: safety evaluation of robot crowd navigation in complex scenes

Navigating safely and efficiently in dense crowds remains a challenging problem for mobile robots. The interaction mechanisms involved in collision avoidance require robots to exhibit active and foresighted behaviors while understanding the crowd dynamics. Deep reinforcement learning methods have shown superior performance compared to model-based approaches. However, existing methods lack an intuitive and quantitative safety evaluation for agents, and they may potentially trap agents in local optima during training, hindering their ability to learn optimal strategies. In addition, sparse reward problems further compound these limitations. To address these challenges, we propose SafeCrowdNav, a comprehensive crowd navigation algorithm that emphasizes obstacle avoidance in complex environments. Our approach incorporates a safety evaluation function to quantitatively assess the current safety score and an intrinsic exploration reward to balance exploration and exploitation based on scene constraints. By combining prioritized experience replay and hindsight experience replay techniques, our model effectively learns the optimal navigation policy in crowded environments. Experimental outcomes reveal that our approach enables robots to improve crowd comprehension during navigation, resulting in reduced collision probabilities and shorter navigation times compared to state-of-the-art algorithms. Our code is available at https://github.com/Janet-xujing-1216/SafeCrowdNav.

A Path-Planning Method Based on Improved Soft Actor-Critic Algorithm for Mobile Robots

The path planning problem has gained more attention due to the gradual popularization of mobile robots. The utilization of reinforcement learning techniques facilitates the ability of mobile robots to successfully navigate through an environment containing obstacles and effectively plan their path. This is achieved by the robots' interaction with the environment, even in situations when the environment is unfamiliar. Consequently, we provide a refined deep reinforcement learning algorithm that builds upon the soft actor-critic (SAC) algorithm, incorporating the concept of maximum entropy for the purpose of path planning. The objective of this strategy is to mitigate the constraints inherent in conventional reinforcement learning, enhance the efficacy of the learning process, and accommodate intricate situations. In the context of reinforcement learning, two significant issues arise: inadequate incentives and inefficient sample use during the training phase. To address these challenges, the hindsight experience replay (HER) mechanism has been presented as a potential solution. The HER mechanism aims to enhance algorithm performance by effectively reusing past experiences. Through the utilization of simulation studies, it can be demonstrated that the enhanced algorithm exhibits superior performance in comparison with the pre-existing method.

Local Path Planning for Mobile Robots Based on Fuzzy Dynamic Window Algorithm

Due to the increased employment of robots in modern society, path planning methods based on human-robot collaborative mobile robots have been the subject of research in both academia and industry. The dynamic window approach used in the research of the robot local path planning problem involves a mixture of fixed weight coefficients, which makes it hard to deal with the changing dynamic environment and the issue of the sub-optimal global planning paths that arise after local obstacle avoidance. By dynamically modifying the combination of weight coefficients, we propose, in this research, the use of fuzzy control logic to optimize the evaluation function's sub-functions and enhance the algorithm's performance through the safe and dynamic avoidance of obstacles. The global path is introduced to enhance the dynamic window technique's ability to plan globally, and important points on the global path are selected as key sub-target sites for the local motion planning phase of the dynamic window technique. The motion position changes after local obstacle avoidance to keep the mobile robot on the intended global path. According to the simulation results, the enhanced dynamic window algorithm cuts planning time and path length by 16% and 5%, respectively, while maintaining good obstacle avoidance and considering a better global path in the face of various dynamic environments. It is difficult to achieve a local optimum using this algorithm.

Tracking by segmentation with future motion estimation applied to person-following robots

Person-following is a crucial capability for service robots, and the employment of vision technology is a leading trend in building environmental understanding. While most existing methodologies rely on a tracking-by-detection strategy, which necessitates extensive datasets for training and yet remains susceptible to environmental noise, we propose a novel approach: real-time tracking-by-segmentation with a future motion estimation framework. This framework facilitates pixel-level tracking of a target individual and predicts their future motion. Our strategy leverages a single-shot segmentation tracking neural network for precise foreground segmentation to track the target, overcoming the limitations of using a rectangular region of interest (ROI). Here we clarify that, while the ROI provides a broad context, the segmentation within this bounding box offers a detailed and more accurate position of the human subject. To further improve our approach, a classification-lock pre-trained layer is utilized to form a constraint that curbs feature outliers originating from the person being tracked. A discriminative correlation filter estimates the potential target region in the scene to prevent foreground misrecognition, while a motion estimation neural network anticipates the target's future motion for use in the control module. We validated our proposed methodology using the VOT, LaSot, YouTube-VOS, and Davis tracking datasets, demonstrating its effectiveness. Notably, our framework supports long-term person-following tasks in indoor environments, showing promise for practical implementation in service robots.

Smooth Autonomous Patrolling for a Differential-Drive Mobile Robot in Dynamic Environments

Today, mobile robots have a wide range of real-world applications where they can replace or assist humans in many tasks, such as search and rescue, surveillance, patrolling, inspection, environmental monitoring, etc. These tasks usually require a robot to navigate through a dynamic environment with smooth, efficient, and safe motion. In this paper, we propose an online smooth-motion-planning method that generates a smooth, collision-free patrolling trajectory based on clothoid curves. Moreover, the proposed method combines global and local planning methods, which are suitable for changing large environments and enabling efficient path replanning with an arbitrary robot orientation. We propose a method for planning a smoothed path based on the golden ratio wherein a robot's orientation is aligned with a new path that avoids unknown obstacles. The simulation results show that the proposed algorithm reduces the patrolling execution time, path length, and deviation of the tracked trajectory from the patrolling route compared to the original patrolling method without smoothing. Furthermore, the proposed algorithm is suitable for real-time operation due to its computational simplicity, and its performance was validated through the results of an experiment employing a differential-drive mobile robot.

