TY - GEN
T1 - Search-based Test-CASe Generation by Monitoring Responsibility Safety Rules
AU - Hekmatnejad, Mohammad
AU - Hoxha, Bardh
AU - Fainekos, Georgios
N1 - Funding Information:
This work has been partially funded by NSF awards 1350420 and 1361926, and the NSF I/UCRC Center for Embedded Systems. 1Mohammad Hekmatnejad and Georgios Fainekos are with Department of Computer Science and Engineering, Arizona State University, Tempe AZ 85281, USA {mhekmatn,fainekos}@asu.edu 2Bardh Hoxha is with Toyota Research Institute of North America, Ann Arbor, MI, 48187, USA bardh.hoxha@toyota.com
Publisher Copyright:
© 2020 IEEE.
PY - 2020/9/20
Y1 - 2020/9/20
N2 - The safety of Automated Vehicles (AV) as Cyber-Physical Systems (CPS) depends on the safety of their consisting modules (software and hardware) and their rigorous integration. Deep Learning is one of the dominant techniques used for perception, prediction and decision making in AVs. The accuracy of predictions and decision-making is highly dependant on the tests used for training their underlying deep-learning. In this work, we propose a method for screening and classifying simulation-based driving test data to be used for training and testing controllers. Our method is based on monitoring and falsification techniques, which lead to a systematic automated procedure for generating and selecting qualified test data. We used Responsibility Sensitive Safety (RSS) rules as our qualifier specifications to filter out the random tests that do not satisfy the RSS assumptions. Therefore, the remaining tests cover driving scenarios that the controlled vehicle does not respond safely to its environment. Our framework is distributed with the publicly available S-TALiRo and Sim-ATAV tools.
AB - The safety of Automated Vehicles (AV) as Cyber-Physical Systems (CPS) depends on the safety of their consisting modules (software and hardware) and their rigorous integration. Deep Learning is one of the dominant techniques used for perception, prediction and decision making in AVs. The accuracy of predictions and decision-making is highly dependant on the tests used for training their underlying deep-learning. In this work, we propose a method for screening and classifying simulation-based driving test data to be used for training and testing controllers. Our method is based on monitoring and falsification techniques, which lead to a systematic automated procedure for generating and selecting qualified test data. We used Responsibility Sensitive Safety (RSS) rules as our qualifier specifications to filter out the random tests that do not satisfy the RSS assumptions. Therefore, the remaining tests cover driving scenarios that the controlled vehicle does not respond safely to its environment. Our framework is distributed with the publicly available S-TALiRo and Sim-ATAV tools.
UR - http://www.scopus.com/inward/record.url?scp=85093109664&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85093109664&partnerID=8YFLogxK
U2 - 10.1109/ITSC45102.2020.9294489
DO - 10.1109/ITSC45102.2020.9294489
M3 - Conference contribution
AN - SCOPUS:85093109664
T3 - 2020 IEEE 23rd International Conference on Intelligent Transportation Systems, ITSC 2020
BT - 2020 IEEE 23rd International Conference on Intelligent Transportation Systems, ITSC 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 23rd IEEE International Conference on Intelligent Transportation Systems, ITSC 2020
Y2 - 20 September 2020 through 23 September 2020
ER -