Real-Time Inter-Vehicle Data Fusion Based on a New Metric for Evidence Distance in Autonomous Vehicle Systems
Source abstract
Abstract
Safety is a major concern for autonomous vehicle driving. The autonomous vehicles relying solely on ego-vehicle sensors have limitations in dealing with collisions. The risk can be reduced by communicating with other vehicles sharing sensed information. In this paper, we study a real-time multisource data fusion scheme based on Dempster–Shafer theory of evidence (DS) through cooperative vehicle-to-vehicle (V2V) communications. The classical DS can produce erroneous outputs when confidences are highly conflicting. In particular, a false negative error on object detection may lead to serious accidents. We propose a novel metric to measure distance between confidences on the collected data taking the asymmetry in the importance of sensed events into account. Based on the proposed distance, we consider the weighted DS combination in order to fuse multiple confidences. The proposed scheme is simple, and enables the vehicles to combine confidences in real-time. From real-world experiments, we show that it is feasible to lower the false negative rate by the proposed data fusion scheme, and to avoid accidents using the proposed collision warning system.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Autonomous Vehicle Technology and Safety · Traffic and Road Safety · Human-Automation Interaction and Safety
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer and Radio Communications Engineering, Korea University, Seoul 02841, Korea
Department of Computer Science and Engineering Software, Korea University, Seoul 02841, Korea
Funding
National Research Foundation of Korea
References (76)
Show source-provided references
1. Singh, S. (2015). Critical reasons for crashes investigated in the national motor vehicle crash causation survey, Traffic Safety Facts-Crash Stats.
2. Preparing a nation for autonomous vehicles: Opportunities, barriers and policy recommendations10.1016/j.tra.2015.04.003 ↗
3. Betz, J., Heilmeier, A., Wischnewski, A., Stahl, T., and Lienkamp, M. (2019). Autonomous Driving-A Crash Explained in Detail. Appl. Sci., 9.10.3390/app9235126 ↗
4. Collision avoidance/mitigation system: Motion planning of autonomous vehicle via predictive occupancy map10.1109/ACCESS.2019.2912067 ↗
5. Aghav, J., Hirwe, P., and Nene, M. (2017, January 23–24). Deep Learning for Real Time Collision Detection and Avoidance. Proceedings of the International Conference on Communication, Computing and Networking, Chandigarh, India.
6. Nobis, F., Geisslinger, M., Weber, M., Betz, J., and Lienkamp, M. (2019, January 15–17). A Deep Learning-based Radar and Camera Sensor Fusion Architecture for Object Detection. Proceedings of the 2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF2019), Bonn, Germany.10.1109/SDF.2019.8916629 ↗
7. Fukatsu, R., and Sakaguchi, K. (May, January 28). Millimeter-Wave V2V communications with cooperative perception for automated driving. Proceedings of the 2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring), Kuala Lumpur, Malaysia.10.1109/VTCSpring.2019.8746344 ↗
8. Perfecto, C., Del Ser, J., Bennis, M., and Bilbao, M.N. (2017, January 12–15). Beyond WYSIWYG: Sharing contextual sensing data through mmWave V2V communications. Proceedings of the 2017 European Conference on Networks and Communications (EuCNC), Oulu, Finland.10.1109/EuCNC.2017.7980726 ↗
9. Jung, C., Lee, D., Lee, S., and Shim, D.H. (2020). V2X-Communication-Aided Autonomous Driving: System Design and Experimental Validation. Sensors, 20.10.3390/s20102903 ↗
10. Yang, X., Liu, L., Vaidya, N.H., and Zhao, F. (2004, January 26). A vehicle-to-vehicle communication protocol for cooperative collision warning. Proceedings of the First Annual International Conference on Mobile and Ubiquitous Systems: Networking and Services, Boston, MA, USA.
11. V2X access technologies: Regulation, research, and remaining challenges10.1109/COMST.2018.2808444 ↗
12. IEEE 1609 Working Group (2016). IEEE Standard for Wireless Access in Vehicular Environments (WAVE)-Multi-Channel Operation, IEEE Standards Associations. IEEE Std 1609.4-2016.
