Omnidirectional Humanoid Locomotion on Stairs via Unsafe Stepping Penalty and Sparse LiDAR Elevation Mapping

2026-03-09

AI Summary

This work addresses the challenges of safe omnidirectional stair traversal for humanoid robots, which are hindered by perceptual blind spots from forward-facing depth cameras and inefficient learning due to sparse penalty signals for hazardous footholds. The authors propose a single-stage training framework that integrates a dense hazardous-foothold penalty mechanism with a sparse LiDAR-based rolling elevation mapping system. Terrain perception stability is enhanced through spatiotemporal confidence decay and self-protection zones, while an edge-guided asymmetric U-Net mitigates reconstruction distortion on stair risers. Experiments demonstrate nearly 100% safe foothold placement on stairs in simulation, high safety during real-world deployment, and successful long-distance outdoor navigation across complex terrain, confirming strong sim-to-real transferability and long-term operational stability.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Natural Language Processing: Safety and Robustness

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Humanoid robots, characterized by numerous degrees of freedom and a high center of gravity, are inherently unstable. Safe omnidirectional locomotion on stairs requires both omnidirectional terrain perception and reliable foothold selection. Existing methods often rely on forward-facing depth cameras, which create blind zones that restrict omnidirectional mobility. Furthermore, sparse post-contact unsafe stepping penalties lead to low learning efficiency and suboptimal strategies. To realize safe stair-traversal gaits, this paper introduces a single-stage training framework incorporating a dense unsafe stepping penalty that provides continuous feedback as the foot approaches a hazardous placement. To obtain stable and reliable elevation maps, we build a rolling point-cloud mapping system with spatiotemporal confidence decay and a self-protection zone mechanism, producing temporally consistent local maps. These maps are further refined by an Edge-Guided Asymmetric U-Net (EGAU), which mitigates reconstruction distortion caused by sparse LiDAR returns on stair risers. Simulation and real-robot experiments show that the proposed method achieves a near-100\% safe stepping rate on stair terrains in simulation, while maintaining a remarkably high safe stepping rate in real-world deployments. Furthermore, it completes a continuous long-distance walking test on complex outdoor terrains, demonstrating reliable sim-to-real transfer and long-term stability.

Problem

• omnidirectional locomotion
• stair traversal
• unsafe stepping
• terrain perception
• humanoid robot

Innovation

• dense unsafe stepping penalty
• sparse LiDAR elevation mapping
• Edge-Guided Asymmetric U-Net
• omnidirectional locomotion
• sim-to-real transfer