An Optimized Trajectory Planner and Motion Controller Framework for Autonomous Driving in Unstructured Environments

Long Short-Term Memory Neural Networks for Modeling Dynamical Processes and Predictive Control: A Hybrid Physics-Informed Approach

This work has two objectives. Firstly, it describes a novel physics-informed hybrid neural network (PIHNN) model based on the long short-term memory (LSTM) neural network. The presented model structure combines the first-principle process description and data-driven neural sub-models using a specialized data fusion block that relies on fuzzy logic. The second objective of this work is to detail a computationally efficient model predictive control (MPC) algorithm that employs the PIHNN model. The validity of the presented modeling and MPC approaches is demonstrated for a simulated polymerization reactor. It is shown that the PIHNN structure gives very good modeling results, while the MPC controller results in excellent control quality.

Forgery Cyber-Attack Supported by LSTM Neural Network: An Experimental Case Study

This work is concerned with the vulnerability of a network industrial control system to cyber-attacks, which is a critical issue nowadays. This is because an attack on a controlled process can damage or destroy it. These attacks use long short-term memory (LSTM) neural networks, which model dynamical processes. This means that the attacker may not know the physical nature of the process; an LSTM network is sufficient to mislead the process operator. Our experimental studies were conducted in an industrial control network containing a magnetic levitation process. The model training, evaluation, and structure selection are described. The chosen LSTM network very well mimicked the considered process. Finally, based on the obtained results, we formulated possible protection methods against the considered types of cyber-attack.

An Optimization-Based Motion Planner for Car-like Logistics Robots on Narrow Roads

Thanks to their strong maneuverability and high load capacity, car-like robots with non-holonomic constraints are often used in logistics to improve efficiency. However, it is difficult to plan a safe and smooth optimal path in real time on the restricted narrow roads of the logistics park. To solve this problem, an optimization-based motion planning method inspired by the Timed-Elastic-Band algorithm is proposed, called Narrow-Roads-Timed-Elastic-Band (NRTEB). Three optimization modules are added to the inner and outer workflow of the Timed-Elastic-Band framework. The simulation results show that the proposed method achieves safe reversing planning on narrow roads while the jerk of the trajectory is reduced by 72.11% compared to the original method. Real-world experiments reveal that the proposed method safely and smoothly avoids dynamic obstacles in real time when navigating forward and backward. The motion planner provides a safer and smoother trajectory for car-like robots on narrow roads in real time, which greatly enhances the safety, robustness and reliability of the Timed-Elastic-Band planner in logistics parks.

Research Scenarios of Autonomous Vehicles, the Sensors and Measurement Systems Used in Experiments

Automated and autonomous vehicles are in an intensive development phase. It is a phase that requires a lot of modelling and experimental research. Experimental research into these vehicles is in its initial state. There is a lack of findings and standardized recommendations for the organization and creation of research scenarios. There are also many difficulties in creating research scenarios. The main difficulties are the large number of systems for simultaneous checking. Additionally, the vehicles have a very complicated structure. A review of current publications allowed for systematization of the research scenarios of vehicles and their components as well as the measurement systems used. These include perception systems, automated response to threats, and critical situations in the area of road safety. The scenarios analyzed ensure that the planned research tasks can be carried out, including the investigation of systems that enable autonomous driving. This study uses passenger cars equipped with highly sophisticated sensor systems and localization devices. Perception systems are the necessary equipment during the conducted study. They provide recognition of the environment, mainly through vision sensors (cameras) and lidars. The research tasks include autonomous driving along a detected road lane on a curvilinear track. The effective maintenance of the vehicle in this lane is assessed. The location used in the study is a set of specialized research tracks on which stationary or moving obstacles are often placed.

An Efficient LiDAR Point Cloud Map Coding Scheme Based on Segmentation and Frame-Inserting Network

In this article, we present an efficient coding scheme for LiDAR point cloud maps. As a point cloud map consists of numerous single scans spliced together, by recording the time stamp and quaternion matrix of each scan during map building, we cast the point cloud map compression into the point cloud sequence compression problem. The coding architecture includes two techniques: intra-coding and inter-coding. For intra-frames, a segmentation-based intra-prediction technique is developed. For inter-frames, an interpolation-based inter-frame coding network is explored to remove temporal redundancy by generating virtual point clouds based on the decoded frames. We only need to code the difference between the original LiDAR data and the intra/inter-predicted point cloud data. The point cloud map can be reconstructed according to the decoded point cloud sequence and quaternion matrices. Experiments on the KITTI dataset show that the proposed coding scheme can largely eliminate the temporal and spatial redundancies. The point cloud map can be encoded to 1/24 of its original size with 2 mm-level precision. Our algorithm also obtains better coding performance compared with the octree and Google Draco algorithms.

Motion Planning for Autonomous Vehicles Based on Sequential Optimization

This study presents the development and analysis of a technique for planning the autonomous vehicle (AV) motion references using sequential optimization. The method determines the trajectory plan, speed and acceleration distributions, and other AV kinematic parameters. The approach combines the basics of the finite element method (FEM) and nonlinear optimization with nonlinear constraints. First, we briefly described the generalization of representing an arbitrary function by finite elements (FE) within a road segment. We chose a one-dimensional FE with two nodes and three degrees of freedom (DOF) in a node corresponding to the 5th-degree polynomial. Next, we presented a method for defining the motion trajectory. The following are considered: the formation of a restricted space for the AV’s allowable maneuvering, the motion trajectory geometry and its relation with vehicle steerability parameters, cost functions and their influences on the desirable trajectory’s nature, and the compliance of nonlinear restrictions of the node parameters with the motion area boundaries. In the second stage, we derived a technique for optimizing the AV’s speed and acceleration redistributions. The model considers possible combinations of objective functions, limiting the kinematic parameters by the tire slip critical speed, maximum speed level, maximum longitudinal acceleration, and critical lateral acceleration. In the simulation section, we compared several variants of trajectories and versions of distributing the longitudinal speed and acceleration curves. The advantages, drawbacks, and conclusions regarding the proposed technique are presented.

Computationally Efficient Nonlinear Model Predictive Control Using the L1 Cost-Function

Model Predictive Control (MPC) algorithms typically use the classical L2 cost function, which minimises squared differences of predicted control errors. Such an approach has good numerical properties, but the L1 norm that measures absolute values of the control errors gives better control quality. If a nonlinear model is used for prediction, the L1 norm leads to a difficult, nonlinear, possibly non-differentiable cost function. A computationally efficient alternative is discussed in this work. The solution used consists of two concepts: (a) a neural approximator is used in place of the non-differentiable absolute value function; (b) an advanced trajectory linearisation is performed on-line. As a result, an easy-to-solve quadratic optimisation task is obtained in place of the nonlinear one. Advantages of the presented solution are discussed for a simulated neutralisation benchmark. It is shown that the obtained trajectories are very similar, practically the same, as those possible in the reference scheme with nonlinear optimisation. Furthermore, the L1 norm even gives better performance than the classical L2 one in terms of the classical control performance indicator that measures squared control errors.