Application of the Improved Rapidly Exploring Random Tree Algorithm to an Insect-like Mobile Robot in a Narrow Environment

When intelligent mobile robots perform global path planning in complex and narrow environments, several issues often arise, including low search efficiency, node redundancy, non-smooth paths, and high costs. This paper proposes an improved path planning algorithm based on the rapidly exploring random tree (RRT) approach. Firstly, the target bias sampling method is employed to screen and eliminate redundant sampling points. Secondly, the adaptive step size strategy is introduced to address the limitations of the traditional RRT algorithm. The mobile robot is then modeled and analyzed to ensure that the path adheres to angle and collision constraints during movement. Finally, the initial path is pruned, and the path is smoothed using a cubic B-spline curve, resulting in a smoother path with reduced costs. The evaluation metrics employed include search time, path length, and the number of sampling nodes. To evaluate the effectiveness of the proposed algorithm, simulations of the RRT algorithm, RRT-connect algorithm, RRT* algorithm, and the improved RRT algorithm are conducted in various environments. The results demonstrate that the improved RRT algorithm reduces the generated path length by 25.32% compared to the RRT algorithm, 26.42% compared to the RRT-connect algorithm, and 4.99% compared to the RRT* algorithm. Moreover, the improved RRT algorithm significantly improves the demand for reducing path costs. The planning time of the improved RRT algorithm is reduced by 64.96% compared to that of the RRT algorithm, 40.83% compared to that of the RRT-connect algorithm, and 27.34% compared to that of the RRT* algorithm, leading to improved speed. These findings indicate that the proposed method exhibits a notable improvement in the three crucial evaluation metrics: sampling time, number of nodes, and path length. Additionally, the algorithm performed well after undergoing physical verification with an insect-like mobile robot in a real environment featuring narrow elevator entrances.

A Robust Semi-Direct 3D SLAM for Mobile Robot Based on Dense Optical Flow in Dynamic Scenes

Dynamic objects bring about a large number of error accumulations in pose estimation of mobile robots in dynamic scenes, and result in the failure to build a map that is consistent with the surrounding environment. Along these lines, this paper presents a robust semi-direct 3D simultaneous localization and mapping (SLAM) algorithm for mobile robots based on dense optical flow. First, a preliminary estimation of the robot's pose is conducted using the sparse direct method and the homography matrix is utilized to compensate for the current frame image to reduce the image deformation caused by rotation during the robot's motion. Then, by calculating the dense optical flow field of two adjacent frames and segmenting the dynamic region in the scene based on the dynamic threshold, the local map points projected within the dynamic regions are eliminated. On this basis, the robot's pose is optimized by minimizing the reprojection error. Moreover, a high-performance keyframe selection strategy is developed, and keyframes are inserted when the robot's pose is successfully tracked. Meanwhile, feature points are extracted and matched to the keyframes for subsequent optimization and mapping. Considering that the direct method is subject to tracking failure in practical application scenarios, the feature points and map points of keyframes are employed in robot relocation. Finally, all keyframes and map points are used as optimization variables for global bundle adjustment (BA) optimization, so as to construct a globally consistent 3D dense octree map. A series of simulations and experiments demonstrate the superior performance of the proposed algorithm.

Dynamic Output Feedback and Neural Network Control of a Non-Holonomic Mobile Robot

This paper presents the design and synthesis of a dynamic output feedback neural network controller for a non-holonomic mobile robot. First, the dynamic model of a non-holonomic mobile robot is presented, in which these constraints are considered for the mathematical derivation of a feasible representation of this kind of robot. Then, two control strategies are provided based on kinematic control for this kind of robot. The first control strategy is based on driftless control; this means that considering that the velocity vector of the mobile robot is orthogonal to its restriction, a dynamic output feedback and neural network controller is designed so that the control action would be zero only when the velocity of the mobile robot is zero. The Lyapunov stability theorem is implemented in order to find a suitable control law. Then, another control strategy is designed for trajectory-tracking purposes, in which similar to the driftless controller, a kinematic control scheme is provided that is suitable to implement in more sophisticated hardware. In both control strategies, a dynamic control law is provided along with a feedforward neural network controller, so in this way, by the Lyapunov theory, the stability and convergence to the origin of the mobile robot position coordinates are ensured. Finally, two numerical experiments are presented in order to validate the theoretical results synthesized in this research study. Discussions and conclusions are provided in order to analyze the results found in this research study.

IRDC-Net: Lightweight Semantic Segmentation Network Based on Monocular Camera for Mobile Robot Navigation

Computer vision plays a significant role in mobile robot navigation due to the wealth of information extracted from digital images. Mobile robots localize and move to the intended destination based on the captured images. Due to the complexity of the environment, obstacle avoidance still requires a complex sensor system with a high computational efficiency requirement. This study offers a real-time solution to the problem of extracting corridor scenes from a single image using a lightweight semantic segmentation model integrating with the quantization technique to reduce the numerous training parameters and computational costs. The proposed model consists of an FCN as the decoder and MobilenetV2 as the decoder (with multi-scale fusion). This combination allows us to significantly minimize computation time while achieving high precision. Moreover, in this study, we also propose to use the Balance Cross-Entropy loss function to handle diverse datasets, especially those with class imbalances and to integrate a number of techniques, for example, the Adam optimizer and Gaussian filters, to enhance segmentation performance. The results demonstrate that our model can outperform baselines across different datasets. Moreover, when being applied to practical experiments with a real mobile robot, the proposed model's performance is still consistent, supporting the optimal path planning, allowing the mobile robot to efficiently and effectively avoid the obstacles.

