Robots coordinate better with uncertain skill execution times
Multi-Robot Multi-Goal Motion Planning with Stochastic Skills
Robotics
Summary
When multiple robots work together on tasks involving complicated movements, their actions can take different amounts of time and paths can change unpredictably. The authors developed a planning method that lets robots adjust their motions on the fly by considering these uncertainties during planning. This method helps robots avoid collisions and coordinate smoothly, even when skill execution varies. Their approach uses a mathematical model called a Markov Decision Process to plan reactive strategies over a combined roadmap of possible movements.
What this means in practice
- •For industrial automation teams: Plan coordinated robotic tasks in manufacturing where movement times and trajectories are uncertain, improving efficiency and safety in shared workspaces.
- •For warehouse robotics operators: Enable groups of robots to dynamically adjust their paths during picking and packing when actions take variable time due to changing conditions.
Authors
William Schnyder, Valentin N. Hartmann, Stelian Coros
Abstract
As robots are increasingly deployed in groups and share workspaces to execute real-world tasks, planning their concurrent motions around complex manipulation skills becomes essential. These skills involve continuous physical execution and may exhibit stochastic behavior, resulting in variable execution times and uncertain continuous trajectories. Existing planners either limit execution to single-robot scenarios, rely on open-loop paths, or use post-hoc scheduling that prevents dynamic coordination. In this paper, we address this gap by integrating stochastic skills into sampling-based multi-robot planning by formulating the problem as a Markov Decision Process (MDP) over a multi-modal composite roadmap. For stochastic skills, solving the MDP yields a reactive policy that allows controllable robots to dynamically adapt their motions in response to other robots' execution of manipulation skills. By resolving skill uncertainty directly at planning time, this approach avoids the pessimism of conservative baselines and unlocks robust, dynamic multi-robot coordination. Code for the planners is available at https://www.vhartmann.com/stochastic-skills.