Multi-robot planning method finds best collision-free tasks and motions
Asymptotically Optimal Multi-Robot Task and Motion Planning
Robotics
Summary
Planning tasks and movements for multiple robots working together is very hard because robots must avoid colliding while coordinating complex jobs. The authors found a way for planning that gets better and better over time until it finds the best possible plans. Their method breaks down the problem so each robot plans individually but also explores how to switch between tasks correctly. This approach ensures the whole multi-robot system can find efficient plans without searching everything all at once, making it faster and more reliable. The authors also added smart shortcuts to make the planning practical for real robots.
What this means in practice
- •For robotics engineers: Plan coordinated movements and tasks for multiple robots in factories where smooth and efficient collaboration is crucial.
- •For warehouse automation teams: Create scalable motion plans for multiple robots moving goods without collisions, improving handling speed and safety.
Authors
Thi Thuy Ngan Duong, Cheuk Tung Shadow Yiu, Rahul Shome, Yoonchang Sung
Abstract
Multi-robot task and motion planning (MR-TAMP) requires jointly reasoning about discrete task decisions and continuous collision-free motions of multiple interacting robots. Although asymptotically optimal algorithms have been developed for task and motion planning, extending these guarantees to the multi-robot setting introduces an important challenge: different task transitions may involve different subsets of robots and therefore impose constraints of different dimensions on the composite configuration space. Consequently, an asymptotically optimal planner must not only optimize motion within each task mode, but also ensure sufficient exploration of the different types of transitions connecting them. We characterize this transition structure and establish sufficient conditions for global asymptotic optimality in MR-TAMP, requiring persistent coverage of relevant transitions and asymptotically improving motion planning within connected feasible regions. Based on these conditions, we develop an efficient asymptotically optimal MR-TAMP algorithm that combines evolving individual-robot roadmaps with implicit tensor-product search, avoiding explicit construction of the composite roadmap. The planner further employs conditional transition sampling, lazy collision checking, and mode- and solution-level guidance to improve finite-time planning efficiency while retaining persistent exploration. The resulting framework provides asymptotic optimality guarantees for multi-robot manipulation while efficiently exploiting the structure of individual-robot motion planning.