A Multipole Magnetoactive Elastomer for Vibration-Driven Locomotion

Smart materials such as magnetoactive elastomers (MAEs) combine elastic and magnetic properties that can be significantly changed in response to a magnetic field and therefore offer enormous potential for applications in both scientific research and engineering. When such an elastomer contains microsized hard magnetic particles, it can become an elastic magnet once magnetized in a strong magnetic field. This article studies a multipole MAE with the aim of utilizing it as an actuation element of vibration-driven locomotion robots. The elastomer beam has three magnetic poles overall with the same poles at the ends and possesses silicone bristles protruding from its underside. The quasi-static bending of the multipole elastomer in a uniform magnetic field is investigated experimentally. The theoretical model exploits the magnetic torque to describe the field-induced bending shapes. The unidirectional locomotion of the elastomeric bristle-bot is realized in two prototype designs using magnetic actuation of either an external or an integrated source of an alternating magnetic field. The motion principle is based on cyclic interplay of asymmetric friction and inertia forces caused by field-induced bending vibrations of the elastomer. The locomotion behavior of both prototypes shows a strong resonant dependency of the advancing speed on the frequency of applied magnetic actuation.

Optimizing Appearance-Based Localization with Catadioptric Cameras: Small-Footprint Models for Real-Time Inference on Edge Devices

This paper considers the task of appearance-based localization: visual place recognition from omnidirectional images obtained from catadioptric cameras. The focus is on designing an efficient neural network architecture that accurately and reliably recognizes indoor scenes on distorted images from a catadioptric camera, even in self-similar environments with few discernible features. As the target application is the global localization of a low-cost service mobile robot, the proposed solutions are optimized toward being small-footprint models that provide real-time inference on edge devices, such as Nvidia Jetson. We compare several design choices for the neural network-based architecture of the localization system and then demonstrate that the best results are achieved with embeddings (global descriptors) yielded by exploiting transfer learning and fine tuning on a limited number of catadioptric images. We test our solutions on two small-scale datasets collected using different catadioptric cameras in the same office building. Next, we compare the performance of our system to state-of-the-art visual place recognition systems on the publicly available COLD Freiburg and Saarbrücken datasets that contain images collected under different lighting conditions. Our system compares favourably to the competitors both in terms of the accuracy of place recognition and the inference time, providing a cost- and energy-efficient means of appearance-based localization for an indoor service robot.

Particle Swarm Algorithm Path-Planning Method for Mobile Robots Based on Artificial Potential Fields

Path planning is an important part of the navigation control system of mobile robots since it plays a decisive role in whether mobile robots can realize autonomy and intelligence. The particle swarm algorithm can effectively solve the path-planning problem of a mobile robot, but the traditional particle swarm algorithm has the problems of a too-long path, poor global search ability, and local development ability. Moreover, the existence of obstacles makes the actual environment more complex, thus putting forward more stringent requirements on the environmental adaptation ability, path-planning accuracy, and path-planning efficiency of mobile robots. In this study, an artificial potential field-based particle swarm algorithm (apfrPSO) was proposed. First, the method generates robot planning paths by adjusting the inertia weight parameter and ranking the position vector of particles (rPSO), and second, the artificial potential field method is introduced. Through comparative numerical experiments with other state-of-the-art algorithms, the results show that the algorithm proposed was very competitive.

A Procedure for Taking a Remotely Controlled Elevator with an Autonomous Mobile Robot Based on 2D LIDAR

Navigating between the different floors of a multistory building is a task that requires walking up or down stairs or taking an elevator or lift. This work proposes a procedure to take a remotely controlled elevator with an autonomous mobile robot based on 2D LIDAR. The application of the procedure requires ICP matching for mobile robot self-localization, a building with remotely controlled elevators, and a 2D map of the floors of the building detailing the position of the elevators. The results show that the application of the procedure enables an autonomous mobile robot to take a remotely controlled elevator and to navigate between floors based on 2D LIDAR information.

Image-based robot navigation with task achievability

Image-based robot action planning is becoming an active area of research owing to recent advances in deep learning. To evaluate and execute robot actions, recently proposed approaches require the estimation of the optimal cost-minimizing path, such as the shortest distance or time, between two states. To estimate the cost, parametric models consisting of deep neural networks are widely used. However, such parametric models require large amounts of correctly labeled data to accurately estimate the cost. In real robotic tasks, collecting such data is not always feasible, and the robot itself may require collecting it. In this study, we empirically show that when a model is trained with data autonomously collected by a robot, the estimation of such parametric models could be inaccurate to perform a task. Specifically, the higher the maximum predicted distance, the more inaccurate the estimation, and the robot fails navigating in the environment. To overcome this issue, we propose an alternative metric, "task achievability" (TA), which is defined as the probability that a robot will reach a goal state within a specified number of timesteps. Compared to the training of optimal cost estimator, TA can use both optimal and non-optimal trajectories in the training dataset to train, which leads to a stable estimation. We demonstrate the effectiveness of TA through robot navigation experiments in an environment resembling a real living room. We show that TA-based navigation succeeds in navigating a robot to different target positions, even when conventional cost estimator-based navigation fails.

