This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
APEX: Autonomous Vehicle Plan Verification and Execution
Technical Paper
2016-01-0019
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
Autonomous vehicles (AVs) have already driven millions of miles on public roads, but even the simplest scenarios have not been certified for safety. Current methodologies for the verification of AV’s decision and control systems attempt to divorce the lower level, short-term trajectory planning and trajectory tracking functions from the behavioral rules-based framework that governs mid-term actions. Such analysis is typically predicated on the discretization of the state space and has several limitations. First, it requires that a conservative buffer be added around obstacles such that many feasible plans are classified as unsafe. Second, the discretized controllers modeled in this analysis require several refinement steps before being implementable on an actual AV, and typically do not allow the specification of comfort-related properties on the trajectories. Consumer-ready AVs use motion planning algorithms that generate smooth trajectories. While viable algorithms exist for the generation of smooth trajectories originating from a single state, analysis should consider that the AV faces state estimation errors and disturbances. Verification is restricted to a discretized state space with fixed-size cells; this assumption can artificially limit the set of available trajectories if the discretization is too coarse. Conversely, too fine of a discretization renders the problem intractable for automated analysis. This work presents a new verification tool, APEX, which investigates the combined action of a behavioral planner and state lattice-based motion planner to guarantee a safe vehicle trajectory is chosen. In APEX, decisions made at the behavioral layer can be traced through to the spatio-temporal evolution of the AV and verified. Thus, there is no need to create abstractions of the AV’s controllers, and aggressive trajectories required for evasive maneuvers can be accurately investigated.
Recommended Content
Authors
Topic
Citation
O'Kelly, M., Abbas, H., Gao, S., Kato, S. et al., "APEX: Autonomous Vehicle Plan Verification and Execution," SAE Technical Paper 2016-01-0019, 2016, https://doi.org/10.4271/2016-01-0019.Also In
References
- Waldrop M. Mitchell Autonomous vehicles: No drivers required Nature 518 7537 20 23 feb 2015 10.1038/518020a http://dx.doi.org/10.1038/518020a
- Volvo press release: US urged to establish nationwide federal guidelines for autonomous driving 2015
- Humphrey Laura R , Wolff Eric M , and Topcu Ufuk Formal specification and synthesis of mission plans for unmanned aerial vehicles AAAI Spring Symposium Series 2014
- Kato Shinpei , Takeuchi Eijiro , Ishiguro Yoshio , Ninomiya Yoshiki , Takeda Kazuya , and Hamada Tsuyoshi An open approach to autonomous vehicles Micro, IEEE 35 6 60 68 Nov 2015 0272-1732 10.1109/MM.2015.133
- Alur Rajeev , Feder Tomas , and Henzinger Thomas A. The benefits of relaxing punctuality Symposium on Principles of Distributed Computing 139 152 1991
- Fletcher Luke , Teller Seth , Olson Edwin , Moore David , Kuwata Yoshiaki , How Jonathan , Leonard John , Miller Isaac , Campbell Mark , Huttenlocher Dan et al. The mit- cornell collision and why it happened Journal of Field Robotics 25 10 775 807 2008
- Urmson Chris , Anhalt Joshua , Bagnell Drew , Baker Christopher , Bittner Robert , Clark MN , Dolan John , Duggins Dave , Galatali Tugrul , Geyer Chris et al. Autonomous driving in urban environments: Boss and the urban challenge Journal of Field Robotics 25 8 425 466 2008
- Wongpiromsarn Tichakorn , Topcu Ufuk , and Murray Richard M. Receding horizon control for temporal logic specifications Proceedings of the 13th ACM International Conference on Hybrid Systems: Computation and Control, HSCC ’10 101 110 New York, NY, USA 2010 ACM 978-1-60558-955-8 10.1145/1755952.1755968 http://doi.acm.org/10.1145/1755952.1755968
- Nilsson Petter , Hussien Omar , Balkan Ayca , Chen Yuxiao , Ames Aaron D , Grizzle Jessy W , Ozay Necmiye , Peng Huei , and Tabuada Paulo Correct-by-construction adaptive cruise control: Two approaches
- Althoff Matthias and Dolan John M Reachability computation of low-order models for the safety verification of high-order road vehicle models American Control Conference (ACC), 2012 3559 3566 IEEE 2012
- Gat Erann On three-layer architectures Artificial Intelligence and Mobile Robots MIT Press 1998
- Kong Soonho , Gao Sicun , Chen Wei , and Clarke Edmund M. dreach: Delta-reachability analysis for hybrid systems Tools and Algorithms for the Construction and Analysis of Systems - 21st International Conference, TACAS 2015 200 205 2015
- Gao Sicun , Kong Soonho , Chen Wei , and Clarke Edmund Delta-complete analysis for bounded reachability of hybrid systems arXiv preprint arXiv:1404.7171 2014
- Rajamani Rajesh Vehicle dynamics and control Springer Science & Business Media 2011
- Althoff M. and Dolan J.M. Online verification of automated road vehicles using reachability analysis Robotics, IEEE Transactions on 30 4 903 918 Aug 2014 1552-3098 10.1109/TRO.2014.2312453
- Snider Jarrod M Automatic steering methods for autonomous automobile path tracking Robotics Institute, Pittsburgh, PA, Tech. Rep. CMU-RITR-09-08 2009
- McNaughton Matthew Parallel Algorithms for Real-time Motion Planning PhD thesis Robotics Institute, Carnegie Mellon University Pittsburgh, PA July 2011
- Nagy Bryan and Kelly Alonzo Trajectory generation for car-like robots using cubic curvature polynomials Field and Service Robots 11 2001