Jacky Liang*, Mohit Sharma*, Alex LaGrassa, Shivam Vats, Saumya Saxena, Oliver Kroemer
* Equal Contribution
Robotics Institute, Carnegie Mellon University, USA
[arxiv] [ICRA'22]
Lifelong-learning robots need to be able to acquire new skills and plan for new tasks over time. Prior works on planning with skills often make assumptions on the structure of skills and tasks, like subgoal skills, shared skill implementations, or learning task-specific plan skeletons, that limit their application to new and different skills and tasks. By contrast, we propose doing task planning by jointly searching in the space of skills and their parameters with skill effect models learned in simulation. Our approach is flexible about skill parameterizations and task specifications, and we use an iterative training procedure to efficiently generate relevant data to train such models. 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 supports planning in both state and latent spaces, and it can transfer to the real world without further fine-tuning.
Additional results including generalization results can be found in the Experiment Results page.