The reviewed record of science sign in
Pith

arxiv: 2506.02206 · v1 · pith:KXFBMM6H · submitted 2025-06-02 · cs.RO

Reinforcement Learning with Data Bootstrapping for Dynamic Subgoal Pursuit in Humanoid Robot Navigation

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:KXFBMM6Hrecord.jsonopen to challenge →

classification cs.RO
keywords navigationrobothumanoidmethodbootstrappingdatadynamicframework
0
0 comments X
read the original abstract

Safe and real-time navigation is fundamental for humanoid robot applications. However, existing bipedal robot navigation frameworks often struggle to balance computational efficiency with the precision required for stable locomotion. We propose a novel hierarchical framework that continuously generates dynamic subgoals to guide the robot through cluttered environments. Our method comprises a high-level reinforcement learning (RL) planner for subgoal selection in a robot-centric coordinate system and a low-level Model Predictive Control (MPC) based planner which produces robust walking gaits to reach these subgoals. To expedite and stabilize the training process, we incorporate a data bootstrapping technique that leverages a model-based navigation approach to generate a diverse, informative dataset. We validate our method in simulation using the Agility Robotics Digit humanoid across multiple scenarios with random obstacles. Results show that our framework significantly improves navigation success rates and adaptability compared to both the original model-based method and other learning-based methods.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.