CoChat
Sign Up
Cited by 379Autonomous Vehicle Technology and SafetyReinforcement Learning in RoboticsTraffic control and management

Navigating Occluded Intersections with Autonomous Vehicles Using Deep Reinforcement Learning

Open access
Isele, David, Rahimi, Reza, Cosgun, Akansel, Subramanian, Kaushik, Fujimura, Kikuo·2018·2018 IEEE International Conference on Robotics and Automation (ICRA)
DOI 10.1109/icra.2018.8461233
Open this paper in CoChat — free accountOpen PDF

Abstract

Providing an efficient strategy to navigate safely through unsignaled intersections is a difficult task that requires determining the intent of other drivers. We explore the effectiveness of Deep Reinforcement Learning to handle intersection problems. Using recent advances in Deep RL, we are able to learn policies that surpass the performance of a commonly-used heuristic approach in several metrics including task completion time and goal success rate and have limited ability to generalize. We then explore a system's ability to learn active sensing behaviors to enable navigating safely in the case of occlusions. Our analysis, provides insight into the intersection handling problem, the solutions learned by the network point out several shortcomings of current rule-based methods, and the failures of our current deep reinforcement learning system point to future research directions.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/icra.2018.8461233

Cites

3 of 3 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Manual user interfaces for secondary tasks are more desired than their visual counterparts.

    “Manual user interfaces for secondary tasks are more desired than their visual counterparts [269].”

    From A Survey of Autonomous Driving: <i>Common Practices and Emerging Technologies</i> (2020) · cites this paper as [269]

    The Introduction (p. 1) discusses autonomous vehicles navigating occluded intersections, and the Conclusions (p. 6) discuss deep reinforcement learning for that task. Searches for manual versus visual user interfaces and preferences for secondary tasks found no passage addressing the claim. (LLM, conf=0.76)

    Experimental — accuracy not yet measured

  • Visual interface interactions require glances with durations between 0.6 and 1.6 seconds with a mean of 1.2 seconds.

    “Visual interface interactions require glances with durations between 0.6 and 1.6 seconds with a mean of 1.2 seconds [269].”

    From A Survey of Autonomous Driving: <i>Common Practices and Emerging Technologies</i> (2020) · cites this paper as [269]

    The Experiments with Occlusion section (p. 4) describes simulated intersections, and the Algorithm Comparison Study (p. 3) reports simulation timing and performance metrics. Searches for visual-interface glances and the stated 0.6–1.6-second range and 1.2-second mean found no passage addressing glance durations. (LLM, conf=0.76)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 24

