期刊
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
卷 9, 期 1, 页码 64-74出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JAS.2021.1004275
关键词
Generative adversarial network (GAN); optimal path planning; robot path planning; sampling-based path planning
资金
- National Key R&D Program of China [2019YFB1312400]
- Shenzhen Key Laboratory of Robotics Perception and Intelligence [ZDSYS20200810171800001]
- Hong Kong RGC GRF [14200618]
- Hong Kong RGC CRF [C4063-18G]
The paper proposes an image-based path planning algorithm that uses a generative adversarial network for non-uniform sampling, overcoming limitations of sampling-based path planning methods and improving initial solution quality and convergence speed. Simulation experiments show that the method performs well in environments both similar and different from the training set.
Sampling-based path planning is a popular methodology for robot path planning. With a uniform sampling strategy to explore the state space, a feasible path can be found without the complex geometric modeling of the configuration space. However, the quality of the initial solution is not guaranteed, and the convergence speed to the optimal solution is slow. In this paper, we present a novel image-based path planning algorithm to overcome these limitations. Specifically, a generative adversarial network (GAN) is designed to take the environment map (denoted as RGB image) as the input without other preprocessing works. The output is also an RGB image where the promising region (where a feasible path probably exists) is segmented. This promising region is utilized as a heuristic to achieve non-uniform sampling for the path planner. We conduct a number of simulation experiments to validate the effectiveness of the proposed method, and the results demonstrate that our method performs much better in terms of the quality of the initial solution and the convergence speed to the optimal solution. Furthermore, apart from the environments similar to the training set, our method also works well on the environments which are very different from the training set.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据