CLIMB: Language-Guided Continual Learning for Task Planning with Iterative Model Building

TL;DR

CLIMB is a continual learning framework that uses foundation models and feedback to iteratively build and improve task planning domain models from natural language descriptions, enhancing robotic planning capabilities.

Contribution

This work introduces CLIMB, a novel framework that enables robots to learn and refine task planning models continually from language and experience, including non-obvious predicates.

Findings

CLIMB outperforms baseline methods in planning environments.

It can learn non-obvious predicates during task solving.

The BlocksWorld++ domain facilitates evaluation of continual learning.

Abstract

Intelligent and reliable task planning is a core capability for generalized robotics, requiring a descriptive domain representation that sufficiently models all object and state information for the scene. We present CLIMB, a continual learning framework for robot task planning that leverages foundation models and execution feedback to guide domain model construction. CLIMB can build a model from a natural language description, learn non-obvious predicates while solving tasks, and store that information for future problems. We demonstrate the ability of CLIMB to improve performance in common planning environments compared to baseline methods. We also develop the BlocksWorld++ domain, a simulated environment with an easily usable real counterpart, together with a curriculum of tasks with progressing difficulty for evaluating continual learning. Additional details and demonstrations for this system can be found at https://plan-with-climb.github.io/ .