Biologically Inspired Complete Coverage Path Planning Algorithm Based on Q-Learning

Complete coverage path planning requires that the mobile robot traverse all reachable positions in the environmental map. Aiming at the problems of local optimal path and high path coverage ratio in the complete coverage path planning of the traditional biologically inspired neural network algorithm, a complete coverage path planning algorithm based on Q-learning is proposed. The global environment information is introduced by the reinforcement learning method in the proposed algorithm. In addition, the Q-learning method is used for path planning at the positions where the accessible path points are changed, which optimizes the path planning strategy of the original algorithm near these obstacles. Simulation results show that the algorithm can automatically generate an orderly path in the environmental map, and achieve 100% coverage with a lower path repetition ratio.

Path Planning and Motion Control of Indoor Mobile Robot under Exploration-Based SLAM (e-SLAM)

Indoor mobile robot (IMR) motion control for e-SLAM techniques with limited sensors, i.e., only LiDAR, is proposed in this research. The path was initially generated from simple floor plans constructed by the IMR exploration. The path planning starts from the vertices which can be traveled through, proceeds to the velocity planning on both cornering and linear motion, and reaches the interpolated discrete points joining the vertices. The IMR recognizes its location and environment gradually from the LiDAR data. The study imposes the upper rings of the LiDAR image to perform localization while the lower rings are for obstacle detection. The IMR must travel through a series of featured vertices and perform the path planning further generating an integrated LiDAR image. A considerable challenge is that the LiDAR data are the only source to be compared with the path planned according to the floor map. Certain changes still need to be adapted into, for example, the distance precision with relevance to the floor map and the IMR deviation in order to avoid obstacles on the path. The LiDAR setting and IMR speed regulation account for a critical issue. The study contributed to integrating a step-by-step procedure of implementing path planning and motion control using solely the LiDAR data along with the integration of various pieces of software. The control strategy is thus improved while experimenting with various proportional control gains for position, orientation, and velocity of the LiDAR in the IMR.

SLP-Improved DDPG Path-Planning Algorithm for Mobile Robot in Large-Scale Dynamic Environment

Navigating robots through large-scale environments while avoiding dynamic obstacles is a crucial challenge in robotics. This study proposes an improved deep deterministic policy gradient (DDPG) path planning algorithm incorporating sequential linear path planning (SLP) to address this challenge. This research aims to enhance the stability and efficiency of traditional DDPG algorithms by utilizing the strengths of SLP and achieving a better balance between stability and real-time performance. Our algorithm generates a series of sub-goals using SLP, based on a quick calculation of the robot's driving path, and then uses DDPG to follow these sub-goals for path planning. The experimental results demonstrate that the proposed SLP-enhanced DDPG path planning algorithm outperforms traditional DDPG algorithms by effectively navigating the robot through large-scale dynamic environments while avoiding obstacles. Specifically, the proposed algorithm improves the success rate by 12.33% compared to the traditional DDPG algorithm and 29.67% compared to the A*+DDPG algorithm in navigating the robot to the goal while avoiding obstacles.

A New Nonlinear Dynamic Speed Controller for a Differential Drive Mobile Robot

A disturbance/uncertainty estimation and disturbance rejection technique are proposed in this work and verified on a ground two-wheel differential drive mobile robot (DDMR) in the presence of a mismatched disturbance. The offered scheme is the an improved active disturbance rejection control (IADRC) approach-based enhanced dynamic speed controller. To efficiently eliminate the effect produced by the system uncertainties and external torque disturbance on both wheels, the IADRC is adopted, whereby all the torque disturbances and DDMR parameter uncertainties are conglomerated altogether and considered a generalized disturbance. This generalized disturbance is observed and cancelled by a novel nonlinear sliding mode extended state observer (NSMESO) in real-time. Through numerical simulations, various performance indices are measured, with a reduction of 86% and 97% in the ITAE index for the right and left wheels, respectively. Finally, these indices validate the efficacy of the proposed dynamic speed controller by almost damping the chattering phenomena and supplying a high insusceptibility in the closed-loop system against torque disturbance.

Path Planning for Unmanned Delivery Robots Based on EWB-GWO Algorithm

With the rise of robotics within various fields, there has been a significant development in the use of mobile robots. For mobile robots performing unmanned delivery tasks, autonomous robot navigation based on complex environments is particularly important. In this paper, an improved Gray Wolf Optimization (GWO)-based algorithm is proposed to realize the autonomous path planning of mobile robots in complex scenarios. First, the strategy for generating the initial wolf pack of the GWO algorithm is modified by introducing a two-dimensional Tent-Sine coupled chaotic mapping in this paper. This guarantees that the GWO algorithm generates the initial population diversity while improving the randomness between the two-dimensional state variables of the path nodes. Second, by introducing the opposition-based learning method based on the elite strategy, the adaptive nonlinear inertia weight strategy and random wandering law of the Butterfly Optimization Algorithm (BOA), this paper improves the defects of slow convergence speed, low accuracy, and imbalance between global exploration and local mining functions of the GWO algorithm in dealing with high-dimensional complex problems. In this paper, the improved algorithm is named as an EWB-GWO algorithm, where EWB is the abbreviation of three strategies. Finally, this paper enhances the rationalization of the initial population generation of the EWB-GWO algorithm based on the visual-field line detection technique of Bresenham's line algorithm, reduces the number of iterations of the EWB-GWO algorithm, and decreases the time complexity of the algorithm in dealing with the path planning problem. The simulation results show that the EWB-GWO algorithm is very competitive among metaheuristics of the same type. It also achieves optimal path length measures and smoothness metrics in the path planning experiments.

