SGCP: A Self-Organized Game-Theoretic Framework For Collaborative Perception

2026-01-18

AI Summary

This work proposes a fully decentralized vehicle-to-vehicle cooperative perception framework for dense traffic scenarios lacking roadside infrastructure and operating under stringent communication constraints. The approach employs a two-stage game-theoretic mechanism: first, vehicles autonomously form stable clusters based on perceptual complementarity and motion consistency, and elect a coordinator within each cluster; subsequently, the coordinator guides members to selectively transmit critical point cloud segments via a non-cooperative potential game, while exchanging compact detection messages to achieve global scene awareness. By innovatively integrating self-organized clustering with game-driven sparse point cloud transmission, the method significantly reduces communication overhead while enhancing both perception accuracy and spatial coverage, as validated on the CARLA-OpenCDA-NS3 simulation platform against baseline approaches.

Technology Category

• Game Theory and Economic Paradigms: Cooperative Game Theory
• Computer Vision: Vision for Robotics & Autonomous Driving
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Security and Privacy: Data transparency and provenance
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Collaborative perception holds great promise for improving safety in autonomous driving, particularly in dense traffic where vehicles can share sensory information to overcome individual blind spots and extend awareness. However, deploying such collaboration at scale remains difficult when communication bandwidth is limited and no roadside infrastructure is available. To overcome these limitations, we introduce a fully decentralized framework that enables vehicles to self organize into cooperative groups using only vehicle to vehicle communication. The approach decomposes the problem into two sequential game theoretic stages. In the first stage, vehicles form stable clusters by evaluating mutual sensing complementarity and motion coherence, and each cluster elects a coordinator. In the second stage, the coordinator guides its members to selectively transmit point cloud segments from perceptually salient regions through a non cooperative potential game, enabling efficient local fusion. Global scene understanding is then achieved by exchanging compact detection messages across clusters rather than raw sensor data. We design distributed algorithms for both stages that guarantee monotonic improvement of the system wide potential function. Comprehensive experiments on the CARLA-OpenCDA-NS3 co-simulation platform show that our method reduces communication overhead while delivering higher perception accuracy and wider effective coverage compared to existing baselines.

Problem

• collaborative perception
• autonomous driving
• communication constraints
• decentralized coordination
• vehicle-to-vehicle communication

Innovation

• self-organized collaboration
• game-theoretic clustering
• selective point cloud transmission
• decentralized perception
• potential game