Z.C. Jia

Pages: 3-12

Abstract
Aiming at the problems of low planning accuracy and long time-consuming in vehicle obstacle avoidance path planning method, a vehicle obstacle avoidance path planning method based on deep data mining is proposed. Firstly, the steering angle of obstacle vehicle is determined, the motion state is determined, and the obstacle data extraction is completed; Then, the obstacle operation data is placed in Cartesian coordinates to obtain a new state value and complete the preprocessing; Finally, determine the straight-line distance between the obstacle vehicle and the vehicle, build the vehicle obstacle avoidance path planning model with the help of deep data mining, input the obstacle data after training, output the path planning results, and introduce the error correction function to modify the output planning results to realize the vehicle obstacle avoidance path planning. The results show that the proposed method has high accuracy in obstacle avoidance path planning.
Keywords: deep data mining; obstacle; path planning; straight line distance; planning model; error correction