Dynamic Balance Control of Double Gyros Unicycle Robot Based on Sliding Mode Controller

This paper presents a doublegyroscope unicycle robot, which is dynamically balanced by sliding mode controller and PD controller based on its dynamics. This double-gyroscope robot uses the precession effect of the double gyro system to achieve its lateral balance. The two gyroscopes are at the same speed and in reverse direction so as to ensure that the precession torque of the gyroscopes does not interfere with the longitudinal direction of the unicycle robot. The lateral controller of the unicycle robot is a sliding mode controller. It not only maintains the balance ability of the unicycle robot, but also improves its robustness. The longitudinal controller of the unicycle robot is a PD controller, and its input variables are pitch angle and pitch angular velocity. In order to track the set speed, the speed of the unicycle robot is brought into the longitudinal controller to facilitate the speed control. The dynamic balance of the designed double gyro unicycle robot is verified by simulation and experiment results. At the same time, the anti-interference ability of the designed controller is verified by interference simulation and experiment.

Improving Odometric Model Performance Based on LSTM Networks

This paper presents a localization system for an autonomous wheelchair that includes several sensors, such as odometers, LIDARs, and an IMU. It focuses on improving the odometric localization accuracy using an LSTM neural network. Improved odometry will improve the result of the localization algorithm, obtaining a more accurate pose. The localization system is composed by a neural network designed to estimate the current pose using the odometric encoder information as input. The training is carried out by analyzing multiple random paths and defining the velodyne sensor data as training ground truth. During wheelchair navigation, the localization system retrains the network in real time to adjust any change or systematic error that occurs with respect to the initial conditions. Furthermore, another network manages to avoid certain random errors by using the relationship between the power consumed by the motors and the actual wheel speeds. The experimental results show several examples that demonstrate the ability to self-correct against variations over time, and to detect non-systematic errors in different situations using this relation. The final robot localization is improved with the designed odometric model compared to the classic robot localization based on sensor fusion using a static covariance.

Identification of Differential Drive Robot Dynamic Model Parameters

The paper presents the identification process of the mathematical model parameters of a differential-drive two-wheeled mobile robot. The values of the unknown parameters of the dynamics model were determined by carrying out their identification offline with the Levenberg-Marguardt method and identification online with the Recursive least-squares method. The authors compared the parameters identified by offline and online methods and proposed to support the recursive least squares method with the results obtained by offline identification. The correctness of the identification process of the robot dynamics model parameters, and the operation of the control system was verified by comparing the desired trajectories and those obtained through simulation studies and laboratory tests. Then an analysis of errors defined as the difference between the values of reference position, orientation and velocity, and those obtained from simulations and laboratory tests was carried out. On itd basis, the quality of regulation in the proposed algorithm was determined.

Effectiveness of mobile robots collecting vital signs and radiation dose rate for patients receiving Iodine-131 radiotherapy: A randomized clinical trial

Objective

Patients receiving radionuclide 131I treatment expose radiation to others, and there was no clinical trial to verify the effectiveness and safety of mobile robots in radionuclide 131I isolation wards. The objective of this randomized clinical trial was to evaluate the effectiveness and safety of mobile robots in providing vital signs (body temperature and blood pressure) and radiation dose rate monitoring for patients receiving radionuclide therapy.

Methods

An open-label, multicenter, paired, randomized clinical trial was performed at three medical centers in Shanghai and Wuhan, China, from 1 April 2018 to 1 September 2018. A total of 72 participants were assigned to the group in which vital signs and radiation doses were both measured by mobile robots and conventional instruments. Intergroup consistency, completion rate, and first success rate were the primary effectiveness measures, and vital sign measurement results, the error rate of use, and subjective satisfaction were secondary indicators. Adverse events related to the robot were used to assess safety.

Results

Of the 72 randomized participants (median age, 39.5; 27 [37.5%] male participants), 72 (100.0%) completed the trial. The analysis sets of full analysis set, per-protocol set, and safety analysis set included 72 cases (32 cases in Center A, 16 cases in Center B, and 24 cases in Center C). The consistency, completion rate, and first success rate were 100% (P = 1.00), and the first success rates of vital signs and radiation dose rate were 91.7% (P = 1.000), 100.0% (P = 0.120), and 100.0% (P = 1.000). There was no significant difference in vital signs and radiation dose rate measurement results between the robot measurement group and the control group (P = 0.000, 0.044, and 0.023), and subjective satisfaction in the robot measurement group was 71/72 (98.6%), compared to 67/72 (93.1%) in the control group. For safety evaluation, there was no adverse event related to the mobile robot.

Conclusion

The mobile robots have good effectiveness and safety in providing vital signs and radiation dose rate measurement services for patients treated with radionuclides.

