AssemPlanner: A Multi-Agent Based Task Planning Framework for Flexible Assembly System

TL;DR

AssemPlanner introduces a multi-agent framework that converts natural language tasks into actionable assembly operations, enabling flexible and adaptive production line planning without extensive expert configuration.

Contribution

It presents a novel multi-agent, ReAct-based framework for flexible assembly task planning directly from natural language, improving adaptability and reducing setup time.

Findings

Successfully converts natural language tasks into production sequences.

Utilizes a ReAct-based SchedAgent for adaptive decision-making.

Code and datasets are publicly available at the provided GitHub link.

Abstract

In flexible assembly systems, existing task planning methods require a time-consuming configuration process by multiple experts to establish a production line for a new product. To address this challenge, we propose a multi-agent based task planning framework for flexible assembly systems, denoted as AssemPlanner. It takes tasks described in natural language as input, which are then converted into actionable sequential production operations. It comprises several specialized agents, including SchedAgent , KnowledgeAgent, LineBalanceAgent, and a scene graph. Within the proposed framework, SchedAgent serves as the central reasoning engine. Departing from traditional static pipelines, AssemPlanner utilizes a ReAct-based SchedAgent to adaptively adjust actions via multi-agent feedback. By observing the feedback from KnowledgeAgent, LineBalanceAgent, and the scene graph, it autonomously resolves complex industrial process constraints. To facilitate reproducibility, all code and datasets are released at https://github.com/chz332/Assemplanner.