Embodied Lifelong Learning for Task and Motion Planning
This addresses the incremental challenge of enabling robots to continuously improve their task and motion planning skills through accumulated experience in real-world settings like homes.
The paper tackles the problem of lifelong learning for robots in home environments by formalizing a novel lifelong learning approach for task and motion planning (TAMP), resulting in substantial improvements in planning success over time and compared to baselines in 2D and BEHAVIOR domains.
A robot deployed in a home over long stretches of time faces a true lifelong learning problem. As it seeks to provide assistance to its users, the robot should leverage any accumulated experience to improve its own knowledge and proficiency. We formalize this setting with a novel formulation of lifelong learning for task and motion planning (TAMP), which endows our learner with the compositionality of TAMP systems. Exploiting the modularity of TAMP, we develop a mixture of generative models that produces candidate continuous parameters for a planner. Whereas most existing lifelong learning approaches determine a priori how data is shared across various models, our approach learns shared and non-shared models and determines which to use online during planning based on auxiliary tasks that serve as a proxy for each model's understanding of a state. Our method exhibits substantial improvements (over time and compared to baselines) in planning success on 2D and BEHAVIOR domains.