13. Azzaoui, N., Korichi, A., Brik, B., Fekair, M.E.A., and Kerrache, C.A. (2019, January 2–4). Wireless communication in internet of vehicles networks: DSRC-based Vs cellular-based. Proceedings of the 4th International Conference on Smart City Applications, Casablanca, Morocco.10.1145/3368756.3368998 ↗
14. Mahmood, A., Zhang, W.E., and Sheng, Q.Z. (2019). Software-defined heterogeneous vehicular networking: The architectural design and open challenges. Future Internet, 11.10.3390/fi11030070 ↗
15. Chen, J., Ye, F., and Jiang, T. (2017, January 19–22). Numerical analyses of modified DS combination methods based on different distance functions. Proceedings of the 2017 Progress in Electromagnetics Research Symposium-Fall (PIERS-FALL), Singapore.10.1109/PIERS-FALL.2017.8293499 ↗
16. Anomaly-based intrusion detection of jamming attacks, local versus collaborative detection
17. Shafer, G. (1976). A Mathematical Theory of Evidence, Princeton University Press.10.1515/9780691214696 ↗
18. A flexible rule for evidential combination in Dempster-Shafer theory of evidence10.1016/j.asoc.2019.105512 ↗
19. Chen, Q., and Aickelin, U. (2006, January 26–29). Anomaly detection using the Dempster-Shafer method. Proceedings of the International Conference on Data Mining 2006, Las Vegas, NV, USA.10.2139/ssrn.2831339 ↗
20. Siaterlis, C., and Maglaris, B. (2004, January 14–17). Towards multisensor data fusion for DoS detection. Proceedings of the 2004 ACM Symposium on Applied Computing, Nicosia, Cyprus.10.1145/967900.967992 ↗
21. Sakr, A.H., and Bansal, G. (2016, January 1–4). Cooperative localization via DSRC and multisensor multi-target track association. Proceedings of the 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), Rio de Janeiro, Brazil.10.1109/ITSC.2016.7795533 ↗
22. Li, T., Choi, M., Guo, Y., and Lin, L. (2018, January 10–13). Opinion mining at scale: A case study of the first self-driving car fatality. Proceedings of the 2018 IEEE International Conference on Big Data (Big Data), Seattle, WA, USA.10.1109/BigData.2018.8622211 ↗
23. Khan, N., and Anwar, S. (2019, January 29–31). Improved Dempster-Shafer Sensor Fusion using Distance Function and Evidence Weighted Penalty: Application in Object Detection. Proceedings of the ICINCO 2019, Prague, Czech Republic.10.5220/0007917106640671 ↗
24. A new distance between two bodies of evidence10.1016/S1566-2535(01)00026-4 ↗
25. Combining belief functions based on distance of evidence10.1016/j.dss.2004.04.015 ↗
26. Weighted evidence combination rule based on evidence distance and uncertainty measure: An application in fault diagnosis
27. A New Distance Measure of Belief Function in Evidence Theory10.1109/ACCESS.2019.2917630 ↗
28. Aeberhard, M., Paul, S., Kaempchen, N., and Bertram, T. (2011, January 5–9). Object existence probability fusion using dempster-shafer theory in a high-level sensor data fusion architecture. Proceedings of the 2011 IEEE Intelligent Vehicles Symposium (IV), Baden-Baden, Germany.10.1109/IVS.2011.5940430 ↗
29. Claussmann, L., O’Brien, M., Glaser, S., Najjaran, H., and Gruyer, D. (2018, January 26–30). Multi-criteria decision making for autonomous vehicles using fuzzy dempster-shafer reasoning. Proceedings of the 2018 IEEE Intelligent Vehicles Symposium (IV), Suzhou, China.10.1109/IVS.2018.8500451 ↗
30. Mouhagir, H., Cherfaoui, V., Talj, R., Aioun, F., and Guillemard, F. (2017, January 9–14). Trajectory planning for autonomous vehicle in uncertain environment using evidential grid. Proceedings of the 20th International Federation of Automatic Control World Congress, Toulouse, France.
