PolygMap: A Perceptive Locomotion Framework for Humanoid Robot Stair Climbing
Bingquan Li, Ning Wang, Zhicheng He, Yucong Wu, Tianwei Zhang
AI summary
Problem
Humanoid robots lack explicit perception of stair geometry during locomotion, leading to conservative gaits, footstep uncertainty, and odometry drift from vibration and sensor noise. Existing systems often rely on reactive balancing rather than proactive, perception-driven foothold planning.
Approach
PolygMap fuses LiDAR, RGB-D depth, and IMU data to construct a real-time polygonal semantic map of staircases, which is then used to extract safe footholds and generate collision-free whole-body trajectories at 20–30 Hz.
Key results
- Multi-sensor fusion reduces odometry drift and suppresses high-frequency noise
- Real-time polygonal mapping enables robust foothold extraction under varying conditions
- Safe-region trajectory planner achieves 20–30 Hz whole-body motion planning
- Validated through indoor and outdoor real-world stair climbing experiments
Why it matters
Provides a deployable perception-planning pipeline that enhances humanoid robot reliability in unstructured environments for inspection, rescue, and industrial applications.
Abstract
Recently, biped robot walking technology has been significantly developed, mainly in the context of a bland walking scheme. To emulate human walking, robots need to step on the positions they see in unknown spaces accurately. In this paper, we present PolyMap, a perception-based locomotion planning framework for humanoid robots to climb stairs. Our core idea is to build a real-time polygonal staircase plane semantic map, followed by a footstep planar using these polygonal plane segments. These plane segmentation and visual odometry are done by multi-sensor fusion(LiDAR, RGB- D camera and IMUs). The proposed framework is deployed on a NVIDIA Orin, which performs 20-30 Hz whole-body motion planning output. Both indoor and outdoor real-scene experiments indicate that our method is efficient and robust for humanoid robot stair climbing.