paper-with-me

홈 › Papers

Trust the PRoC3S: Solving Long-Horizon Robotics Problems with LLMs and Constraint Satisfaction

2024-06-08 · Aidan Curtis, Nishanth Kumar, Jing Cao, Tomás Lozano-Pérez, Leslie Pack Kaelbling

Recent developments in pretrained large language models (LLMs) applied to robotics have demonstrated their capacity for sequencing a set of discrete skills to achieve open-ended goals in simple robotic tasks. In this paper, we examine the topic of LLM planning for a set of continuously parameterized skills whose execution must avoid violations of a set of kinematic, geometric, and physical constraints. We prompt the LLM to output code for a function with open parameters, which, together with environmental constraints, can be viewed as a Continuous Constraint Satisfaction Problem (CCSP). This CCSP can be solved through sampling or optimization to find a skill sequence and continuous parameter settings that achieve the goal while avoiding constraint violations. Additionally, we consider cases where the LLM proposes unsatisfiable CCSPs, such as those that are kinematically infeasible, dynamically unstable, or lead to collisions, and re-prompt the LLM to form a new CCSP accordingly. Experiments across three different simulated 3D domains demonstrate that our proposed strategy, PRoC3S, is capable of solving a wide range of complex manipulation tasks with realistic constraints on continuous parameters much more efficiently and effectively than existing baselines.

📄 PDF Abstract BibTeX arXiv:2406.05572

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks

2024-05-02 · Murtaza Dalal, Tarun Chiruvolu, Devendra Chaplot, Ruslan Salakhutdinov

Large Language Models (LLMs) have been shown to be capable of performing high-level planning for long-horizon robotics tasks, yet existing methods require access to a pre-defined skill library (e.g. picking, placing, pul…

Language ModelingLanguage ModellingMotion PlanningReinforcement Learning (RL)

Triple-S: A Collaborative Multi-LLM Framework for Solving Long-Horizon Implicative Tasks in Robotics

2025-08-10 · Zixi Jia, Hongbin Gao, Fashe Li, Jiqiang Liu 외 arxiv

Leveraging Large Language Models (LLMs) to write policy code for controlling robots has gained significant attention. However, in long-horizon implicative tasks, this approach often results in API parameter, comments and…

Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks

2022-06-03 · Andrew C. Li, Pashootan Vaezipoor, Rodrigo Toro Icarte, Sheila A. McIlraith

Deep reinforcement learning has shown promise in discrete domains requiring complex reasoning, including games such as Chess, Go, and Hanabi. However, this type of reasoning is less often observed in long-horizon, contin…

Deep Reinforcement Learning

EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics

2026-09-23 · Haoxiang You, Zeyu Shen, Yilang Liu, Zhicheng Zheng 외 hf

We study coding agents for long-horizon, dexterous robotics and ask whether their solutions can provide scalable supervision for learning general robot policies. To test this, we develop EMBODIEDSWE-BENCH, a simulation b…

Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS

2026-05-25 · Bingyu Yan, Xiaoming Zhang, Jinyu Hou, Chaozhuo Li 외 arxiv

While Large Language Model-based Multi-Agent Systems (LLM-MAS) demonstrate remarkable capabilities in solving complex tasks by orchestrating specialized agents and external tools, the implicit trust in tool outputs creat…

Reinforcement Learning