Evaluating Interactions between Automated Vehicles and Cyclists using a coupled In-the-Loop Test Environment

2025-07-29

AI Summary

Current autonomous driving systems (ADS) suffer from insufficient realism in interaction testing with vulnerable road users (VRUs), particularly cyclists. To address this, we propose a novel cyber-physical bidirectional-in-the-loop testing framework that enables closed-loop, real-time, dynamic interaction between an autonomous vehicle and a human cyclist within a high-fidelity virtual environment—marking the first such implementation. Methodologically, the framework leverages Unreal Engine 5 to construct scalable, photorealistic virtual scenarios, integrating vehicle hardware-in-the-loop (HIL), cyclist-in-the-loop (HIL-bike) testbeds, and camera-based visual stimulation modules. Experimental evaluation demonstrates sub-0.15 m trajectory alignment between virtual and physical vehicle states and end-to-end latency consistently below 80 ms, confirming high fidelity and low-latency performance. This framework significantly enhances the realism and repeatability of ADS safety validation for VRU interactions, establishing a new paradigm for complex human–vehicle interaction testing.

Technology Category

• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Computer Vision: Vision for Robotics & Autonomous Driving
• Application Domains: Mobility, Driving & Flight

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Testing and evaluating automated driving systems (ADS) in interactions with vulnerable road users (VRUs), such as cyclists, are essential for improving the safety of VRUs, but often lack realism. This paper presents and validates a coupled in-the-loop test environment that integrates a Cyclist-in-the Loop test bench with a Vehicle-in-the-Loop test bench via a virtual environment (VE) developed in Unreal Engine 5. The setup enables closed-loop, bidirectional interaction between a real human cyclist and a real automated vehicle under safe and controllable conditions. The automated vehicle reacts to cyclist gestures via stimulated camera input, while the cyclist, riding a stationary bicycle, perceives and reacts to the vehicle in the VE in real time. Validation experiments are conducted using a real automated shuttle bus with a track-and-follow function, performing three test maneuvers - straight-line driving with stop, circular track driving, and double lane change - on a proving ground and in the coupled in-the-loop test environment. The performance is evaluated by comparing the resulting vehicle trajectories in both environments. Additionally, the introduced latencies of individual components in the test setup are measured. The results demonstrate the feasibility of the approach and highlight its strengths and limitations for realistic ADS evaluation.

Problem

• Evaluating interactions between automated vehicles and cyclists safely.
• Developing a realistic test environment for automated driving systems.
• Validating bidirectional interaction in a virtual and real setup.

Innovation

• Coupled in-the-loop test environment for AV-cyclist interaction
• Real-time bidirectional interaction via Unreal Engine 5
• Automated vehicle reacts to cyclist gestures