Lifelong Robot Learning with Human Assisted Language Planners
This addresses the problem of enabling lifelong and open-world learning for robots, though it appears incremental as it builds on existing LLM-based planning methods.
The paper tackles the limitation of LLM-based planners being restricted to fixed skill sets by introducing a method that allows them to query and teach robots new skills for rigid object manipulation in a data- and time-efficient way, enabling skill reuse for lifelong learning and demonstrating evaluation in simulation and real-world tasks.
Large Language Models (LLMs) have been shown to act like planners that can decompose high-level instructions into a sequence of executable instructions. However, current LLM-based planners are only able to operate with a fixed set of skills. We overcome this critical limitation and present a method for using LLM-based planners to query new skills and teach robots these skills in a data and time-efficient manner for rigid object manipulation. Our system can re-use newly acquired skills for future tasks, demonstrating the potential of open world and lifelong learning. We evaluate the proposed framework on multiple tasks in simulation and the real world. Videos are available at: https://sites.google.com/mit.edu/halp-robot-learning.