Research papers · Posted 2025.10.11 · Preprint

Beyond ADE and FDE: A Comprehensive Evaluation Framework for Safety-Critical Prediction in Multi-Agent Autonomous Driving Scenarios

Feifei Liu, Haozhe Wang, Zejun Wei, Qirong Lu, Yiyang Wen, Xiaoyu Tang, Jingyan Jiang, Zhijian He · arXiv · English

Overview

The framework evaluates trajectory prediction across map context, agent density and spatial distribution. It investigates proximity effects and scenario-specific failures that average displacement metrics alone can obscure in interactive driving situations.

Version: v1

Beyond ADE and FDE: A Comprehensive Evaluation Framework for Safety-Critical Prediction in Multi-Agent Autonomous Driving Scenarios

Overview

Participation enquiry

Your enquiry has been sent.

Beyond ADE and FDE: A Comprehensive Evaluation Framework for Safety-Critical Prediction in Multi-Agent Autonomous Driving Scenarios

Overview

Related resources

Assuring Learning-Enabled Cyber-Physical Systems with Foundation Models: A Neuro-Symbolic Agenda for Testing, Verification, and Runtime Assurance

Engineering Psychological Safety in Autonomous Vehicles: A Systems-Theoretic Framework for Psychological Safety in Autonomous Vehicles and its Validation in Real-World Scenarios

LLM-Guided Transformation of Non-Critical Driving Scenes into Safety-Critical Scenarios Using Augmented Reality