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

TL;DR

This paper tackles the challenge of evaluating high-level autonomous driving systems in safety-critical, interactive real-world environments by introducing Real-world Troublemaker, a 5G cloud-controlled track testing framework. It integrates cloud-based scenario management with IoT-enabled object targets and a dedicated 5G network to enable dynamic adversarial interactions, guided by a quadratic risk-interaction utility within a Stackelberg-based game and MPC-based planning. The approach is validated in real field trials, showing substantial gains in scenario reproduction accuracy, interaction diversity, and exposure to risky scenarios compared with a baseline. The work offers a scalable, automated pathway to stress-testing ADS in realistic traffic interactions, with future improvements planned in adaptive difficulty and mixed-traffic extensions.

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.

Figures (14)

• Figure 1: Overview of the Troublemaker.
• Figure 2: Overview of interactive scenario generation based on dynamic game strategy.
• Figure 3: The interactive risk illustration.
• Figure 4: Statistical results of empirical driver-vehicle interactions.
• Figure 5: The implementation of the Troublemaker.