Feasibility-guided planning enables optimal path selection & policy switching over mixed terrain via policy-specific feasibility representations.
Video Presentation
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.
Methodology
Locomotion policies and Feasibility-Net models are jointly trained using shared environment rollouts,
where the feasibility models learn to predict velocity tracking performance and terrain distributions simultaneously with policy optimization.
Sliding window methodology for elevation map to feasibility tensor transformation.
Local heightmap patches are extracted at each spatial location and processed through multiple directions to generate policy-specific feasibility predictions.
Individual policy-specific feasibility representations are combined through maximum fusion to create unified cost functions,
enabling graph search algorithms to discover optimal paths with transparent policy selection.
Specialized Policies - Simulation
Steps Policy
Gaps Policy
Bridge Policy
Valley Policy
Specialized Policies - Real-world
Steps Policy
Gaps Policy
Bridge Policy
Valley Policy
Deployment - Simulation
The specialized policies achieve near-optimal performance within their respective domains.
The general policy demonstrates moderate performance on certain terrain types, but suffers complete failure on others.
When multiple paths are available, the feasibility-guided planner selects the most feasible one.
Deployment - Real-world
The Feasibility-Net successfully selects appropriate policies at optimal locations while maintaining feasible trajectory generation,
achieving an overall success rate of 70% for complete mixed terrain traversal under 20 attempts.
First image description.
Second image description.
Third image description.
Fourth image description.
Another Carousel
Poster
BibTeX
@article{Luo2026feasibilityguidedplanning,
title={Feasibility-Guided Planning over Multi-Specialized Locomotion Policies},
author={Ying-Sheng Luo and Lu-Ching Wang and Hanjaya Mandala and Yu-Lun Chou and Guilherme Christmann and Yu-Chung Chen and Yung-Shun Chan and Chun-Yi Lee and Wei-Chao Chen},
booktitle={2026 IEEE International Conference on Robotics and Automation (ICRA)},
year={2026},
}
