LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916563396853760 |
|---|---|
| author | Nayak, Siddharth Orozco, Adelmo Morrison Have, Marina Ten Thirumalai, Vittal Zhang, Jackson Chen, Darren Kapoor, Aditya Robinson, Eric Gopalakrishnan, Karthik Harrison, James Ichter, Brian Mahajan, Anuj Balakrishnan, Hamsa |
| author_facet | Nayak, Siddharth Orozco, Adelmo Morrison Have, Marina Ten Thirumalai, Vittal Zhang, Jackson Chen, Darren Kapoor, Aditya Robinson, Eric Gopalakrishnan, Karthik Harrison, James Ichter, Brian Mahajan, Anuj Balakrishnan, Hamsa |
| contents | The ability of Language Models (LMs) to understand natural language makes them a powerful tool for parsing human instructions into task plans for autonomous robots. Unlike traditional planning methods that rely on domain-specific knowledge and handcrafted rules, LMs generalize from diverse data and adapt to various tasks with minimal tuning, acting as a compressed knowledge base. However, LMs in their standard form face challenges with long-horizon tasks, particularly in partially observable multi-agent settings. We propose an LM-based Long-Horizon Planner for Multi-Agent Robotics (LLaMAR), a cognitive architecture for planning that achieves state-of-the-art results in long-horizon tasks within partially observable environments. LLaMAR employs a plan-act-correct-verify framework, allowing self-correction from action execution feedback without relying on oracles or simulators. Additionally, we present MAP-THOR, a comprehensive test suite encompassing household tasks of varying complexity within the AI2-THOR environment. Experiments show that LLaMAR achieves a 30% higher success rate than other state-of-the-art LM-based multi-agent planners in MAP-THOR and Search \& Rescue tasks. Code can be found at https://github.com/nsidn98/LLaMAR |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_10031 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments Nayak, Siddharth Orozco, Adelmo Morrison Have, Marina Ten Thirumalai, Vittal Zhang, Jackson Chen, Darren Kapoor, Aditya Robinson, Eric Gopalakrishnan, Karthik Harrison, James Ichter, Brian Mahajan, Anuj Balakrishnan, Hamsa Robotics Multiagent Systems The ability of Language Models (LMs) to understand natural language makes them a powerful tool for parsing human instructions into task plans for autonomous robots. Unlike traditional planning methods that rely on domain-specific knowledge and handcrafted rules, LMs generalize from diverse data and adapt to various tasks with minimal tuning, acting as a compressed knowledge base. However, LMs in their standard form face challenges with long-horizon tasks, particularly in partially observable multi-agent settings. We propose an LM-based Long-Horizon Planner for Multi-Agent Robotics (LLaMAR), a cognitive architecture for planning that achieves state-of-the-art results in long-horizon tasks within partially observable environments. LLaMAR employs a plan-act-correct-verify framework, allowing self-correction from action execution feedback without relying on oracles or simulators. Additionally, we present MAP-THOR, a comprehensive test suite encompassing household tasks of varying complexity within the AI2-THOR environment. Experiments show that LLaMAR achieves a 30% higher success rate than other state-of-the-art LM-based multi-agent planners in MAP-THOR and Search \& Rescue tasks. Code can be found at https://github.com/nsidn98/LLaMAR |
| title | LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments |
| topic | Robotics Multiagent Systems |
| url | https://arxiv.org/abs/2407.10031 |