31. Laghmara, H., Boudali, M.-T., Laurain, T., Ledy, J., Orjuela, R., Lauffenburger, J.-P., and Basset, M. (2019, January 9–12). Obstacle Avoidance, Path Planning and Control for Autonomous Vehicles. Proceedings of the 2019 IEEE Intelligent Vehicles Symposium (IV), Paris, France.10.1109/IVS.2019.8814173 ↗
32. Xu, F., Liang, H., Wang, Z., Lin, L., and Chu, Z. (2018, January 11–14). A Real-Time Vehicle Detection Algorithm Based on Sparse Point Clouds and Dempster-Shafer Fusion Theory. Proceedings of the 2018 IEEE International Conference on Information and Automation (ICIA), Fujian, China.10.1109/ICInfA.2018.8812461 ↗
33. Analyzing the degree of conflict among belief functions10.1016/j.artint.2006.05.002 ↗
34. A new distance between BPAs based on the power-set-distribution pignistic probability function10.1007/s10489-017-1018-9 ↗
35. A novel method to use fuzzy soft sets in decision making based on ambiguity measure and Dempster-Shafer theory of evidence An application in medical diagnosis10.1016/j.artmed.2016.04.004 ↗
36. Measuring ambiguity in the evidence theory10.1109/TSMCA.2005.853483 ↗
37. Hafner, M., Cunningham, D., Caminiti, L., and Del Vecchio, D. (2011, January 16–20). Automated vehicle-to-vehicle collision avoidance at intersections. Proceedings of the World Congress on Intelligent Transport Systems, Orlando, FL, USA.
38. Cooperative Collision Avoidance for Overtaking Maneuvers in Cellular V2X-Based Autonomous Driving10.1109/TVT.2019.2906509 ↗
39. Vehicle-localization-based and DSRC-based autonomous vehicle rear-end collision avoidance concerning measurement uncertainties10.1002/tee.22936 ↗
40. Aparicio-Navarro, F.J., Kyriakopoulos, K.G., and Parish, D.J. (2011, January 10–11). An on-line wireless attack detection system using multi-layer data fusion. Proceedings of the 2011 IEEE International Workshop on Measurements and Networking Proceedings (M&N), Anacapri, Italy.10.1109/IWMN.2011.6088478 ↗
41. Yu, D., and Frincke, D. (2005, January 18–20). Alert confidence fusion in intrusion detection systems with extended Dempster-Shafer theory. Proceedings of the 43rd Annual Southeast Regional Conference, Kennesaw, GA, USA.10.1145/1167253.1167289 ↗
42. Folster, F., Rohling, H., and Lubbert, U. (2005, January 9–12). An automotive radar network based on 77 GHz FMCW sensors. Proceedings of the IEEE International Radar Conference, Arlington, VA, USA.
43. Sentz, K., and Ferson, S. (2002). Combination of evidence in Dempster-Shafer Theory.10.2172/800792 ↗
44. Saxena, S., Isukapati, I.K., Smith, S.F., and Dolan, J.M. (2019, January 27–30). Multiagent Sensor Fusion for Connected & Autonomous Vehicles to Enhance Navigation Safety. Proceedings of the 2019 IEEE Intelligent Transportation Systems Conference (ITSC), Auckland, New Zealand.10.1109/ITSC.2019.8917298 ↗
45. Autonomous vehicle perception: The technology of today and tomorrow10.1016/j.trc.2018.02.012 ↗
46. Gentle, J.E. (2007). Matrix Algebra: Theory, Computations, and Applications in Statistics, Springer.10.1007/978-0-387-70873-7 ↗
47. Combining belief functions when evidence conflicts10.1016/S0167-9236(99)00084-6 ↗
48. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
49. Vehicle classification with confidence by classified vector quantization10.1109/MITS.2013.2245725 ↗
50. Amato, G., Falchi, F., and Gennaro, C. (July, January 30). Geometric consistency checks for kNN based image classification relying on local features. Proceedings of the Fourth International Conference of Similarity Search and Application, Lipari, Italy.
51. Guo, C., Pleiss, G., Sun, Y., and Weinberger, K.Q. (2017, January 6–11). On calibration of modern neural networks. Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia.
52. Kull, M., Nieto, M.P., Kangsepp, M., Silva Filho, T., Song, H., and Flach, P. (2019, January 8–14). Beyond temperature scaling: Obtaining well-calibrated multi-class probabilities with Dirichlet calibration. Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, BC, Canada.
53. Alotibi, F., and Abdelhakim, M. (2019, January 22–25). Anomaly Detection in Cooperative Adaptive Cruise Control Using Physics Laws and Data Fusion. Proceedings of the 2019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall), Honolulu, HI, USA.10.1109/VTCFall.2019.8891165 ↗
54. Yan, Z.-Z., Yan, X.-P., Xie, L., and Wang, Z. (2011, January 28–31). The research of weighted-average fusion method in inland traffic flow detection. Proceedings of the International Conference on Information Computing and Applications, Qinhuangdao, China.10.1007/978-3-642-25255-6_12 ↗
55. Wang, Y., Chen, H., Zhang, Q., and Lv, H. (2018, January 28–30). The application of multiple wireless sensor data fusion algorithm in temperature monitoring system. Proceedings of the WCSE, Bangkok, Tahiland.
