Vote-Tree-Planner: Optimizing Execution Order in LLM-based Task Planning Pipeline via Voting

TL;DR

Vote-Tree-Planner introduces a voting-based sampling strategy to optimize execution order in LLM-driven robotic task planning, reducing redundancy and improving success rates and efficiency.

Contribution

It presents a novel voting-guided plan traversal method that enhances planning effectiveness and reduces LLM query frequency in task planning systems.

Findings

Higher success rate on unseen datasets

Reduced number of LLM queries

Improved planning stability and accuracy

Abstract

Integrating large language models (LLMs) into closed-loop robotic task planning has become increasingly popular within embodied artificial intelligence. Previous efforts mainly focused on leveraging the strong reasoning abilities of LLMs to enhance task planning performance while often overlooking task planning efficiency and executability due to repetitive queries to LLMs. This paper addresses the synergy between LLMs and task planning systems, aiming to minimize redundancy while enhancing planning effectiveness. Specifically, building upon Prog-Prompt and the high-level concept of Tree-Planner, we propose Vote-Tree-Planner. This sampling strategy utilizes votes to guide plan traversal during the decision-making process. Our approach is motivated by a straightforward observation: assigning weights to agents during decision-making enables the evaluation of critical paths before execution. With this simple vote-tree construction, our method further improves the success rate and reduces the number of queries to LLMs. The experimental results highlight that our Vote-Tree-Planner demonstrates greater stability and shows a higher average success rate and goal condition recall on the unseen dataset compared with previous baseline methods. These findings underscore the potential of the Vote-Tree-Planner to enhance planning accuracy, reliability, and efficiency in LLM-based planning systems.