Mimicking-Bench: A Benchmark for Generalizable Humanoid-Scene Interaction Learning via Human Mimicking
This work addresses the need for scalable benchmarks in robotics to improve humanoid-scene interaction learning, though it is incremental as it builds on prior imitation learning methods with a new dataset.
The paper tackles the problem of learning generalizable humanoid robot skills for interacting with 3D scenes by mimicking human data, introducing Mimicking-Bench as a comprehensive benchmark with 11K object shapes and 23K human references to address limitations in existing small-scale datasets.
Learning generic skills for humanoid robots interacting with 3D scenes by mimicking human data is a key research challenge with significant implications for robotics and real-world applications. However, existing methodologies and benchmarks are constrained by the use of small-scale, manually collected demonstrations, lacking the general dataset and benchmark support necessary to explore scene geometry generalization effectively. To address this gap, we introduce Mimicking-Bench, the first comprehensive benchmark designed for generalizable humanoid-scene interaction learning through mimicking large-scale human animation references. Mimicking-Bench includes six household full-body humanoid-scene interaction tasks, covering 11K diverse object shapes, along with 20K synthetic and 3K real-world human interaction skill references. We construct a complete humanoid skill learning pipeline and benchmark approaches for motion retargeting, motion tracking, imitation learning, and their various combinations. Extensive experiments highlight the value of human mimicking for skill learning, revealing key challenges and research directions.