A path planning method for unmanned vehicles based on flow field

Abstract

The invention relates to a path planning method for an unmanned vehicle based on a flow field, which includes the following steps: establishing a flow field calculation model according to the starting point and end point of the vehicle and obstacles in the environment; The vehicle kinematics model is established as the state quantity; the vehicle kinematics model is used as the rolling equation to solve the rolling time-domain optimization problem of the flow field, and the velocity vector distribution of the flow field is used as the guiding information for path planning to obtain the planned path. is the front wheel angle, the optimization objective includes the consistency between the vehicle motion and the flow field motion and the vehicle does not collide with obstacles during the motion process, and the constraint condition is that the front wheel angle does not exceed the maximum steering wheel angle. Compared with the prior art, the present invention can find a smooth and obstacle-avoiding path connecting the start point and the end point in complex terrain. On the premise of obstacle avoidance, the smoothness and completeness of the path achieve good results at the same time.

Description

technical field [0001] The invention relates to a path planning method for an unmanned vehicle, in particular to a path planning method for an unmanned vehicle based on a flow field. Background technique [0002] A driverless car is a smart car that can drive autonomously without a driver. Unmanned vehicles generally use on-board sensors such as lidar, vision sensors, and millimeter-wave radars to perceive the surrounding environment of the vehicle, and make decisions about the behavior to be executed based on the environmental information obtained from environmental perception. Generate the required reference trajectory based on the behavior, and control the steering and speed of the vehicle accordingly, so that the vehicle can drive safely and reliably on the road. Unmanned vehicles have fundamentally changed the traditional closed-loop control mode of "people-vehicle-road" and removed uncontrollable drivers from the closed-loop system, thereby greatly improving the effic...

AI Technical Summary

Problems solved by technology

However, the disadvantage of this method is that it cannot be applied to non-integrity systems, and the path is not smooth

[0009] To sum up, the existing planning methods are often unable to achieve good results in the two indicators of smooth path and solving complex terrain.

In addition, unmanned vehicles have specific structural and kinematic characteristics. When planning the path of unmanned vehicles, it is necessary to consider the constraints of the model. That is to say, for paths that do not satisfy the model constraints, unmanned vehicles cannot execute of

Images