Hindsight Planner: A Closed-Loop Few-Shot Planner for Embodied Instruction Following
This addresses robustness issues in embodied AI for task planning, but it is incremental as it builds on existing LLM-based methods with a novel adaptation approach.
The paper tackles the problem of building a robust task planner for Embodied Instruction Following by framing it as a POMDP and proposing a closed-loop planner with a hindsight method, achieving competitive performance on the ALFRED dataset where the few-shot agent approaches or surpasses full-shot supervised agents.
This work focuses on building a task planner for Embodied Instruction Following (EIF) using Large Language Models (LLMs). Previous works typically train a planner to imitate expert trajectories, treating this as a supervised task. While these methods achieve competitive performance, they often lack sufficient robustness. When a suboptimal action is taken, the planner may encounter an out-of-distribution state, which can lead to task failure. In contrast, we frame the task as a Partially Observable Markov Decision Process (POMDP) and aim to develop a robust planner under a few-shot assumption. Thus, we propose a closed-loop planner with an adaptation module and a novel hindsight method, aiming to use as much information as possible to assist the planner. Our experiments on the ALFRED dataset indicate that our planner achieves competitive performance under a few-shot assumption. For the first time, our few-shot agent's performance approaches and even surpasses that of the full-shot supervised agent.