Moving Through Clutter: Scaling Data Collection and Benchmarking for 3D Scene-Aware Humanoid Locomotion via Virtual Reality
This addresses a gap for robotics researchers by providing a foundational dataset and benchmarks for studying humanoid navigation in real-world cluttered settings, though it is incremental as it focuses on data collection rather than novel algorithms.
The paper tackles the lack of data and benchmarks for humanoid locomotion in cluttered 3D environments by introducing Moving Through Clutter (MTC), a VR-based framework that generated a dataset of 348 trajectories across 145 scenes to enable scene-aware planning and control.
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.