Model-Agnostic Multi-Agent Perception Framework

Existing multi-agent perception systems assume that every agent utilizes the same model with identical parameters and architecture. The performance can be degraded with different perception models due to the mismatch in their confidence scores. In this work, we propose a model-agnostic multi-agent perception framework to reduce the negative effect caused by the model discrepancies without sharing the model information. Specifically, we propose a confidence calibrator that can eliminate the prediction confidence score bias. Each agent performs such calibration independently on a standard public database to protect intellectual property. We also propose a corresponding bounding box aggregation algorithm that considers the confidence scores and the spatial agreement of neighboring boxes. Our experiments shed light on the necessity of model calibration across different agents, and the results show that the proposed framework improves the baseline 3D object detection performance of heterogeneous agents. The code can be found at this url.

Authors

• Runsheng Xu
• Weizhe Chen 0004
• Hao Xiang
• Xin Xia 0007
• Lantao Liu
• Jiaqi Ma 0003

Keywords

• Solid modeling
• Three-dimensional displays
• Databases
• Object detection
• Intellectual property
• Prediction algorithms
• Calibration
• Bounding Box
• Confidence Score
• Perceptual System
• Multi-agent Systems
• 3D Object Detection
• Aggregation Algorithm
• Neural Network
• Point Cloud
• Functional Scale
• Scaling Method
• Autonomous Vehicles
• Average Precision
• Calibration Method
• Update Rule
• Coordinate Frame
• Nondecreasing Function
• Non-maximum Suppression
• Calibration Dataset
• Classification Confidence
• Late Fusion
• Bounding Box Coordinates
• Online Phase
• Early Fusion
• Architecture For Detection
• Detector Output
• Object Boxes
• Bounding Box Regression
• Candidate Boxes