Dynamic Obstacle Avoidance for Unmanned Underwater Vehicles Based on an Improved Velocity Obstacle Method

Advancements in Learning-Based Navigation Systems for Robotic Applications in MRO Hangar: Review

The field of learning-based navigation for mobile robots is experiencing a surge of interest from research and industry sectors. The application of this technology for visual aircraft inspection tasks within a maintenance, repair, and overhaul (MRO) hangar necessitates efficient perception and obstacle avoidance capabilities to ensure a reliable navigation experience. The present reliance on manual labour, static processes, and outdated technologies limits operation efficiency in the inherently dynamic and increasingly complex nature of the real-world hangar environment. The challenging environment limits the practical application of conventional methods and real-time adaptability to changes. In response to these challenges, recent years research efforts have witnessed advancement with machine learning integration aimed at enhancing navigational capability in both static and dynamic scenarios. However, most of these studies have not been specific to the MRO hangar environment, but related challenges have been addressed, and applicable solutions have been developed. This paper provides a comprehensive review of learning-based strategies with an emphasis on advancements in deep learning, object detection, and the integration of multiple approaches to create hybrid systems. The review delineates the application of learning-based methodologies to real-time navigational tasks, encompassing environment perception, obstacle detection, avoidance, and path planning through the use of vision-based sensors. The concluding section addresses the prevailing challenges and prospective development directions in this domain.

Collision Detection and Avoidance for Underwater Vehicles Using Omnidirectional Vision

Exploration of marine habitats is one of the key pillars of underwater science, which often involves collecting images at close range. As acquiring imagery close to the seabed involves multiple hazards, the safety of underwater vehicles, such as remotely operated vehicles (ROVs) and autonomous underwater vehicles (AUVs), is often compromised. Common applications for obstacle avoidance in underwater environments are often conducted with acoustic sensors, which cannot be used reliably at very short distances, thus requiring a high level of attention from the operator to avoid damaging the robot. Therefore, developing capabilities such as advanced assisted mapping, spatial awareness and safety, and user immersion in confined environments is an important research area for human-operated underwater robotics. In this paper, we present a novel approach that provides an ROV with capabilities for navigation in complex environments. By leveraging the ability of omnidirectional multi-camera systems to provide a comprehensive view of the environment, we create a 360° real-time point cloud of nearby objects or structures within a visual SLAM framework. We also develop a strategy to assess the risk of obstacles in the vicinity. We show that the system can use the risk information to generate warnings that the robot can use to perform evasive maneuvers when approaching dangerous obstacles in real-world scenarios. This system is a first step towards a comprehensive pilot assistance system that will enable inexperienced pilots to operate vehicles in complex and cluttered environments.

Optimal Navigation of an Unmanned Surface Vehicle and an Autonomous Underwater Vehicle Collaborating for Reliable Acoustic Communication with Collision Avoidance

This paper focuses on safe navigation of an unmanned surface vehicle in proximity to a submerged autonomous underwater vehicle so as to maximise short-range, through-water data transmission while minimising the probability that the two vehicles will accidentally collide. A sliding mode navigation law is developed, and a rigorous proof of optimality of the proposed navigation law is presented. The developed navigation algorithm is relatively computationally simple and easily implementable in real time. Illustrative examples with extensive computer simulations demonstrate the effectiveness of the proposed method.

Mini-AUV Hydrodynamic Parameters Identification via CFD Simulations and Their Application on Control Performance Evaluation

This manuscript presents a fully detailed methodology in order to identify the hydrodynamic parameters of a mini autonomous underwater vehicle (mini-AUV) and evaluate its performance using different controllers. The methodology consists of close-to-reality simulation using a Computed Fluid Dynamics (CFD) module of the ANSYS™ Workbench software, the processing of the data, obtained by simulation, with a set of Savistky–Golay filters; and, the application of the Least Square Method in order to estimate the hydrodynamic parameters of the mini-AUV. Finally, these parameters are considered to design the three different controllers that are based on the robot manipulators theory. Numerical simulations are carried out to evaluate the performance of the controllers.

Trajectory Optimization of Pickup Manipulator in Obstacle Environment Based on Improved Artificial Potential Field Method

In order to realize the technique of quick picking and obstacle avoidance, this work proposes a trajectory optimization method for the pickup manipulator under the obstacle condition. The proposed method is based on the improved artificial potential field method and the cosine adaptive genetic algorithm. Firstly, the Denavit–Hartenberg (D-H) method is used to carry out the kinematics modeling of the pickup manipulator. Taking into account the motion constraints, the cosine adaptive genetic algorithm is utilized to complete the time-optimal trajectory planning. Then, for the collision problem in the obstacle environment, the artificial potential field method is used to establish the attraction, repulsion, and resultant potential field functions. By improving the repulsion potential field function and increasing the sub-target point, obstacle avoidance planning of the improved artificial potential field method is completed. Finally, combined with the improved artificial potential field method and cosine adaptive genetic algorithm, the movement simulation analysis of the five-Degree-of-Freedom pickup manipulator is carried out. The trajectory optimization under the obstacle environment is realized, and the picking efficiency is improved.

