DAG-Plan: Generating Directed Acyclic Dependency Graphs for Dual-Arm Cooperative Planning
Zeyu Gao, Yao Mu, Jinye Qu, Mengkang Hu, Shijia Peng, Chengkai Hou, Lingyue Guo, Ping Luo, Shanghang Zhang, Yanfeng Lu
AI summary
Problem
Current LLM-based dual-arm planners rely on rigid linear sequences that cannot model parallelism or adapt to real-time changes, forcing a trade-off between efficiency and adaptability.
Approach
DAG-Plan uses an LLM once to convert natural language instructions into a structured DAG that explicitly maps task dependencies and parallel opportunities, then dynamically assigns executable sub-tasks to both arms based on real-time state and cost.
Key results
- 48% higher success rate than single-query linear methods
- 84.1% higher execution efficiency than iterative querying methods
- Eliminates latency of repeated LLM calls
- Enables truly adaptive and parallel dual-arm operation
Why it matters
Offers a scalable, graph-based planning paradigm that unlocks efficient and reliable LLM-driven coordination for complex dual-arm and multi-robot systems.
Abstract
Dual-arm robots promise greater efficiency but require planning for complex tasks with nonlinear sub-task dependencies. Current methods using Large Language Mod- els (LLMs) suffer from a fundamental trade-off: generating linear sequences is efficient but fails to model parallelism and adapt to changes, while iterative querying is adaptive but too slow and costly. To bridge this gap, we introduce DAG-Plan, a novel task planning framework that for the first time employs a Directed Acyclic Graph (DAG) as the central representation for dual-arm coordination. The key insight is that a DAG natively captures complex sub-task dependencies and explicitly reveals opportunities for parallel execution. Within this framework, an LLM is used only once as a powerful semantic parser to translate a natural language instruction into a structured DAG. During execution, our system dynamically assigns candidate nodes to the suitable arm based on real-time environmental observations, enabling truly adaptive and parallel operation. Extensive evaluation on a dual-arm kitchen benchmark shows that DAG-Plan’s structured approach fundamentally outperforms existing paradigms. It achieves a 48% higher success rate than single-query linear sequence methods with dual arm by robustly managing dependencies, and an 84.1% higher execution efficiency than iterative querying methods by eliminating the latency of repeated LLM calls. Our work demonstrates that a principled, graph-based representation is the key to unlocking efficient and reliable LLM-based planning for complex robotic systems. More demos and code are available on https://sites.google.com/view/dag-plan.