Generative Adversarial Network based Heuristics for Sampling-based Path Planning
This work aims to improve the efficiency and solution quality of sampling-based path planning for robotics, which is an incremental improvement for robot navigation.
This paper addresses the limitations of sampling-based path planning, specifically the poor quality of initial solutions and slow convergence. The authors propose a GAN-based image processing method that takes an environment map as input and outputs a segmented "promising region" to guide non-uniform sampling for path planners, resulting in improved initial solution quality and faster convergence.
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 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 nonuniform 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 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.