Search papers, labs, and topics across Lattice.
This paper introduces a hierarchical closed-loop framework that integrates Large Language Models (LLMs) with multi-robot systems to enhance robust manipulation across various tasks. By employing three specialized agents鈥擯lanning, Manipulation, and Verification鈥攖he system effectively decomposes high-level instructions into actionable sub-tasks while adapting to real-world uncertainties. Experimental results indicate that this approach significantly improves success rates and adaptability in both single and multi-workspace manipulation scenarios.
A novel closed-loop framework enables multi-robot systems to achieve robust manipulation by integrating LLMs with real-time feedback mechanisms.
Multi-robot systems provide the parallelism and redundancy necessary for long-horizon tasks, while Large Language Models (LLMs) offer the reasoning capabilities to decompose these objectives into actionable plans. However, effectively grounding this high-level reasoning in physical multi-robot execution remains an open challenge. Existing LLM-based approaches fall mainly into two categories: Single-robot methods achieve robust contact-rich manipulation but lack the coordination mechanisms required for tasks spanning multiple workspaces. Current multi-robot frameworks focus on high-level planning, often treating manipulation as an idealized primitive that fails to account for real-world execution uncertainties. To address this, we propose a hierarchical closed-loop agentic LLM-based framework to ensure robust multi-robot manipulation. Our system consists of three specialized agents: the Planning Agent decomposes instructions into allocated sub-tasks, the Manipulation Agent for each robot executes actions via adaptive tool use, and the Verification Agent closes the loop by monitoring physical outcomes and feeding back semantic corrections. Extensive real-world experiments demonstrate that our framework achieves superior success rates, ensures robust adaptability ranging from single to cross workspace manipulation, and offers a generalizable approach for diverse manipulation tasks.
