Vehicle motion planning method and unmanned vehicle

Abstract

The inventor provides a vehicle motion planning method and an unmanned vehicle, and relates to the field of unmanned vehicles, and especially relates to an unmanned vehicle motion planning. The method comprises: according to n travelling paths, updating probability distribution of an experienced region, in a vehicle motion process, according to the updated probability distribution of the experienced region, combined with probability of vehicle state conversion, calculating probability to transfer to an adjacent grid; according to the probability to transfer to the adjacent grid, expanding a random tree, and doing collision detection, if the vehicle passes the collision detection, using the corresponding grid to expand the random tree, and updating a current state; until all grids have been tried and the vehicle cannot pass the collision detection, or the vehicle has reached an objective grid. In the method, n actual paths are converted to probability to represent, and are applied in the path planning method, and according to the state information of the vehicle, the probability to transfer to the corresponding grid is calculated, so a motion planning module makes full use of the experiential knowledge to improve search efficiency.

Description

technical field [0001] The invention relates to the field of unmanned vehicles, in particular to motion planning for unmanned vehicles. Background technique [0002] The motion planning module of the unmanned vehicle / robot converts the abstract motion target (start / end point), limit (speed / obstacle) and other instructions into a trajectory that the robot / unmanned vehicle can specifically execute (from the start point to the end point, between meet various constraints and requirements) and the corresponding control parameters to achieve this trajectory. [0003] The motion planning module of the unmanned vehicle needs to find an optimal path in all achievable states. The dimensions of all achievable states may be very large, so the search space of the algorithm for searching the optimal path is very large. Due to the limitation of time and the computing power of the on-board computer, it is generally unrealistic to find the optimal path. [0004] In existing motion planning...

AI Technical Summary

Problems solved by technology

The dimensions of all achievable states may be very large, so the search space of the algorithm for searching the optimal path is very large. Due to the limitation of time and the computing power of the on-board computer, it is generally unrealistic to find the optimal path

[0004] In existing motion planning algorithms such as RRT (algorithms based on random sampling), it is impossible to deal with avoidance and safe area information in some dangerous areas, and the danger / safety of the area corresponds to automatic driving and can include various road conditions that cannot be directly represented.

Images