Real-world Troublemaker: A 5G Cloud-controlled Track Testing Framework for Automated Driving Systems in Safety-critical Interaction Scenarios

TL;DR

This paper introduces a 5G cloud-controlled testing framework for autonomous driving systems that enhances interaction realism and scenario diversity, significantly improving safety evaluation accuracy and coverage in real-world conditions.

Contribution

The paper presents a novel 5G cloud-controlled framework with dynamic game strategy for interactive testing of ADS, addressing limitations of traditional pre-programmed testing methods.

Findings

Scenario reproduction accuracy improved by 65.2%

Interaction strategy diversity increased by 9.2 times

Safety-critical scenario exposure frequency increased by 3.5 times

Abstract

Track testing plays a critical role in the safety evaluation of autonomous driving systems (ADS), as it provides a real-world interaction environment. However, the inflexibility in motion control of object targets and the absence of intelligent interactive testing methods often result in pre-fixed and limited testing scenarios. To address these limitations, we propose a novel 5G cloud-controlled track testing framework, Real-world Troublemaker. This framework overcomes the rigidity of traditional pre-programmed control by leveraging 5G cloud-controlled object targets integrated with the Internet of Things (IoT) and vehicle teleoperation technologies. Unlike conventional testing methods that rely on pre-set conditions, we propose a dynamic game strategy based on a quadratic risk interaction utility function, facilitating intelligent interactions with the vehicle under test (VUT) and creating a more realistic and dynamic interaction environment. The proposed framework has been successfully implemented at the Tongji University Intelligent Connected Vehicle Evaluation Base. Field test results demonstrate that Troublemaker can perform dynamic interactive testing of ADS accurately and effectively. Compared to traditional methods, Troublemaker improves scenario reproduction accuracy by 65.2\%, increases the diversity of interaction strategies by approximately 9.2 times, and enhances exposure frequency of safety-critical scenarios by 3.5 times in unprotected left-turn scenarios.