Hierarchical RL-Guided Large-scale Navigation of a Snake Robot

Shuo Jiang, Adarsh Salagame, Alireza Ramezani, Lawson L. S. Wong

Abstract

Classical snake robot control leverages mimicking snake-like gaits tuned for specific environments. However, to operate adaptively in unstructured environments, gait generation must be dynamically scheduled. In this work, we present a four-layer hierarchical control scheme to enable the snake robot to navigate freely in large-scale environments. The proposed model decomposes navigation into global planning, local planning, gait generation, and gait tracking. Using reinforcement learning (RL) and a central pattern generator (CPG), our method learns to navigate in complex mazes within hours and can be directly deployed to arbitrary new environments in a zero-shot fashion. We use the high-fidelity model of Northeastern's slithering robot COBRA to test the effectiveness of the proposed hierarchical control approach.
BibTeX
@inproceedings{jiang2024hierarchical,
  author = {Shuo Jiang and Adarsh Salagame and Alireza Ramezani and Lawson L. S. Wong},
  title = {{Hierarchical RL-Guided Large-scale Navigation of a Snake Robot}},
  booktitle = {AIM},
  year = {2024},
  url = {https://openreview.net/forum?id=09ez5sUGpo},
}

Loading related content...

Figure