Performance of the SABAT Neutron-Based Explosives Detector Integrated with an Unmanned Ground Vehicle: A Simulation Study

The effective and safe detection of illicit materials, explosives in particular, is currently of growing importance taking into account the geopolitical situation and increasing risk of a terrorist attack. The commonly used methods of detection are based predominantly on metal detectors and georadars, which show only the shapes of the possible dangerous objects and do not allow for exact identification and risk assessment. A supplementary or even alternative method may be based on neutron activation analysis, which provides the possibility of a stoichiometric analysis of the suspected object and its non-invasive identification. One such sensor is developed by the SABAT collaboration, with its primary application being underwater threat detection. In this article, we present performance studies of this sensor, integrated with a mobile robot, in terms of the minimal detectable quantity of commonly used explosives in different environmental conditions. The paper describes the functionality of the used platform considering electronics, sensors, onboard computing power, and communication system to carry out manual operation and remote control. Robotics solutions based on modularized structures allow the extension of sensors and effectors that can significantly improve the safety of personnel as well as work efficiency, productivity, and flexibility.

Deep Deterministic Policy Gradient-Based Autonomous Driving for Mobile Robots in Sparse Reward Environments

In this paper, we propose a deep deterministic policy gradient (DDPG)-based path-planning method for mobile robots by applying the hindsight experience replay (HER) technique to overcome the performance degradation resulting from sparse reward problems occurring in autonomous driving mobile robots. The mobile robot in our analysis was a robot operating system-based TurtleBot3, and the experimental environment was a virtual simulation based on Gazebo. A fully connected neural network was used as the DDPG network based on the actor-critic architecture. Noise was added to the actor network. The robot recognized an unknown environment by measuring distances using a laser sensor and determined the optimized policy to reach its destination. The HER technique improved the learning performance by generating three new episodes with normal experience from a failed episode. The proposed method demonstrated that the HER technique could help mitigate the sparse reward problem; this was further corroborated by the successful autonomous driving results obtained after applying the proposed method to two reward systems, as well as actual experimental results.

Smooth Complete Coverage Trajectory Planning Algorithm for a Nonholonomic Robot

The complete coverage path planning is a process of finding a path which ensures that a mobile robot completely covers the entire environment while following the planned path. In this paper, we propose a complete coverage path planning algorithm that generates smooth complete coverage paths based on clothoids that allow a nonholonomic mobile robot to move in optimal time while following the path. This algorithm greatly reduces coverage time, the path length, and overlap area, and increases the coverage rate compared to the state-of-the-art complete coverage algorithms, which is verified by simulation. Furthermore, the proposed algorithm is suitable for real-time operation due to its computational simplicity and allows path replanning in case the robot encounters unknown obstacles. The efficiency of the proposed algorithm is validated by experimental results on the Pioneer 3DX mobile robot.

Online Boosting-Based Target Identification among Similar Appearance for Person-Following Robots

It is challenging for a mobile robot to follow a specific target person in a dynamic environment, comprising people wearing similar-colored clothes and having the same or similar height. This study describes a novel framework for a person identification model that identifies a target person by merging multiple features into a single joint feature online. The proposed framework exploits the deep learning output to extract four features for tracking the target person without prior knowledge making it generalizable and more robust. A modified intersection over union between the current frame and the last frame is proposed as a feature to distinguish people, in addition to color, height, and location. To improve the performance of target identification in a dynamic environment, an online boosting method was adapted by continuously updating the features in every frame. Through extensive real-life experiments, the effectiveness of the proposed method was demonstrated by showing experimental results that it outperformed the previous methods.

Design and Calibration of Plane Mirror Setups for Mobile Robots with a 2D-Lidar

Lidar sensors are widely used for environmental perception on autonomous robot vehicles (ARV). The field of view (FOV) of Lidar sensors can be reshaped by positioning plane mirrors in their vicinity. Mirror setups can especially improve the FOV for ground detection of ARVs with 2D-Lidar sensors. This paper presents an overview of several geometric designs and their strengths for certain vehicle types. Additionally, a new and easy-to-implement calibration procedure for setups of 2D-Lidar sensors with mirrors is presented to determine precise mirror orientations and positions, using a single flat calibration object with a pre-aligned simple fiducial marker. Measurement data from a prototype vehicle with a 2D-Lidar with a 2 m range using this new calibration procedure are presented. We show that the calibrated mirror orientations are accurate to less than 0.6° in this short range, which is a significant improvement over the orientation angles taken directly from the CAD. The accuracy of the point cloud data improved, and no significant decrease in distance noise was introduced. We deduced general guidelines for successful calibration setups using our method. In conclusion, a 2D-Lidar sensor and two plane mirrors calibrated with this method are a cost-effective and accurate way for robot engineers to improve the environmental perception of ARVs.

Trainable Quaternion Extended Kalman Filter with Multi-Head Attention for Dead Reckoning in Autonomous Ground Vehicles

Extended Kalman filter (EKF) is one of the most widely used Bayesian estimation methods in the optimal control area. Recent works on mobile robot control and transportation systems have applied various EKF methods, especially for localization. However, it is difficult to obtain adequate and reliable process-noise and measurement-noise models due to the complex and dynamic surrounding environments and sensor uncertainty. Generally, the default noise values of the sensors are provided by the manufacturer, but the values may frequently change depending on the environment. Thus, this paper mainly focuses on designing a highly accurate trainable EKF-based localization framework using inertial measurement units (IMUs) for the autonomous ground vehicle (AGV) with dead reckoning, with the goal of fusing it with a laser imaging, detection, and ranging (LiDAR) sensor-based simultaneous localization and mapping (SLAM) estimation for enhancing the performance. Convolution neural networks (CNNs), backward propagation algorithms, and gradient descent methods are implemented in the system to optimize the parameters in our framework. Furthermore, we develop a unique cost function for training the models to improve EKF accuracy. The proposed work is general and applicable to diverse IMU-aided robot localization models.

