CLEA: Closed-Loop Embodied Agent for Enhancing Task Execution in Dynamic Environments
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929738434478080 |
|---|---|
| author | Lei, Mingcong Wang, Ge Zhao, Yiming Mai, Zhixin Zhao, Qing Guo, Yao Li, Zhen Cui, Shuguang Han, Yatong Ren, Jinke |
| author_facet | Lei, Mingcong Wang, Ge Zhao, Yiming Mai, Zhixin Zhao, Qing Guo, Yao Li, Zhen Cui, Shuguang Han, Yatong Ren, Jinke |
| contents | Large Language Models (LLMs) exhibit remarkable capabilities in the hierarchical decomposition of complex tasks through semantic reasoning. However, their application in embodied systems faces challenges in ensuring reliable execution of subtask sequences and achieving one-shot success in long-term task completion. To address these limitations in dynamic environments, we propose Closed-Loop Embodied Agent (CLEA) -- a novel architecture incorporating four specialized open-source LLMs with functional decoupling for closed-loop task management. The framework features two core innovations: (1) Interactive task planner that dynamically generates executable subtasks based on the environmental memory, and (2) Multimodal execution critic employing an evaluation framework to conduct a probabilistic assessment of action feasibility, triggering hierarchical re-planning mechanisms when environmental perturbations exceed preset thresholds. To validate CLEA's effectiveness, we conduct experiments in a real environment with manipulable objects, using two heterogeneous robots for object search, manipulation, and search-manipulation integration tasks. Across 12 task trials, CLEA outperforms the baseline model, achieving a 67.3% improvement in success rate and a 52.8% increase in task completion rate. These results demonstrate that CLEA significantly enhances the robustness of task planning and execution in dynamic environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_00729 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CLEA: Closed-Loop Embodied Agent for Enhancing Task Execution in Dynamic Environments Lei, Mingcong Wang, Ge Zhao, Yiming Mai, Zhixin Zhao, Qing Guo, Yao Li, Zhen Cui, Shuguang Han, Yatong Ren, Jinke Robotics Artificial Intelligence Large Language Models (LLMs) exhibit remarkable capabilities in the hierarchical decomposition of complex tasks through semantic reasoning. However, their application in embodied systems faces challenges in ensuring reliable execution of subtask sequences and achieving one-shot success in long-term task completion. To address these limitations in dynamic environments, we propose Closed-Loop Embodied Agent (CLEA) -- a novel architecture incorporating four specialized open-source LLMs with functional decoupling for closed-loop task management. The framework features two core innovations: (1) Interactive task planner that dynamically generates executable subtasks based on the environmental memory, and (2) Multimodal execution critic employing an evaluation framework to conduct a probabilistic assessment of action feasibility, triggering hierarchical re-planning mechanisms when environmental perturbations exceed preset thresholds. To validate CLEA's effectiveness, we conduct experiments in a real environment with manipulable objects, using two heterogeneous robots for object search, manipulation, and search-manipulation integration tasks. Across 12 task trials, CLEA outperforms the baseline model, achieving a 67.3% improvement in success rate and a 52.8% increase in task completion rate. These results demonstrate that CLEA significantly enhances the robustness of task planning and execution in dynamic environments. |
| title | CLEA: Closed-Loop Embodied Agent for Enhancing Task Execution in Dynamic Environments |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2503.00729 |