International Journal of Vehicle Autonomous Systems (6 papers in press)
Optimal mobile robot path planning in the presence of moving obstacles
by Adriano Zambom
Abstract: This paper presents an optimisation method to search for the optimal trajectory of an unmanned mobile robot while avoiding stationary and moving obstacles that may be in collision route. In order to meet the kinematic restrictions of the vehicle, the path is estimated using a finite-dimensional approximating space generated by B-splines basis functions. A penalised continuous function is used to convert the constrained minimisation problem into an unconstrained one. The optimisation is performed through a genetic algorithm that searches the finite-dimensional space of the B-splines coefficients, which determine the trajectory to be travelled. Experimental results with linear and nonlinear moving obstacle fields illustrate the estimated optimal trajectories.
Keywords: autonomous vehicle; genetic algorithm; B-splines; kinematics; constrained optimisation.
Development of shared steering torque system of electric vehicles in presence of driver behaviour estimation
by Khalfaoui Mohamed, Hartani Kada, Abdelkader Merah, Norediene Aouadj
Abstract: This paper proposes a new approach to develop a preventive driver assistance system for lane-keeping of electric vehicles. It is used to add a steering torque to that of the driver when there is degradation in driver performance (fatigue, drowsiness or inattention). Based on a cybernetic model of the driver, the drivers behaviour has been estimated by using an extended Kalman filter. An optimal linear quadratic regulator (LQR) controller is designed to impose a corrected steering torque on the steering wheel by minimising the cost function that contains all signals related to the electric vehicle and the drivers behaviour. The proposed controller model, based on three degrees of freedom, has been implemented on an electric vehicle using MATLAB/Simulink environment. The performance of the cooperative operation between the driver and the active steering torque controller is further evaluated by simulation tests.
Keywords: electric vehicles; driver assistance system; lateral control; lane keeping; LQR control; Kalman filter.
Real-time path planning module for autonomous vehicles in cluttered environment using a 3D camera
by Sobers Lourdu Xavier Francis, Sreenatha G. Anavatti, Matthew Garratt
Abstract: This paper is concerned with the real-time path planning of AGVs in a cluttered environment. In order to perform real-time operations with limited processing resources, an efficient path-planning algorithm and identification of the obstacles by a single sensor are presented. For an AGV, path planning in a cluttered environment is a challenging task due to its lack of information about the surroundings and its need to re-plan its path quickly whenever it senses obstacles nearby. Therefore, an efficient path-planning algorithm that offers an AGV sufficient time to re-plan its path to avoid moving obstacles is proposed and, to measure its computational efficacy, its time complexity is considered. In real-time experimentation of autonomous path-planning, AGV relies completely on perception system to sense the immediate environment and avoid obstacles when it traverses towards the goal. As the Time-of-Flight (ToF)-based PMD (Photonic Mixer Device) three dimensional (3D) sensor can provide range and intensity data at low computational cost, it is used as a single proprioceptive sensor to detect static and dynamic obstacles.
Keywords: path planning; scene flow; 3D ToF camera; PMD camera; graph search algorithm.
Path selection method of intelligent vehicle based on fuzzy big data game
by Zhiwu Huang
Abstract: In view of the traditional intelligent vehicle routing method, the problem of inaccurate selection, long time and low efficiency has always existed. We propose a path selection method for intelligent vehicles based on a fuzzy big data game. Through analysis of the modelling principle of intelligent transportation vehicle routing and the relevant principle of the least squares algorithm, we calculate the function of risk factors in the path selection of intelligent transportation vehicles and establish the conditional constraint model for vehicle routing. By using the depth neural network method, the path congestion state is identified, and the intelligent vehicle routing database is established. The simulation results show that the extraction time and accuracy of the method are better than those of the traditional path selection method.
Keywords: intelligent transportation; path selection; improvement strategy; fuzzy control; big data game.
Design and implementation of global path planning system for unmanned surface vehicle among multiple task points
by Wang Yanlong, Yu Xuemin, Liang Xu
Abstract: Global path planning is the key technology in the design of unmanned surface vehicles. This paper establishes global environment modelling based on electronic charts and hexagonal grids, which are proved to be better than square grids in validity, safety and rapidity. Besides, we introduce the cube coordinate system to simplify hexagonal algorithms. Furthermore, we propose an improved A* algorithm to realise the path planning between two points. Based on that, we build the global path planning modelling for multiple task points and present an improved ant colony optimisation to realise it accurately. The simulation results show that the global path planning system can plan an optimal path to tour multiple task points safely and quickly, which is superior to traditional methods in safety, rapidity and path length. Besides, the planned path can directly apply to actual applications of USVs.
Keywords: USV; path planning; hexagonal grids; A* algorithm; ant colony optimisation.
Special Issue on: Dynamics, Control and Energy Efficiency of Electrified Vehicles
A modified extreme seeking based adaptive fuzzy sliding mode control scheme for vehicle anti-lock braking
by Wenfei Li, Haiping Du, Weihua Li
Abstract: Vehicle anti-lock braking systems (ABS) are designed to optimise vehicle braking performance, but there are some challenges for their control. One of the challenges is that the optimal slip ratio is difficult to obtain in real time and it can differ under different road conditions. Another challenge is that ABS are nonlinear and many parameters of them are difficult to identify in advance. To solve these problems, a new extremum seeking based adaptive fuzzy sliding mode control strategy is proposed to seek and track the optimal slip ratio for improving the performance of a blended anti-lock braking system. The proposed modified sliding mode based extreme seeking algorithm (MSMES) is able to avoid the large oscillation and automatically search for the optimal slip ratio even when road conditions change. An adaptive fuzzy sliding mode controller (AFSMC) is designed to overcome the problem of possible disturbances, uncertainties, and the nonlinear characteristics of ABS and it is able to mimic an ideal controller and to estimate the error boundary between the ideal controller and the designed controller. In order to validate the effectiveness of the proposed approach, numerical simulations on a quarter-vehicle braking model have been tested. The results show that the proposed control method not only is able to track the optimal slip ratio under different road conditions accurately but also is very robust.
Keywords: anti-lock braking system; extremum seeking; adaptive fuzzy sliding mode control; adaptive nonlinear observer.