Moving Through Clutter: Scaling Data Collection and Benchmarking for 3D Scene-Aware Humanoid Locomotion via Virtual Reality

TL;DR

This paper introduces Moving Through Clutter, a VR-based framework for collecting and benchmarking humanoid locomotion data in complex, cluttered 3D environments, addressing a gap in scene-aware robot navigation research.

Contribution

It presents a novel VR system for data collection in cluttered scenes, a new dataset of human trajectories, and benchmarks for evaluating scene-aware humanoid locomotion performance.

Findings

Compiled 348 trajectories in 145 diverse scenes

Established benchmarks for stability and collision safety

Enabled analysis of geometry-induced locomotion adaptation

Abstract

Recent advances in humanoid locomotion have enabled dynamic behaviors such as dancing, martial arts, and parkour, yet these capabilities are predominantly demonstrated in open, flat, and obstacle-free settings. In contrast, real-world environments such as homes, offices, and public spaces, are densely cluttered, three-dimensional, and geometrically constrained, requiring scene-aware whole-body coordination, precise balance control, and reasoning over spatial constraints imposed by furniture and household objects. However, humanoid locomotion in cluttered 3D environments remains underexplored, and no public dataset systematically couples full-body human locomotion with the scene geometry that shapes it. To address this gap, we present Moving Through Clutter (MTC), an opensource Virtual Reality (VR) based data collection and evaluation framework for scene-aware humanoid locomotion in cluttered environments. Our system procedurally generates scenes with controllable clutter levels and captures embodiment-consistent, whole-body human motion through immersive VR navigation, which is then automatically retargeted to a humanoid robot model. We further introduce benchmarks that quantify environment clutter level and locomotion performance, including stability and collision safety. Using this framework, we compile a dataset of 348 trajectories across 145 diverse 3D cluttered scenes. The dataset provides a foundation for studying geometry-induced adaptation in humanoid locomotion and developing scene-aware planning and control methods.