Search-Based Task Planning with Learned Skill Effect Models for Lifelong Robotic Manipulation
This addresses the challenge of flexible adaptation to new skills and tasks in real-world robotic settings, representing an incremental improvement over prior methods with less restrictive assumptions.
The paper tackles the problem of lifelong robotic manipulation by proposing a search-based task planning approach that uses learned skill effect models, enabling robots to integrate new skills and find lower-cost strategies without task-specific assumptions.
Robots deployed in many real-world settings need to be able to acquire new skills and solve new tasks over time. Prior works on planning with skills often make assumptions on the structure of skills and tasks, such as subgoal skills, shared skill implementations, or task-specific plan skeletons, which limit adaptation to new skills and tasks. By contrast, we propose doing task planning by jointly searching in the space of parameterized skills using high-level skill effect models learned in simulation. We use an iterative training procedure to efficiently generate relevant data to train such models. Our approach allows flexible skill parameterizations and task specifications to facilitate lifelong learning in general-purpose domains. Experiments demonstrate the ability of our planner to integrate new skills in a lifelong manner, finding new task strategies with lower costs in both train and test tasks. We additionally show that our method can transfer to the real world without further fine-tuning.