Abstract
The Responsibility-Sensitive Safety (RSS) model is a state-of-the-art parametrizable approach to facilitating safety planning and control, which has been widely used in autonomous driving systems. However, the current RSS model neither considers perceptual risks, nor can adaptively adjust its parameter settings according to different scenarios. These limitations may lead to unsafe or inefficient behavior of the autonomous vehicles. Therefore, this paper proposes a novel perceptual risk-aware adaptive RSS approach, which trains the interpretable perceptual risk assessment model to evaluate the risk level of different scenarios and provides interpretable reasons for reference, then adaptively selects the corresponding parameters in the RSS model for safety monitoring according to the obtained perceptual risk level. This new risk-aware adaptive approach significantly reduces safety margins and increases traffic density, while maintaining risk limits. Our experiments illustrate that our approach can well balance the safety and practicality of autonomous driving systems for complex scenarios.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
The remaining grey parts are the Sense, Plan and Act modules for autonomous driving [1].
- 2.
- 3.
The perceptual rules corresponding to the completed test data set can be found on the GitHub repository mentioned on page 10.
References
Anderson, J., Kalra, N., Stanley, K., Sorensen, P., Samaras, C., Oluwatola, T.: Autonomous Vehicle Technology: A Guide for Policymakers (2014)
Banna, V., et al.: An experience report on machine learning reproducibility: guidance for practitioners and tensorflow model garden contributors. arXiv abs/2107.00821 (2021)
Birch, J., et al.: A structured argument for assuring safety of the intended functionality (SOTIF). In: Casimiro, A., Ortmeier, F., Schoitsch, E., Bitsch, F., Ferreira, P. (eds.) SAFECOMP 2020. LNCS, vol. 12235, pp. 408–414. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-55583-2_31
Carvalho, A., Lefevre, S., Schildbach, G., Kong, J., Borrelli, F.: Automated driving: the role of forecasts and uncertainty - a control perspective. Eur. J. Control 24, 14–32 (2015). https://doi.org/10.1016/j.ejcon.2015.04.007
Cho, H., Seo, Y.W., Kumar, B., Rajkumar, R.: A multi-sensor fusion system for moving object detection and tracking in urban driving environments (2014). https://doi.org/10.1109/ICRA.2014.6907100
Dosovitskiy, A., Ros, G., Codevilla, F., López, A.M., Koltun, V.: CARLA: an open urban driving simulator. CoRR abs/1711.03938 (2017). https://arxiv.org/abs/1711.03938
Eggert, J., Mueller, F.: A foresighted driver model derived from integral expected risk, pp. 1223–1230 (2019). https://doi.org/10.1109/ITSC.2019.8916978
Fremont, D., et al.: Scenic: a language for scenario specification and data generation. Mach. Learn. 1–45 (2022). https://doi.org/10.1007/s10994-021-06120-5
Jain, A., Koppula, H., Raghavan, B., Soh, S., Saxena, A.: Car that knows before you do: anticipating maneuvers via learning temporal driving models, pp. 3182–3190 (2015). https://doi.org/10.1109/ICCV.2015.364
Kohli, P., Chadha, A.: Enabling pedestrian safety using computer vision techniques: a case study of the 2018 Uber Inc. Self-driving car crash. In: Arai, K., Bhatia, R. (eds.) FICC 2019. LNNS, vol. 69, pp. 261–279. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-12388-8_19
Koopman, P., Ferrell, U., Fratrik, F., Wagner, M.: A safety standard approach for fully autonomous vehicles. In: Romanovsky, A., Troubitsyna, E., Gashi, I., Schoitsch, E., Bitsch, F. (eds.) SAFECOMP 2019. LNCS, vol. 11699, pp. 326–332. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-26250-1_26
Majumdar, R., Mathur, A., Pirron, M., Stegner, L., Zufferey, D.: Paracosm: a language and tool for testing autonomous driving systems (2019)
Pandey, G., McBride, J., Eustice, R.: Ford campus vision and lidar data set. I. J. Robot. Res. 30, 1543–1552 (2011). https://doi.org/10.1177/0278364911400640
Rezaei, M., Klette, R.: Look at the driver, look at the road: no distraction! no accident! (2014). https://doi.org/10.1109/CVPR.2014.24
Ribeiro, M., Singh, S., Guestrin, C.: Anchors: high-precision model-agnostic explanations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018). https://doi.org/10.1609/aaai.v32i1.11491
Salay, R., Czarnecki, K., Elli, M.S., Alvarez, I.J., Sedwards, S., Weast, J.: PURSS: towards perceptual uncertainty aware responsibility sensitive safety with ML. In: Espinoza, H., et al. (eds.) Proceedings of the Workshop on Artificial Intelligence Safety, co-located with 34th AAAI Conference on Artificial Intelligence, SafeAI@AAAI 2020, New York City, NY, USA, 7 February 2020. CEUR Workshop Proceedings, vol. 2560, pp. 91–95. CEUR-WS.org (2020). https://ceur-ws.org/Vol-2560/paper34.pdf
Shalev-Shwartz, S., Shammah, S., Shashua, A.: On a formal model of safe and scalable self-driving cars (2017)
Shia, V., et al.: Semiautonomous vehicular control using driver modeling. IEEE Trans. Intell. Transp. Syst. 15, 2696–2709 (2014). https://doi.org/10.1109/TITS.2014.2325776
Xu, X., Wang, X., Wu, X., Hassanin, O., Chai, C.: Calibration and evaluation of the responsibility-sensitive safety model of autonomous car-following maneuvers using naturalistic driving study data. Transp. Res. Part C Emerg. Technol. 123, 102988 (2021). https://doi.org/10.1016/j.trc.2021.102988
Zhao, S., Qu, X., Li, Y.: Curve driving safety warning system for vehicle with driver-vehicle-environment synergy, vol. 42, pp. 112–118 (2016). https://doi.org/10.11936/bjutxb2015020042
Acknowledgement
This work is supported by National Key Research and Development Program (2020AAA0107800), National Natural Science Foundation of China (62272165), the “Digital Silk Road” Shanghai International Joint Lab of Trustworthy Intelligent Software (Grant No.22510750100), and Shanghai Trusted Industry Internet Software Collaborative Innovation Center.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, X., Wu, X., Zhao, Y., Li, Y. (2023). Perceptual Risk-Aware Adaptive Responsibility Sensitive Safety for Autonomous Driving. In: Indulska, M., Reinhartz-Berger, I., Cetina, C., Pastor, O. (eds) Advanced Information Systems Engineering. CAiSE 2023. Lecture Notes in Computer Science, vol 13901. Springer, Cham. https://doi.org/10.1007/978-3-031-34560-9_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-34560-9_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-34559-3
Online ISBN: 978-3-031-34560-9
eBook Packages: Computer ScienceComputer Science (R0)