Learning-based Fast Path Planning in Complex Environments

Liu，Jianbang1; Li，Baopu2; Li，Tingguang3; Chi，Wenzheng4; Wang，Jiankun5; Meng，Max Q.H.1,6

10.1109/ROBIO54168.2021.9739261

2021

978-1-6654-0536-2

2021 IEEE International Conference on Robotics and Biomimetics, ROBIO 2021

1351-1358

27-31 Dec. 2021

Sanya, China

In this paper, we present a novel path planning algorithm to achieve fast path planning in complex environments. Most existing path planning algorithms are difficult to quickly find a feasible path in complex environments or even fail. However, our proposed framework can overcome this difficulty by using a learning-based prediction module and a sampling-based path planning module. The prediction module utilizes an auto-encoder-decoder-like convolutional neural network (CNN) to output a promising region where the feasible path probably lies in. In this process, the environment is treated as RGB image to feed in our designed CNN module, and the output is also RGB image. No extra computation is required so that we can maintain a high processing speed of 60 frame-per-second (FPS). Incorporated with a sampling-based path planner, we can extract a feasible path from the output image so that the robot can track it from start to goal. To demonstrate the advantage of the proposed algorithm, we compare it with conventional path planning algorithms in a series of simulation experiments. The results reveal that the proposed algorithm can achieve much better performance in terms of planning time, success rate, and path length.

Conferences Biomimetics Biological system modeling Prediction algorithms Path planning Planning Convolutional neural networks

通讯

英语

EI

20221611977456

Complex networks ; Convolutional neural networks

Computer Systems and Equipment:722

2-s2.0-85128184868

Scopus

1.Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong,Hong Kong
2.Baidu Research (US),United States
3.Tencent Robotics X,Shenzhen,China
4.Soochow University,School of Mechanical and Electric Engineering,Suzhou,China
5.Southern University of Science and Technology,Department of Electronic and Electrical Engineering,Shenzhen,China
6.Shenzhen Research Institute,Chinese University of Hong Kong,Shenzhen,China

Liu，Jianbang,Li，Baopu,Li，Tingguang,et al. Learning-based Fast Path Planning in Complex Environments[C],2021:1351-1358.