Moving Out: Physically-grounded Human-AI Collaboration
This addresses the challenge of physically grounded human-AI collaboration for robotics, but it is incremental as it builds on existing benchmarks and methods.
The paper tackles the problem of enabling embodied agents to collaborate effectively with humans in physical environments by introducing the Moving Out benchmark, which includes tasks like moving heavy items together, and shows that their proposed BASS method outperforms state-of-the-art models in AI-AI and human-AI collaboration.
The ability to adapt to physical actions and constraints in an environment is crucial for embodied agents (e.g., robots) to effectively collaborate with humans. Such physically grounded human-AI collaboration must account for the increased complexity of the continuous state-action space and constrained dynamics caused by physical constraints. In this paper, we introduce Moving Out, a new human-AI collaboration benchmark that resembles a wide range of collaboration modes affected by physical attributes and constraints, such as moving heavy items together and maintaining consistent actions to move a big item around a corner. Using Moving Out, we designed two tasks and collected human-human interaction data to evaluate models' abilities to adapt to diverse human behaviors and unseen physical attributes. To address the challenges in physical environments, we propose a novel method, BASS (Behavior Augmentation, Simulation, and Selection), to enhance the diversity of agents and their understanding of the outcome of actions. Our experiments show that BASS outperforms state-of-the-art models in AI-AI and human-AI collaboration. The project page is available at https://live-robotics-uva.github.io/movingout_ai/.