An all-round AI-Chemist with a scientific mind

The realization of automated chemical experiments by robots unveiled the prelude to an artificial intelligence (AI) laboratory. Several AI-based systems or robots with specific chemical skills have been demonstrated, but conducting all-round scientific research remains challenging. Here, we present an all-round AI-Chemist equipped with scientific data intelligence that is capable of performing basic tasks generally required in chemical research. Based on a service platform, the AI-Chemist is able to automatically read the literatures from a cloud database and propose experimental plans accordingly. It can control a mobile robot in-house or online to automatically execute the complete experimental process on 14 workstations, including synthesis, characterization and performance tests. The experimental data can be simultaneously analysed by the computational brain of the AI-Chemist through machine learning and Bayesian optimization, allowing a new hypothesis for the next iteration to be proposed. The competence of the AI-Chemist has been scrutinized by three different chemical tasks. In the future, the more advanced all-round AI-Chemists equipped with scientific data intelligence may cause changes to the landscape of the chemical laboratory.

Loop Closure Detection Based on Residual Network and Capsule Network for Mobile Robot

Loop closure detection based on a residual network (ResNet) and a capsule network (CapsNet) is proposed to address the problems of low accuracy and poor robustness for mobile robot simultaneous localization and mapping (SLAM) in complex scenes. First, the residual network of a feature coding strategy is introduced to extract the shallow geometric features and deep semantic features of images, reduce the amount of image noise information, accelerate the convergence speed of the model, and solve the problems of gradient disappearance and network degradation of deep neural networks. Then, the dynamic routing mechanism of the capsule network is optimized through the entropy peak density, and a vector is used to represent the spatial position relationship between features, which can improve the ability of image feature extraction and expression to optimize the overall performance of networks. Finally, the optimized residual network and capsule network are fused to retain the differences and correlations between features, and the global feature descriptors and feature vectors are combined to calculate the similarity of image features for loop closure detection. The experimental results show that the proposed method can achieve loop closure detection for mobile robots in complex scenes, such as view changes, illumination changes, and dynamic objects, and improve the accuracy and robustness of mobile robot SLAM.

Interval Type-3 Fuzzy Adaptation of the Bee Colony Optimization Algorithm for Optimal Fuzzy Control of an Autonomous Mobile Robot

In this study, the first goal is achieving a hybrid approach composed by an Interval Type-3 Fuzzy Logic System (IT3FLS) for the dynamic adaptation of α and β parameters of Bee Colony Optimization (BCO) algorithm. The second goal is, based on BCO, to find the best partition of the membership functions (MFs) of a Fuzzy Controller (FC) for trajectory tracking in an Autonomous Mobile Robot (AMR). A comparative with different types of Fuzzy Systems, such as Fuzzy BCO with Type-1 Fuzzy Logic System (FBCO-T1FLS), Fuzzy BCO with Interval Type-2 Fuzzy Logic System (FBCO-IT2FLS) and Fuzzy BCO with Generalized Type-2 Fuzzy Logic System (FBCO-GT2FLS) is analyzed. A disturbance is added to verify if the FBCO-IT3FLS performance is better when the uncertainty is present. Several performance indices are used; RMSE, MSE and some metrics of control such as, ITAE, IAE, ISE and ITSE to measure the controller’s performance. The experiments show excellent results using FBCO-IT3FLS and are better than FBCO-GT2FLS, FBCO-IT2FLS and FBCO-T1FLS in the adaptation of α and β parameters.

Object-Based Change Detection Algorithm with a Spatial AI Stereo Camera

This paper presents a real-time object-based 3D change detection method that is built around the concept of semantic object maps. The algorithm is able to maintain an object-oriented metric-semantic map of the environment and can detect object-level changes between consecutive patrol routes. The proposed 3D change detection method exploits the capabilities of the novel ZED 2 stereo camera, which integrates stereo vision and artificial intelligence (AI) to enable the development of spatial AI applications. To design the change detection algorithm and set its parameters, an extensive evaluation of the ZED 2 camera was carried out with respect to depth accuracy and consistency, visual tracking and relocalization accuracy and object detection performance. The outcomes of these findings are reported in the paper. Moreover, the utility of the proposed object-based 3D change detection is shown in real-world indoor and outdoor experiments.

CLSQL: Improved Q-Learning Algorithm Based on Continuous Local Search Policy for Mobile Robot Path Planning

How to generate the path planning of mobile robots quickly is a problem in the field of robotics. The Q-learning(QL) algorithm has recently become increasingly used in the field of mobile robot path planning. However, its selection policy is blind in most cases in the early search process, which slows down the convergence of optimal solutions, especially in a complex environment. Therefore, in this paper, we propose a continuous local search Q-Learning (CLSQL) algorithm to solve these problems and ensure the quality of the planned path. First, the global environment is gradually divided into independent local environments. Then, the intermediate points are searched in each local environment with prior knowledge. After that, the search between each intermediate point is realized to reach the destination point. At last, by comparing other RL-based algorithms, the proposed method improves the convergence speed and computation time while ensuring the optimal path.

