PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 13, 20242 citationsOpen Access

Grounding LLMs For Robot Task Planning Using Closed-loop State Feedback

View Full Paper
VBVineet BhatAKAli Umut KaypakPKP. Krishnamurthy

Key Points

Key points are not available for this paper at this time.

Abstract

Robotic planning algorithms direct agents to perform actions within diverse environments to accomplish a task. Large Language Models (LLMs) like PaLM 2, GPT-3.5, and GPT-4 have revolutionized this domain, using their embedded real-world knowledge to tackle complex tasks involving multiple agents and objects. This paper introduces an innovative planning algorithm that integrates LLMs into the robotics context, enhancing task-focused execution and success rates. Key to our algorithm is a closed-loop feedback which provides real-time environmental states and error messages, crucial for refining plans when discrepancies arise. The algorithm draws inspiration from the human neural system, emulating its brain-body architecture by dividing planning across two LLMs in a structured, hierarchical fashion. Our method not only surpasses baselines within the VirtualHome Environment, registering a notable 35% average increase in task-oriented success rates, but achieves an impressive execution score of 85%, approaching the human-level benchmark of 94%. Moreover, effectiveness of the algorithm in real robot scenarios is shown using a realistic physics simulator and the Franka Research 3 Arm.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Bhat et al. (2024) studied this question.

synapsesocial.com/papers/68e79591b6db643587706cfehttps://doi.org/10.48550/arxiv.2402.08546
Ask AI
Helpful
Bookmark
Share
View Full Paper

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Generalized Planning in PDDL Domains with Pretrained Large Language Models2024 · 70 citations
  2. 2SayNav: Grounding Large Language Models for Dynamic Planning to Navigation in New Environments2024 · 64 citations
  3. 3Safe Navigation and Obstacle Avoidance Using Differentiable Optimization Based Control Barrier Functions2023 · 45 citations
  4. 4Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models2025 · 48 citations
  5. 5Grounding DINO: Marrying DINO with Grounded Pre-training for Open-Set Object Detection2024 · 1,690 citations