Harmonic Mobile Manipulation
This addresses the challenge of enabling practical indoor robot deployment for daily life tasks, representing a strong specific gain in mobile manipulation.
The paper tackles the problem of robots performing household tasks requiring coordinated navigation and manipulation, such as opening doors, by introducing HarmonicMM, an end-to-end learning method that shows notable improvement over existing techniques in simulated and real-world environments, adapting to novel unseen settings without additional tuning.
Recent advancements in robotics have enabled robots to navigate complex scenes or manipulate diverse objects independently. However, robots are still impotent in many household tasks requiring coordinated behaviors such as opening doors. The factorization of navigation and manipulation, while effective for some tasks, fails in scenarios requiring coordinated actions. To address this challenge, we introduce, HarmonicMM, an end-to-end learning method that optimizes both navigation and manipulation, showing notable improvement over existing techniques in everyday tasks. This approach is validated in simulated and real-world environments and adapts to novel unseen settings without additional tuning. Our contributions include a new benchmark for mobile manipulation and the successful deployment with only RGB visual observation in a real unseen apartment, demonstrating the potential for practical indoor robot deployment in daily life. More results are on our project site: https://rchalyang.github.io/HarmonicMM/