Policy Adaptation via Language Optimization: Decomposing Tasks for Few-Shot Imitation
This addresses the challenge of few-shot adaptation for robot manipulation, enabling more efficient learning in real-world scenarios.
The paper tackles the problem of adapting robot policies to new tasks with few demonstrations by using vision-language models to decompose tasks semantically, achieving consistent completion of long-horizon manipulation tasks and outperforming state-of-the-art methods.
Learned language-conditioned robot policies often struggle to effectively adapt to new real-world tasks even when pre-trained across a diverse set of instructions. We propose a novel approach for few-shot adaptation to unseen tasks that exploits the semantic understanding of task decomposition provided by vision-language models (VLMs). Our method, Policy Adaptation via Language Optimization (PALO), combines a handful of demonstrations of a task with proposed language decompositions sampled from a VLM to quickly enable rapid nonparametric adaptation, avoiding the need for a larger fine-tuning dataset. We evaluate PALO on extensive real-world experiments consisting of challenging unseen, long-horizon robot manipulation tasks. We find that PALO is able of consistently complete long-horizon, multi-tier tasks in the real world, outperforming state of the art pre-trained generalist policies, and methods that have access to the same demonstrations.