Abstract:A hierarchical trajectory planning method with path and speed co-search and decoupling optimization is proposed to address the multi-constraint trajectory planning problem in structured road scenarios. To ensure the quality of the initial trajectory solution, the upper initial trajectory planner constructs the Spatio-temporal cost map by taking into account the risk field and spatio-temporal information of dynamic obstacles, and searches for the safe and feasible initial trajectory using a three-dimensional A* algorithm. The lower trajectory planner implements decoupling for the trajectory planning as path planning and velocity planning with the minimum curvature, maximum speed, and comfort as the goal. A numerical optimization algorithm is used to construct a spline optimization model for the path and speed, in order that in the process of obstacle avoidance it can give full play to the dynamic performance of the vehicle and at the same time improve the ride comfort, simplify the constraint conditions on local space-time tunnel thought, and improve solving efficiency. The experiment results show that the proposed method has better driving efficiency, comfort, and real-time performance.

Abstract:Parking trajectory characteristics were analyzed, and an approach for trajectory planning was proposed on the basis of the B spline theory, and the parking path was realized by adjusting the control points. Potential collision points were analyzed,and the constraint equations were established accordingly. The orientation constraints at the start point,the location constraints at the parking point,and the restriction of vehicle were considered, and the constraint equations were established respectively. Parking kinematic function was presented on the basis of Ackerman steering theory, and parking trajectory optimization function was presented to minimize the max trajectory curvature in parking process with the restrictions mentioned above. The approach was used to plan parking path for general parking space and tight parking space, and the trajectory function was solved in Matlab. The simulation results have shown that the car can reverse into parking set safely in general parking space, with the trajectory curvature changing continuously and the car paralleling the parking set at the parking point. The car can reverse into parking set without collision in tight parking space by adjusting steering angle repeatedly, with the trajectory curvature changing continuously. It is proved that the approach proposed can find a collision-free path in different parking spaces and meets the demand of continuous trajectory curvature, so the problem of shutting down to steer the wheel in parking process has been solved.

Abstract:This paper designed an eight-axis control system by adopting ASIC as the central core, and using the PCI multi-axis controller to control the stepper motor movement through state feedback. Combining the advantages of Hopfield neural network and the genetic algorithm, the control system adopted GA-Hopfield neural network to optimize the path of Chinese sculpture. This method solved the perplexity sculpture process problem and shortened the total sculpture path. This paper presented the hardware structure of the system, the GA-Hopfield neural network optimization algorithm and its simulation. The application has shown that the multi-axis motion control system has good stability and control accuracy.