PushingBots: Collaborative Pushing Via Neural Accelerated Combinatorial Hybrid Optimization
Zili Tang, Ying Zhang, Meng Guo
AI summary
Problem
Existing collaborative pushing methods rely on predefined contact modes and fixed object shapes, limiting their ability to handle general multi-robot, multi-object tasks in complex, cluttered environments with dynamic uncertainties.
Approach
The method decomposes multi-object pushing tasks via MAPF, dynamically assigns robots to subtasks in a receding horizon, and optimizes contact modes and forces using a hybrid search accelerated by an offline/online diffusion model.
Key results
- Novel combinatorial-hybrid optimization algorithm for mode-free multi-robot pushing
- Theoretical feasibility and completeness guarantees for arbitrary robot/object counts
- Diffusion-based neural accelerator that predicts keyframes and modes to boost planning efficiency
- Validated across simulations and hardware with generalization to heterogeneous robots and 6D pushing
Why it matters
Provides a scalable, theoretically grounded solution for non-prehensile manipulation, enabling low-cost mobile robot fleets to perform complex collaborative tasks without specialized grippers.
Abstract
Many robots are not equipped with a manipulator and many objects are not suitable for prehensile manipulation (such as large boxes and cylinders). In these cases, pushing is a simple yet effective non-prehensile skill for robots to interact with and further change the environment. Existing work often assumes a set of predefined pushing modes and fixed-shape objects. This work tackles the general problem of controlling a robotic fleet to push collaboratively numerous arbitrary objects to respective destinations, within complex environments of cluttered and movable obstacles. It incorporates several characteristic chal- lenges for multi-robot systems such as online task coordination under large uncertainties of cost and duration, and for contact- rich tasks such as hybrid switching among different contact modes, and under-actuation due to constrained contact forces. The proposed method is based on combinatorial hybrid opti- mization over dynamic task assignments and hybrid execution via sequences of pushing modes and associated forces. It consists of three main components: (I) the decomposition, ordering and rolling assignment of pushing subtasks to robot subgroups; (II) the keyframe guided hybrid search to optimize the sequence of parameterized pushing modes for each subtask; (III) the hybrid control to execute these modes and transit among them. Last but not least, a diffusion-based accelerator is adopted to predict the keyframes and pushing modes that should be prioritized during hybrid search; and further improve planning efficiency. The framework is complete under mild assumptions. Its efficiency and effectiveness under different numbers of robots and general- shaped objects are validated extensively in simulations and hard- ware experiments, as well as generalizations to heterogeneous robots, planar assembly and 6D pushing.