Zusammenfassung
Sichere Verhaltensplanung und Entscheidungsfindung gehören zu den größten Herausforderungen für hochautomatisierte Systeme. Wichtig sind hierbei insbesondere die Erklärbarkeit, Wartbarkeit und Skalierbarkeit des Verfahrens. Wir schlagen daher eine hierarchische verhaltensbasierte Architektur zur taktischen und strategischen Verhaltensgenerierung für automatisierte Fahrzeuge vor. Wir verwenden modulare Verhaltensbausteine, um komplexere Verhaltensweisen in einem Bottom-up-Ansatz zusammenzustellen. Das System ist in der Lage, eine Vielzahl von szenario- und methodenspezifischen Lösungen, wie POMDPs, RRT* oder Reinforcement Learning, in einer nachvollziehbaren Architektur zu kombinieren. Dies ermöglicht den Einsatz heterogener Planungsmethoden, die auf spezifische Fahrmanöver zugeschnitten sind. Experimentelle Ergebnisse veranschaulichen unser Konzept.
Abstract
Behavior planning and decision-making are some of the major challenges for highly automated systems. Most importantly the concept has to be explainable, maintainable and scalable. Therefore, we propose a hierarchical behavior-based architecture for tactical and strategical behavior generation in automated driving. We utilize modular behavior blocks to compose more complex behaviors in a bottom-up approach. The system is capable of combining a variety of scenario- and methodology-specific solutions, like POMDPs, RRT* or learning-based behavior, into one understandable and traceable architecture. We illustrate our design in an explanatory experiment.
Funding statement: Die Autoren danken der Deutschen Forschungsgemeinschaft (DFG) (SPP 1835) für die Unterstützung von Teilen dieser Arbeit im Schwerpunktprogramm Kooperativ Interagierende Automobile sowie den Projektpartnern für die fruchtbare Zusammenarbeit.
Literatur
1. M. Aeberhard et al.“Experience, Results and Lessons Learned from Automated Driving on Germany’s Highways”. IEEE Intell. Transp. Syst. Mag. 7.1 (Fr. 2015).10.1109/MITS.2014.2360306Search in Google Scholar
2. M. Althoff, M. Koschi and S. Manzinger. “CommonRoad: Composable Benchmarks for Motion Planning on Roads”. In: IEEE Intell. Veh. Symp., 2017.Search in Google Scholar
3. A. Bacha et al.“Odin: Team Victortango’s Entry in the Darpa Urban Challenge”. J. of Field Robot. 25.8 (2008).10.1002/rob.20248Search in Google Scholar
4. H. Banzhaf et al.“From Footprints to Beliefprints: Motion Planning under Uncertainty for Maneuvering Automated Vehicles in Dense Scenarios”. In: Int. Conf. on Intell. Transp. Syst., Nov. 2018.10.1109/ITSC.2018.8569897Search in Google Scholar
5. Philipp Bender et al.“The Combinatorial Aspect of Motion Planning: Maneuver Variants in Structured Environments”. In: IEEE Intell. Veh. Symp., IEEE, 2015.Search in Google Scholar
6. R. Brooks. “A Robust Layered Control System for a Mobile Robot”. IEEE J. on Robot. and Automation 2.1 (1986).10.7551/mitpress/1716.003.0003Search in Google Scholar
7. Richard E. Fikes and Nils J. Nilsson. “STRIPS: A New Approach to the Application of Theorem Proving to Problem Solving”. Artificial Intelligence 2.3–4 (1971).10.1016/0004-3702(71)90010-5Search in Google Scholar
8. B. Gutjahr, L. Groll and M. Werling. “Lateral Vehicle Trajectory Optimization Using Constrained Linear Time-Varying MPC”. IEEE Trans. Intell. Transp. Syst. 18.6 (Juni 2017).10.1109/TITS.2016.2614705Search in Google Scholar
