SOURCE-LINKED INTELLIGENCE

MAAP: Multi-Agent Active Perception for Collaborative Manipulation

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Multi-agent manipulation naturally produces multiple task-driven viewpoints: every arm carries a wrist camera and moves through the scene while acting. Yet these observations are typically underutilized, and active perception in manipulation is still often treated as requiring a dedicated sensing agent. We introduce MAAP (Multi-Agent Active Perception), in which every arm is dual-purpose: it executes manipulation actions and, through the wrist camera it carries, simultaneously serves as a moving viewpoint for the team. We pair this with RAIL (Role-Aware Imitation Learning), a controller that p

Read original source ↗ Open in workspace

recordType

paper

region

Global