An Embodied Intelligence-Based Biologically Inspired Strategy for Searching a Moving Target

Bacterial chemotaxis in unicellular Escherichia coli, the simplest biological creature, enables it to perform effective searching behaviour even with a single sensor, achieved via a sequence of "tumbling" and "swimming" behaviours guided by gradient information. Recent studies show that suitable random walk strategies may guide the behaviour in the absence of gradient information. This article presents a novel and minimalistic biologically inspired search strategy inspired by bacterial chemotaxis and embodied intelligence concept: a concept stating that intelligent behaviour is a result of the interaction among the "brain," body morphology including the sensory sensitivity tuned by the morphology, and the environment. Specifically, we present bacterial chemotaxis inspired searching behaviour with and without gradient information based on biological fluctuation framework: a mathematical framework that explains how biological creatures utilize noises in their behaviour. Via extensive simulation of a single sensor mobile robot that searches for a moving target, we will demonstrate how the effectiveness of the search depends on the sensory sensitivity and the inherent random walk strategies produced by the brain of the robot, comprising Ballistic, Levy, Brownian, and Stationary search. The result demonstrates the importance of embodied intelligence even in a behaviour inspired by the simplest creature.

An Enhanced Hybrid Visual-Inertial Odometry System for Indoor Mobile Robot

As mobile robots are being widely used, accurate localization of the robot counts for the system. Compared with position systems with a single sensor, multi-sensor fusion systems provide better performance and increase the accuracy and robustness. At present, camera and IMU (Inertial Measurement Unit) fusion positioning is extensively studied and many representative Visual-Inertial Odometry (VIO) systems have been produced. Multi-State Constraint Kalman Filter (MSCKF), one of the tightly coupled filtering methods, is characterized by high accuracy and low computational load among typical VIO methods. In the general framework, IMU information is not used after predicting the state and covariance propagation. In this article, we proposed a framework which introduce IMU pre-integration result into MSCKF framework as observation information to improve the system positioning accuracy. Additionally, the system uses the Helmert variance component estimation (HVCE) method to adjust the weight between feature points and pre-integration to further improve the positioning accuracy. Similarly, this article uses the wheel odometer information of the mobile robot to perform zero speed detection, zero-speed update, and pre-integration update to enhance the positioning accuracy of the system. Finally, after experiments carried out in Gazebo simulation environment, public dataset and real scenarios, it is proved that the proposed algorithm has better accuracy results while ensuring real-time performance than existing mainstream algorithms.

Self-Supervised Robust Feature Matching Pipeline for Teach and Repeat Navigation

The performance of deep neural networks and the low costs of computational hardware has made computer vision a popular choice in many robotic systems. An attractive feature of deep-learned methods is their ability to cope with appearance changes caused by day-night cycles and seasonal variations. However, deep learning of neural networks typically relies on large numbers of hand-annotated images, which requires significant effort for data collection and annotation. We present a method that allows autonomous, self-supervised training of a neural network in visual teach-and-repeat (VT&R) tasks, where a mobile robot has to traverse a previously taught path repeatedly. Our method is based on a fusion of two image registration schemes: one based on a Siamese neural network and another on point-feature matching. As the robot traverses the taught paths, it uses the results of feature-based matching to train the neural network, which, in turn, provides coarse registration estimates to the feature matcher. We show that as the neural network gets trained, the accuracy and robustness of the navigation increases, making the robot capable of dealing with significant changes in the environment. This method can significantly reduce the data annotation efforts when designing new robotic systems or introducing robots into new environments. Moreover, the method provides annotated datasets that can be deployed in other navigation systems. To promote the reproducibility of the research presented herein, we provide our datasets, codes and trained models online.

Autonomous Navigation System of Greenhouse Mobile Robot Based on 3D Lidar and 2D Lidar SLAM

The application of mobile robots is an important link in the development of intelligent greenhouses. In view of the complex environment of a greenhouse, achieving precise positioning and navigation by robots has become the primary problem to be solved. Simultaneous localization and mapping (SLAM) technology is a hot spot in solving the positioning and navigation in an unknown indoor environment in recent years. Among them, the SLAM based on a two-dimensional (2D) Lidar can only collect the environmental information at the level of Lidar, while the SLAM based on a 3D Lidar demands a high computation cost; hence, it has higher requirements for the industrial computers. In this study, the robot navigation control system initially filtered the information of a 3D greenhouse environment collected by a 3D Lidar and fused the information into 2D information, and then, based on the robot odometers and inertial measurement unit information, the system has achieved a timely positioning and construction of the greenhouse environment by a robot using a 2D Lidar SLAM algorithm in Cartographer. This method not only ensures the accuracy of a greenhouse environmental map but also reduces the performance requirements on the industrial computer. In terms of path planning, the Dijkstra algorithm was used to plan the global navigation path of the robot while the Dynamic Window Approach (DWA) algorithm was used to plan the local navigation path of the robot. Through the positioning test, the average position deviation of the robot from the target positioning point is less than 8 cm with a standard deviation (SD) of less than 3 cm; the average course deviation is less than 3° with an SD of less than 1° at the moving speed of 0.4 m/s. The robot moves at the speed of 0.2, 0.4, and 0.6 m/s, respectively; the average lateral deviation between the actual movement path and the target movement path is less than 10 cm, and the SD is less than 6 cm; the average course deviation is <3°, and the SD is <1.5°. Both the positioning accuracy and the navigation accuracy of the robot can meet the requirements of mobile navigation and positioning in the greenhouse environment.