Technological advances in the automotive industry have increased the complexity of vehicle testing and simultaneously require sophisticated methods to ensure safety, accuracy and reproducibility. Testing on proving grounds is essential to validate advanced systems at performance limits or for durability testing under controlled and repeatable conditions. However, these tests require precise planning, compliance and accuracy, which are error-prone and physically demanding for vehicles and drivers. Automation helps to overcome these challenges. This work presents an innovative approach using an Intelligent Test Coordinator (ITC) and Robot Driving System (RDS) for test vehicles to automate test preparation and execution. The ITC uses a Large Language Model and error feedback to automate the design of test procedures and generate precise RDS instructions for real-world test scenarios. Simulations validate test setups before execution, and vehicles equipped with RDS perform driverless testing. The performance of the ITC is validated by creating 240 test setups for different driving scenarios. The robot-guided vehicles perform real-world tests based on test setups on various tracks, including flat asphalt surfaces and handling tracks. These tests demonstrate that the proposed approach outperforms human-driven vehicles in terms of safety, accuracy and repeatability. The proposed approach to automation enhances testing efficiency and facilitates comprehensive validation of vehicle safety and performance.

Automated vehicle testing is crucial for ensuring safety, consistency, and efficiency as the number and complexity of vehicle tests on proving grounds increase. In dynamic tests with high speeds and sharp curves, early and long-range obstacle detection is essential for maintaining safety. Therefore, a Rapid and Long-range Detector (RLD) algorithm is necessary to seamlessly integrate into a sensor network, which includes vehicle and Roadside Unit (RSU) sensors, to monitor robot-guided vehicles. This paper presents a new method, based on a given approach, for rapid and comprehensive obstacle detection with minimal latency, using trajectory and motion data from robot-guided vehicles. This method uses point cloud-based sensors for reliable and precise detection. Our approach has proven to be effective and robust in a series of experiments involving a range of highly dynamic driving scenarios under different conditions. These results provide a solid foundation for ensuring safe and automated vehicle testing on proving grounds.

The importance of accurate and efficient vehicle testing on proving grounds continues to grow, which makes automation a key solution to meet this growing demand. Robot-guided vehicles enable precise and reproducible execution of complex tests without a driver. In dynamic driving test scenarios, the ability to perceive obstacles at long distances plays a crucial role in ensuring the safety of both the test vehicle and individ-uals on the proving ground. To enable automated testing with robot-guided vehicles, Rapid and Long-Range Detection (RLD) algorithms need to be developed for on-board implementation. This paper presents a novel point cloud-based detector for LiDAR (Light Detection And Ranging) sensors that utilizes trajectory data and robot-guided vehicle information to achieve long-range obstacle detection with minimal latency. Our detector excels in computational efficiency, making it suitable for low-performance hardware. In various experiments, we demonstrate the performance of our detector in recognizing obstacles during highly dynamic driving maneuvers. Our method contributes significantly to the further development of automated vehicle testing and paves the way for safer and more efficient driving systems on proving grounds.

As the demand for automated vehicle testing on proving grounds grows, the need for comprehensive and reliable environment monitoring systems becomes increasingly important. In highly dynamic driving test scenarios, long-range perception is essential for detecting dangers and hazards, ensuring the safety of both the test vehicle and other people on the track. However, determining an appropriate sensor setup can be challenging due to the complexity of sensor perception limitations. Perception limitations depend on the sensor characteristics and the environment. In this work, we propose a new approach to automatically evaluate sensor performance for high dynamic driving to improve the safety and efficiency of automated testing on proving grounds. Our approach involves estimating the detection range of common sensor technologies and analyzing the performance of sensor systems under various environmental conditions. By evaluating sensor performance in advance and comparing different sensor setups on tracks with a high-speed profile, we are able to identify critical track sections with higher collision risks and safeguard tests accordingly. This study emphasizes the importance of advanced environmental monitoring and sensor analysis in ensuring the safety and efficiency of automated vehicle testing.

The use of automated vehicle testing on proving grounds is increasing to enable time and cost-effective testing and reduce risks to test drivers. Robot test vehicles are used to perform various functions and load tests, even under severe conditions. Therefore, to ensure safety in proving grounds, perception and monitoring of surrounding vehicles are necessary. This requires a target-oriented, robust and foresighted perception based on road-side systems, due to the fact that test vehicles' on-board sensors are generally insufficient and short-sighted. Such a challenging sensor system has to take into account area-wide coverage, high detection probability, and low cost, for complex areas. To address this problem, we introduce AutoSCOOP, a novel method to automatically optimize sensor coverage on proving grounds. AutoSCOOP uses ray-cast sensor models and a detailed 3D environment model in a game engine to determine accurate and realistic sensor coverage. In combination with an evolutionary strategy-based method, an optimization is performed to find the optimal placement and number of road-side sensors. The methodology is successfully applied to an environmental model based on a real proving ground, and experimental evaluations are presented to show that full coverage is achieved with a minimal number of sensors.