  1. [1][1] M. R. Hafner, D. Cunningham, L. Caminiti, and D. Del Vecchio, 'Cooperative collision avoidance at intersections: Algorithms and experiments,' IEEE Transactions on Intelligent Transportation Systems , vol. 14, no. 3, pp. 1162-1175, 2013. -
  2. [2][2] J. Alonso, V. Milan´ es, J. P´ erez, E. Onieva, C. Gonz´ alez, and T. De Pedro, 'Autonomous vehicle control systems for safe crossroads,' Transportation research part C: emerging technologies , vol. 19, no. 6, pp. 1095-1110, 2011. -
  3. [3][3] M. M. Minderhoud and P. H. Bovy, 'Extended time-to-collision measures for road traffic safety assessment,' Accident Analysis &amp; Prevention , vol. 33, no. 1, pp. 89-97, 2001. -
  4. [5][5] K. Vogel, 'A comparison of headway and time to collision as safety indicators,' Accident analysis &amp; prevention , vol. 35, no. 3, pp. 427433, 2003. -
  5. [6][6] D. Ferguson, C. Baker, M. Likhachev, and J. Dolan, 'A reasoning framework for autonomous urban driving,' in Intelligent Vehicles Symposium, 2008 IEEE . IEEE, 2008, pp. 775-780. -
  6. [7][7] S. Kammel, J. Ziegler, B. Pitzer, M. Werling, T. Gindele, D. Jagzent, J. Sch¨ oder, M. Thuy, M. Goebl, F. von Hundelshausen, et al. , 'Team AnnieWays autonomous system for the DARPA urban challenge 2007,' in The DARPA Urban Challenge . Springer, 2009, pp. 359-391. -
  7. [8][8] C. Urmson, J. Anhalt, D. Bagnell, C. Baker, R. Bittner, M. Clark, J. Dolan, D. Duggins, T. Galatali, C. Geyer, et al. , 'Autonomous driving in urban environments: Boss and the urban challenge,' Journal of Field Robotics , vol. 25, no. 8, pp. 425-466, 2008. -
  8. [9][9] A. Cosgun, L. Ma, J. Chiu, J. Huang, M. Demir, A. M. Anon, T. Lian, H. Tafish, and S. Al-Stouhi, 'Towards full automated drive in urban environments: A demonstration in gomentum station, california,' IEEE Intelligent Vehicles Symposium (IV) , 2017. -
  9. [10][10] L. Fletcher, S. Teller, E. Olson, D. Moore, Y. Kuwata, J. How, J. Leonard, I. Miller, M. Campbell, D. Huttenlocher, et al. , 'The MITCornell collision and why it happened,' Journal of Field Robotics , vol. 25, no. 10, pp. 775-807, 2008. -
  10. [11][11] M. Bojarski, D. Del Testa, D. Dworakowski, B. Firner, B. Flepp, P. Goyal, L. D. Jackel, M. Monfort, U. Muller, J. Zhang, et al. , 'End to end learning for self-driving cars,' arXiv:1604.07316 , 2016. - · arXiv
  11. [12][12] M. Bouton, A. Cosgun, and M. J. Kochenderfer, 'Belief state planning for navigating urban intersections,' IEEE Intelligent Vehicles Symposium (IV) , 2017. -
  12. [13][13] W. Song, G. Xiong, and H. Chen, 'Intention-aware autonomous driving decision-making in an uncontrolled intersection,' Mathematical Problems in Engineering , vol. 2016, 2016. -
  13. [14][14] S. Brechtel, T. Gindele, and R. Dillmann, 'Probabilistic decisionmaking under uncertainty for autonomous driving using continuous pomdps,' in Intelligent Transportation Systems (ITSC), 2014 IEEE 17th International Conference on . IEEE, 2014, pp. 392-399. -
  14. [16][16] Z. Wang, T. Schaul, M. Hessel, H. Van Hasselt, M. Lanctot, and N. De Freitas, 'Dueling network architectures for deep reinforcement learning,' arXiv:1511.06581 , 2015. - · arXiv
  15. [17][17] M. Zhang, Z. McCarthy, C. Finn, S. Levine, and P. Abbeel, 'Learning deep neural network policies with continuous memory states,' in Robotics and Automation (ICRA), 2016 IEEE International Conference on . IEEE, 2016, pp. 520-527. -
  16. [19][19] C. J. Watkins and P. Dayan, 'Q-learning,' Machine learning , vol. 8, no. 3-4, pp. 279-292, 1992. -
  17. [20][20] D. Krajzewicz, J. Erdmann, M. Behrisch, and L. Bieker, 'Recent development and applications of SUMO-simulation of urban mobility,' International Journal on Advances in Systems and Measurements (IARIA) , vol. 5, no. 3-4, 2012. -
  18. [21][21] D. Isele and A. Cosgun, 'Transferring autonomous driving knowledge on simulated and real intersections,' International Conference on Machine Learning Workshop (ICML-WS) , 2017. -
  19. [22][22] M. Treiber, A. Hennecke, and D. Helbing, 'Congested traffic states in empirical observations and microscopic simulations,' Physical Review E , vol. 62, no. 2, p. 1805, 2000. -
  20. [23][23] S. Krauss, 'Microscopic modeling of traffic flow: Investigation of collision free vehicle dynamics,' Ph.D. dissertation, Deutsches Zentrum fuer Luft-und Raumfahrt, 1998. -
  21. [24][24] A. S. Lakshminarayanan, S. Sharma, and B. Ravindran, 'Dynamic frame skip deep q network,' arXiv:1605.05365 , 2016. - · arXiv
  22. [26][26] T. Schaul, J. Quan, I. Antonoglou, and D. Silver, 'Prioritized experience replay,' arXiv:1511.05952 , 2015. - · arXiv
  23. [27][27] S. Shalev-Shwartz, S. Shammah, and A. Shashua, 'Safe, multiagent, reinforcement learning for autonomous driving,' arXiv preprint arXiv:1610.03295 , 2016. - · arXiv
  24. [30][30] D. Isele and A. Cosgun, 'Selective experience replay for lifelong learning,' AAAI Conference on Artificial Intelligence (AAAI) , 2018.

Cited by

Sorted by citations

Authors
Isele, D., Rahimi, R., Cosgun, A., Subramanian, K., & Fujimura, K.
Affiliations
  • University of Pennsylvania (US)
  • University of Virginia (US)
  • Honda Research Institute, USA (US)
  • Georgia Institute of Technology (US)
ORCID
Venue
2018 IEEE International Conference on Robotics and Automation (ICRA)
Publisher
IEEE
Published
2018-05
Pages
2034-2039
ISSN
1050-4729 (ISSN-L)
DOI
10.1109/icra.2018.8461233
OpenAlex
W2963625099
Cited by
379
References
3
Citations by year
2026: 17 · 2025: 25 · 2024: 47 · 2023: 54 · 2022: 71 · 2021: 64 · 2020: 56 · 2019: 28 · 2018: 14 · 2017: 3
FWCI
41.53
Type
conference paper
Language
en
Open access
Locations
  • Proceedings - IEEE International Conference on Robotics and Automation/Proceedings (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • Figshare (submittedVersion, cc-by)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
  • Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
  • Physical Sciences › Engineering › Control and Systems Engineering › Traffic control and management
Keywords
autonomous vehicles, deep reinforcement learning, active sensing, policy generalization

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review