Spatial Intention Maps for Multi-Agent Mobile Manipulation
This work addresses coordination challenges for multi-agent robot teams in physical tasks, representing an incremental improvement over existing spatial action maps.
The paper tackles the problem of coordination in decentralized multi-agent mobile manipulation by introducing spatial intention maps, a new intention representation that improves performance across various tasks and enhances cooperative behaviors like object passing and collision avoidance.
The ability to communicate intention enables decentralized multi-agent robots to collaborate while performing physical tasks. In this work, we present spatial intention maps, a new intention representation for multi-agent vision-based deep reinforcement learning that improves coordination between decentralized mobile manipulators. In this representation, each agent's intention is provided to other agents, and rendered into an overhead 2D map aligned with visual observations. This synergizes with the recently proposed spatial action maps framework, in which state and action representations are spatially aligned, providing inductive biases that encourage emergent cooperative behaviors requiring spatial coordination, such as passing objects to each other or avoiding collisions. Experiments across a variety of multi-agent environments, including heterogeneous robot teams with different abilities (lifting, pushing, or throwing), show that incorporating spatial intention maps improves performance for different mobile manipulation tasks while significantly enhancing cooperative behaviors.