Dual-arm robots offer enhanced versatility and efficiency over single-arm
counterparts by enabling concurrent manipulation of multiple objects or
cooperative execution of tasks using both arms. However, effectively
coordinating the two arms for complex long-horizon tasks remains a significant
challenge. Existing task planning methods predominantly focus on single-arm
robots or rely on predefined bimanual operations, failing to fully leverage the
capabilities of dual-arm systems. To address this limitation, we introduce
DAG-Plan, a structured task planning framework tailored for dual-arm robots.
DAG-Plan harnesses large language models (LLMs) to decompose intricate tasks
into actionable sub-tasks represented as nodes within a directed acyclic graph
(DAG). Critically, DAG-Plan dynamically assigns these sub-tasks to the
appropriate arm based on real-time environmental observations, enabling
parallel and adaptive execution. We evaluate DAG-Plan on the novel Dual-Arm
Kitchen Benchmark, comprising 9 sequential tasks with 78 sub-tasks and 26
objects. Extensive experiments demonstrate the superiority of DAG-Plan over
directly using LLM to generate plans, achieving nearly 50% higher efficiency
compared to the single-arm task planning baseline and nearly double the success
rate of the dual-arm task planning baseline.

通过引入 DAG-Plan，将复杂的长期任务分解为可操作的子任务，利用大型语言模型来实现动态分配并行和自适应执行，以达到比单臂任务规划基线高近 50% 的效率和双臂任务规划基线近两倍的成功率。