56. Research on data fusion of adaptive weighted multisource sensor
57. Radar measurement accuracy associated with target RCS fluctuation10.1049/el.2017.0901 ↗
58. Zhang, Z., Nan, X., and Wang, C. (2019). Real-Time Weighted Data Fusion Algorithm for Temperature Detection Based on Small-Range Sensor Network. Sensors, 19.10.3390/s19010064 ↗
59. Mandava, M., Gammenthaler, R.S., and Hocker, S.F. (2018, January 27–30). Vehicle Speed Enforcement Using Absolute Speed Handheld Lidar. Proceedings of the 2018 IEEE 88th Vehicular Technology Conference (VTC-Fall), Chicago, IL, USA.10.1109/VTCFall.2018.8690893 ↗
60. Weil, C.M., Camell, D., Novotny, D.R., and Johnk, R.T. (2004, January 17–19). Across-the-road photo traffic radars: New calibration techniques. Proceedings of the 15th International Conference on Microwaves, Radar and Wireless Communications, Warsaw, Poland.
61. Shahian Jahromi, B., Tulabandhula, T., and Cetin, S. (2019). Real-Time Hybrid Multi-Sensor Fusion Framework for Perception in Autonomous Vehicles. Sensors, 19.10.3390/s19204357 ↗
62. Computer architectures for autonomous driving10.1109/MC.2017.3001256 ↗
63. Bechtel, M.G., McEllhiney, E., Kim, M., and Yun, H. (2018, January 28–31). Deeppicar: A low-cost deep neural network-based autonomous car. Proceedings of the 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA), Hakodate, Japan.10.1109/RTCSA.2018.00011 ↗
64. Vision-based navigation of autonomous vehicles in roadway environments with unexpected hazards10.1177/0361198119855606 ↗
65. Vehicle speed measurement: Cosine error correction10.1016/j.measurement.2012.05.022 ↗
66. SAE (2020, September 28). Dedicated Short Range Communications (DSRC) Message Set Dictionary, Available online: https://one.nhtsa.gov/DOT/NHTSA/NRD/Multimedia/PDFs/Crash%20Avoidance/2008/811073.pdf.
67. Ahmed-Zaid, F., and Carter, A. (2009). Vehicle Safety Communications-Applications VSC-A, First Annual Report December 7, 2006 through December 31, 2007.
68. Javed, M.A., and Khan, J.Y. (2013, January 16–18). Performance analysis of a time headway based rate control algorithm for VANET safety applications. Proceedings of the 7th International Conference on Signal Processing and Communication Systems (ICSPCS), Gold Coast, Australia.10.1109/ICSPCS.2013.6723983 ↗
69. Empirical study of DSRC performance based on safety pilot model deployment data10.1109/TITS.2017.2649538 ↗
70. Graf, M., Speidel, O., and Dietmayer, K. (2019, January 9–12). Trajectory Planning for Automated Vehicles in Overtaking Scenarios. Proceedings of the 2019 IEEE Intelligent Vehicles Symposium (IV), Paris, France.10.1109/IVS.2019.8813854 ↗
71. Kim, Y., and Bang, H. (2018). Introduction to Kalman Filter and Its Applications. Kalman Filter, IntechOpen.10.5772/intechopen.80600 ↗
72. Lee, J., Kim, G., and Kim, B. (2019). Study on the Improvement of a Collision Avoidance System for Curves. Appl. Sci., 9.10.3390/app9245380 ↗
73. A cooperative formation-based collision avoidance approach for a group of autonomous vehicles10.1002/acs.2563 ↗
74. Millimeter-wave technology for automotive radar sensors in the 77 GHz frequency band10.1109/TMTT.2011.2178427 ↗
75. Liu, X., and Jaekel, A. (2019). Congestion control in V2V safety communication: Problem, analysis, approaches. Electronics, 8.10.3390/electronics8050540 ↗
76. Acceleration-deceleration behaviour of various vehicle types10.1016/j.trpro.2017.05.486 ↗