Real-world Test Drive Vehicle Data Management System for Validation of Automated Driving Systems

Klitzke, Lars; Koch, Carsten; Haja, Andreas; Köster, Frank

doi:10.5220/0007720500002179

Cited by 7 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The quality of the data can be affected by various factors such as the type of sensors used and how they are installed [4], the location where the data is collected, and the fact that rare-occurring situations are difficult to collect [41]. After all, we still have to understand how to extract and select scenarios given massive data collected [44].…”

Section: Data-driven Approachesmentioning

confidence: 99%

Critical Scenario Identification for Realistic Testing of Autonomous Driving Systems

Song

Tan

Runeson

et al. 2023

Preprint

View full text Add to dashboard Cite

Autonomous driving has become an important research area for road traffic, whereas testing of autonomous driving systems to ensure a safe and reliable operation remains an open challenge. Substantial realworld testing or massive driving data collection does not scale since the potential test scenarios in real-world traffic are infinite, and covering large shares of them in the test is impractical. Thus, critical ones have to be prioritized. We have developed for critical test scenario identification and in this study, we implement the approach and validate it on two real autonomous driving systems from industry by integrating it into their tool-chain. Our main contribution in this work is the demonstration and validation of our approach for critical scenario identification for testing real autonomous driving systems.

show abstract

Section: Data-driven Approachesmentioning

confidence: 99%

Critical Scenario Identification for Realistic Testing of Autonomous Driving Systems

Song

Tan

Runeson

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Minatomirai, Nishi-ku, Yokohama-shi, 220-0012 Kanagawa, Japan researchers have already examined the difficulty and importance of AI verification and how it should be done [10,11]. For example, consider the case of AI for peripheral recognition, which is essential for many systems, including autonomous driving.…”

Section: Introductionmentioning

confidence: 99%

Edge Device Verification Techniques for Updated Object Detection AI via Target Object Existence

KITAYAMA,

ONO,

ITO

2024

IEICE Trans. Fundamentals

View full text Add to dashboard Cite

Edge devices with strict safety and reliability requirements, such as autonomous driving cars, industrial robots, and drones, necessitate software verification on such devices before operation. The human cost and time required for this analysis constitute a barrier in the cycle of software development and updating. In particular, the final verification at the edge device should at least strictly confirm that the updated software is not degraded from the current it. Since the edge device does not have the correct data, it is necessary for a human to judge whether the difference between the updated software and the operating it is due to degradation or improvement. Therefore, this verification is very costly. This paper proposes a novel automated method for efficient verification on edge devices of an object detection AI, which has found practical use in various applications. In the proposed method, a target object existence detector (TOED) (a simple binary classifier) judges whether an object in the recognition target class exists in the region of a prediction difference between the AI's operating and updated versions. Using the results of this TOED judgement and the predicted difference, an automated verification system for the updated AI was constructed. TOED was designed as a simple binary classifier with four convolutional layers, and the accuracy of object existence judgment was evaluated for the difference between the predictions of the YOLOv5 L and X models using the Cityscapes dataset. The results showed judgement with more than 99.5% accuracy and 8.6% over detection, thus indicating that a verification system adopting this method would be more efficient than simple analysis of the prediction differences.

show abstract

Critical scenario identification for realistic testing of autonomous driving systems

et al. 2022

View full text Add to dashboard Cite

Autonomous driving has become an important research area for road traffic, whereas testing of autonomous driving systems to ensure a safe and reliable operation remains an open challenge. Substantial real-world testing or massive driving data collection does not scale since the potential test scenarios in real-world traffic are infinite, and covering large shares of them in the test is impractical. Thus, critical ones have to be prioritized. We have developed an approach for critical test scenario identification and in this study, we implement the approach and validate it on two real autonomous driving systems from industry by integrating it into their tool-chain. Our main contribution in this work is the demonstration and validation of our approach for critical scenario identification for testing real autonomous driving systems.

show abstract

Real-world Test Drive Vehicle Data Management System for Validation of Automated Driving Systems

Cited by 7 publications

References 0 publications

Critical Scenario Identification for Realistic Testing of Autonomous Driving Systems

Critical Scenario Identification for Realistic Testing of Autonomous Driving Systems

Edge Device Verification Techniques for Updated Object Detection AI via Target Object Existence

Critical scenario identification for realistic testing of autonomous driving systems

Contact Info

Product

Resources

About