S2P2: Self-Supervised Goal-Directed Path Planning Using RGB-D Data for Robotic Wheelchairs
This work addresses the challenge of efficient and precise navigation for robotic wheelchairs, offering a solution that reduces data collection burdens and improves performance, though it is incremental in advancing self-supervised methods for a specific domain.
The paper tackles the problem of path planning for robotic wheelchairs by proposing S2P2, a self-supervised approach that automatically generates training data from RGB-D images and goal poses, eliminating the need for expert demonstrations and enabling exact goal-directed navigation, with experimental results showing it outperforms traditional algorithms and enhances the robustness of existing map-based systems.
Path planning is a fundamental capability for autonomous navigation of robotic wheelchairs. With the impressive development of deep-learning technologies, imitation learning-based path planning approaches have achieved effective results in recent years. However, the disadvantages of these approaches are twofold: 1) they may need extensive time and labor to record expert demonstrations as training data; and 2) existing approaches could only receive high-level commands, such as turning left/right. These commands could be less sufficient for the navigation of mobile robots (e.g., robotic wheelchairs), which usually require exact poses of goals. We contribute a solution to this problem by proposing S2P2, a self-supervised goal-directed path planning approach. Specifically, we develop a pipeline to automatically generate planned path labels given as input RGB-D images and poses of goals. Then, we present a best-fit regression plane loss to train our data-driven path planning model based on the generated labels. Our S2P2 does not need pre-built maps, but it can be integrated into existing map-based navigation systems through our framework. Experimental results show that our S2P2 outperforms traditional path planning algorithms, and increases the robustness of existing map-based navigation systems. Our project page is available at https://sites.google.com/view/s2p2.