9. S. Hoermann et al.“Entering Crossroads with Blind Corners. A Safe Strategy for Autonomous Vehicles”. In: IEEE Intell. Veh. Symp., Juni 2017.10.1109/IVS.2017.7995803Search in Google Scholar
10. C. Hubmann et al.“Automated Driving in Uncertain Environments: Planning With Interaction and Uncertain Maneuver Prediction”. IEEE Trans. Intell. Veh. 3.1 (März 2018).10.1109/TIV.2017.2788208Search in Google Scholar
11. Constantin Hubmann et al.“A Belief State Planner for Interactive Merge Maneuvers in Congested Traffic”. In: Int. Conf. on Intell. Transp. Syst., Nov. 2018.10.1109/ITSC.2018.8569729Search in Google Scholar
12. Julio K. Rosenblatt. “DAMN: A Distributed Architecture for Mobile Navigation”. J. of Exp. & Theor. Artif. Intell. 9.2–3 (1997).10.1080/095281397147167Search in Google Scholar
13. Martin Lauer et al.“Cognitive Concepts in Autonomous Soccer Playing Robots”. Cogn. Syst. Res. 11.3 (2010).10.1016/j.cogsys.2009.12.003Search in Google Scholar
14. A. Meyer et al.“Deep Semantic Lane Segmentation for Mapless Driving”. In: IEEE/RSJ Int. Conf. on Intell. Robots and Syst., Okt. 2018.10.1109/IROS.2018.8594450Search in Google Scholar
15. Michael Montemerlo et al.“Junior: The Stanford Entry in the Urban Challenge”. J. of Field Robot. 25.9 (2008).10.1007/978-3-642-03991-1_3Search in Google Scholar
16. Maximilian Naumann, Hendrik Konigshof and Christoph Stiller. “Provably Safe and Smooth Lane Changes in Mixed Trafic”. In: IEEE Intell. Transp. Syst. Conf., Okt. 2019.10.1109/ITSC.2019.8917461Search in Google Scholar
17. Maximilian Naumann et al.“CoInCar-Sim: An Open-Source Simulation Framework for Cooperatively Interacting Automobiles”. In: IEEE Intell. Veh. Symp., Juni 2018.10.1109/IVS.2018.8500405Search in Google Scholar
18. J. Nilsson et al.“Lane Change Maneuvers for Automated Vehicles”. IEEE Trans. Intell. Transp. Syst., 18.5, 1087–1096 (2016).10.1109/TITS.2016.2597966Search in Google Scholar
19. P. F. Orzechowski, A. Meyer and M. Lauer. “Tackling Occlusions & Limited Sensor Range with Set-Based Safety Verification”. In: Int. Conf. on Intell. Transp. Syst., 2018.10.1109/ITSC.2018.8569332Search in Google Scholar
20. Pattie Maes. “How to Do the Right Thing”. Connection Science 1.3 (1989).10.1080/09540098908915643Search in Google Scholar
21. Fabian Poggenhans et al.“Lanelet2: A High-Definition Map Framework for the Future of Automated Driving”. In: Int. Conf. on Intell. Transp. Syst., 2018.Search in Google Scholar
22. Bruno Siciliano and Oussama Khatib (Eds.) Springer Handbook of Robotics. Springer Handbooks. Springer International Publishing, 2016.10.1007/978-3-319-32552-1Search in Google Scholar
23. S. Ulbrich et al.“Definition Der Begriffe Szene, Situation Und Szenario Fur Das Automatisierte Fahren”. In: 10. Workshop Fahrerassistenzsysteme FAS, 2015.Search in Google Scholar
24. Moritz Werling and Darren Liccardo. “Automatic Collision Avoidance Using Model-Predictive Online Optimization”. In: IEEE Conf. on Decision and Control, 2012.10.1109/CDC.2012.6426612Search in Google Scholar
25. J. Ziegler et al.“Making Bertha Drive — An Autonomous Journey on a Historic Route”. IEEE Intell. Transp. Syst. Mag. 6.2 (So. 2014).10.1109/MITS.2014.2306552Search in Google Scholar
26. J. Ziegler et al.“Trajectory Planning for Bertha — A Local, Continuous Method”. In: IEEE Intell. Veh. Symp. Proc., pp. 450–457, Juni 2014.10.1109/IVS.2014.6856581Search in Google Scholar
© 2021 Walter de Gruyter GmbH, Berlin/Boston