Feasibility-Guided Planning over Multi-Specialized Locomotion Policies

TL;DR

This paper introduces a feasibility-guided planning framework that integrates multiple terrain-specific policies with classical planning algorithms, enabling efficient and reliable navigation over unstructured terrains in legged robotics.

Contribution

It presents a novel framework combining learned feasibility predictions with classical planning to handle multiple specialized locomotion policies without retraining.

Findings

Efficiently generates reliable plans across diverse terrains

Aligns planning with the capabilities of underlying policies

Works in both simulated and real-world environments

Abstract

Planning over unstructured terrain presents a significant challenge in the field of legged robotics. Although recent works in reinforcement learning have yielded various locomotion strategies, planning over multiple experts remains a complex issue. Existing approaches encounter several constraints: traditional planners are unable to integrate skill-specific policies, whereas hierarchical learning frameworks often lose interpretability and require retraining whenever new policies are added. In this paper, we propose a feasibility-guided planning framework that successfully incorporates multiple terrain-specific policies. Each policy is paired with a Feasibility-Net, which learned to predict feasibility tensors based on the local elevation maps and task vectors. This integration allows classical planning algorithms to derive optimal paths. Through both simulated and real-world experiments, we demonstrate that our method efficiently generates reliable plans across diverse and challenging terrains, while consistently aligning with the capabilities of the underlying policies.