Pragmatic Communication in Multi-Agent Collaborative Perception

doi:10.1109/TPAMI.2026.3680062

Pragmatic Communication in Multi-Agent Collaborative Perception

2026-04-09

0

PRE

AI

DOI：10.1109/TPAMI.2026.3680062

Original

Original request for help

Save

Abstract

En 中文

Collaborative perception allows each agent to enhance its perceptual abilities by exchanging messages with others. It inherently results in a trade-off between perception ability and communication costs. Previous works transmit complete full-frame high-dimensional feature maps among agents, resulting in substantial communication costs. To promote communication efficiency, we propose only transmitting the information needed for the collaborator’s downstream task. This pragmatic communication strategy focuses on three key aspects: i) pragmatic message selection, which selects task-critical parts from the complete data, resulting in spatially and temporally sparse feature vectors; ii) pragmatic message representation, which achieves pragmatic approximation of high-dimensional feature vectors with a task-adaptive dictionary, enabling communicating with integer indices; iii) pragmatic collaborator selection, which identifies beneficial collaborators, pruning unnecessary communication links. Following this strategy, we first formulate a mathematical optimization framework for the perception-communication trade-off and then propose <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PragComm</monospace>, a multi-agent collaborative perception system with two key components: i) single-agent detection and tracking and ii) pragmatic collaboration. The proposed <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PragComm</monospace> promotes pragmatic communication and adapts to a wide range of communication conditions. We evaluate <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PragComm</monospace> for both collaborative 3D object detection and tracking tasks in both real-world, V2V4Real, and simulation datasets, OPV2V and V2X-SIM2.0. <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PragComm</monospace> consistently outperforms previous methods with more than 32.7 K× lower communication volume on OPV2V.

Keywords:

Multi-agent learning

collaborative perception

communication

3D object detection

tracking

Pragmatic Communication in Multi-Agent Collaborative Perception

Abstract

Journal

Organization