Sensor-based Navigation of Omnidirectional Wheeled Robots Dealing with both Collisions and Occlusions

Navigation tasks are often subject to several constraints that can be related to the sensors (visibility) or come from the environment (obstacles). In this paper, we propose a framework for autonomous omnidirectional wheeled robots that takes into account both collision and occlusion risk, during sensor-based navigation. The task consists in driving the robot towards a visual target in the presence of static and moving obstacles. The target is acquired by fixed – limited field of view – on-board cameras, while the surrounding obstacles are detected by lidar scanners. To perform the task, the robot has not only to keep the target in view while avoiding the obstacles, but also to predict its location in the case of occlusion. The effectiveness of our approach is validated through several experiments.

Learn to Steer through Deep Reinforcement Learning

It is crucial for robots to autonomously steer in complex environments safely without colliding with any obstacles. Compared to conventional methods, deep reinforcement learning-based methods are able to learn from past experiences automatically and enhance the generalization capability to cope with unseen circumstances. Therefore, we propose an end-to-end deep reinforcement learning algorithm in this paper to improve the performance of autonomous steering in complex environments. By embedding a branching noisy dueling architecture, the proposed model is capable of deriving steering commands directly from raw depth images with high efficiency. Specifically, our learning-based approach extracts the feature representation from depth inputs through convolutional neural networks and maps it to both linear and angular velocity commands simultaneously through different streams of the network. Moreover, the training framework is also meticulously designed to improve the learning efficiency and effectiveness. It is worth noting that the developed system is readily transferable from virtual training scenarios to real-world deployment without any fine-tuning by utilizing depth images. The proposed method is evaluated and compared with a series of baseline methods in various virtual environments. Experimental results demonstrate the superiority of the proposed model in terms of average reward, learning efficiency, success rate as well as computational time. Moreover, a variety of real-world experiments are also conducted which reveal the high adaptability of our model to both static and dynamic obstacle-cluttered environments. A video of our experiments is available at https://youtu.be/yixnmFXIKf4 and http://v.youku.com/vshow/idXMzg1ODYwMzM5Ng.

Autonomous Minimum Safe Distance Maintenance from Submersed Obstacles in Ocean Currents

A considerable volume of research has recently blossomed in the literature on autonomous underwater vehicles accepting recent developments in mathematical modeling and system identification; pitch control; information filtering and active sensing, including inductive sensors of ELF emissions and also optical sensor arrays for position, velocity, and orientation detection; grid navigation algorithms; and dynamic obstacle avoidance, amongst others. In light of these modern developments, this article develops and compares integrative guidance, navigation, and control methodologies for the Naval Postgraduate School’s Phoenix submerged autonomous vehicle, where these methods are assumed available. The measure of merit reveals how well each of several proposed methodologies cope with known and unknown disturbances, such as currents that can be constant or harmonic, while maintaining a safe passage distance from underwater obstacles, in this case submerged mines. Classical pole-placement designs establish nominal baseline behaviors and are subsequently compared to performance of designs that are optimized to satisfy linear quadratic cost functions in regulators as well as linear-quadratic Gaussian designs. Feed-forward architectures and integral control designs are also evaluated. A noteworthy contribution is a very simple method to mimic optimal results with a “rule of thumb” criteria based on the design’s time constant. Since the rule-of-thumb method uses the assumed system model for computation of the control, it is particularly generic. Cited references each contain methods for online system parameter identification (with a motivation of use in the finding the control signal), permitting the rule of thumb’s generic applicability, since it is expressed in terms of the system parameters. This proposed method permits control design at sea where significant computation abilities are not available. Very simple waypoint guidance is also introduced to guide a vehicle along a preplanned path through a field of obstacles placed at random locations. The linear-quadratic Gaussian design proves best when augmented with integral control, and works well with reduced-order equations, while the “rule of thumb” design is seen to closely mimic the optimal performance. Feed-forward augmentation proves particularly efficient at rejecting constant disturbances, while augmentation with integral control is necessary to counter periodic disturbances, where the augmentations are also optimized in the linear-quadratic Gaussian procedures, yet can be closely mimicked by the proposed “rule of thumb” technique.