Local dynamic obstacle avoidance path planning method for unmanned vehicle

Abstract

The invention provides a local dynamic obstacle avoidance path planning method for an unmanned vehicle, which solves the problems of target inaccessibility and local optimum under partial working conditions of a traditional artificial potential field method by improving the artificial potential field method, and enables the unmanned vehicle to overcome local oscillation, thereby being capable of planning a local planning path meeting obstacle avoidance requirements. According to the method, in the path planning process, vehicle kinematics and dynamics performance requirements are added, the collision safety priority is set, the smoothness of the planned path is guaranteed, and the tracking requirement of a lower-layer vehicle tracker is met; by analyzing the working conditions of complex dynamic obstacles in the road environment, obstacle avoidance planning can be performed for lateral dynamic obstacles and same-direction obstacles, and the two working conditions are combined, so that the planning algorithm meets obstacle avoidance under the working conditions of multiple dynamic obstacles, and the applicability and effectiveness of the planning algorithm are improved.

Description

technical field [0001] The invention belongs to the technical field of automatic driving of unmanned vehicles, and in particular relates to a local dynamic obstacle avoidance path planning method for unmanned vehicles. Background technique [0002] As one of the key technologies in the field of unmanned vehicles, path planning determines whether unmanned vehicles can drive smoothly and safely, and it also acts as a bridge between vehicle environmental information perception and vehicle intelligent control functions. At present, the path planning algorithms used in unmanned vehicles mainly include A * 、D * , fast random tree and other algorithms. Although these algorithms have been initially applied to many real vehicle platforms, they are all limited by the disadvantage of their own high computational complexity, and currently they can only be used for static planning. Due to its simple model structure, the artificial potential field method can avoid obstacles and complete...

AI Technical Summary

Problems solved by technology

[0003] 1. In the complex environment, there are problems such as unreachable targets and local optimum, which lead to local oscillation or stagnation of unmanned vehicles, which do not meet the requirements of local obstacle avoidance planning;

[0004] 2. Most of the potential field method path planning does not consider the vehicle kinematics and dynamic performance, resulting in the planned path not meeting the vehicle tracking requirements;

[0005] 3. Most potential field method planning algorithms are applicable to static scenes or simple dynamic scenes. When there are complex dynamic obstacles in the road environment, the planning algorithm cannot effectively plan an obstacle avoidance path in real time.

Images