Abstract
This study introduces a strategy inspired by cooperative behavior in nature to enhance information sharing among autonomous vehicles (AVs), advancing intelligent transportation systems. However, in the context of multiple light detection and ranging (LiDAR)-equipped vehicles cooperating, the generated point cloud data can obstruct real-time environment perception. This research assumes real-time, lossless data transmission, and accurate and reliable pose information sharing between cooperative vehicles. Based on human-inspired principles and computer imaging techniques, a method was proposed to encode dynamic grids for fusion LiDAR point cloud data, contingent upon inter-vehicle distances. Each grid cell corresponds to an image pixel, creating smaller cells for dense point clouds and larger cells for sparse point clouds. This maintains an approximately equal number of point clouds per cell. Additionally, a ground segmentation approach is developed, based on density and elevation differences of adjacent grids to retain significant obstacle points. A grid density-based adjacent clustering approach was proposed, which effectively classified the connected grid cells containing the obstacle points. Experiments using the robot operating system on a standard computer with public data show that the perception processing period for six cooperative vehicles is merely 43.217 ms. This demonstrates the efficacy of our method in handling large volumes of LiDAR point cloud data. Comparative analysis with three alternative methods confirmed the superior accuracy and recall of our clustering approach. This underscores the robustness of our biologically inspired methodology for the design of cooperative perception, thereby promoting efficient and safe vehicle navigation.
Similar content being viewed by others
Data Availability
A publicly available dataset was analyzed in this study. The data can be found here: https://mobility-lab.seas.ucla.edu/opv2v/(access on 17 March 2022).
References
Khatab E, Onsy A, Varley M, Abouelfarag A. Vulnerable objects detection for autonomous driving: a review. Integration. 2021;78:36–48.
Su Z, Hui Y, Luan TH, Liu Q, Xing R. Deep learning based autonomous driving in vehicular networks. 2020. p. 131–50.
Tsukada M, Oi T, Ito A, Hirata M, Esaki H. AutoC2X: open-source software to realize V2X cooperative perception among autonomous vehicles. In: 2020 IEEE 92nd Vehicular Technology Conference (VTC2020-Fall). 2020. p. 1–6.
Cui G, Zhang W, Xiao Y, Yao L, Fang Z. Cooperative perception technology of autonomous driving in the internet of vehicles environment: a review. Sensors. 2022;22(15).
Xu R, Guo Y, Han X, Xia X, Xiang H, Ma J. OpenCDA: an open cooperative driving automation framework integrated with co-simulation. CoRR. abs/2107.06260. 2021.
Qian C, Zhang H, Li W, Tang J, Liu H, Li B. Cooperative GNSS-RTK ambiguity resolution with GNSS, INS, and LiDAR data for connected vehicles. Remote Sens. 2020;12(6).
Zeng Y, Qin H, Wang K, Li Q. A survey of LiDAR-based perception for autonomous driving: from detection to segmentation. IEEE Trans Intell Transp Syst. 2021;22(1):449–69.
Yuan C, Lyu L, Sun H, Li X. LiDAR-based pedestrian detection in autonomous driving: recent advances and future research directions. IEEE Trans Intell Transp Syst. 2021;22(1):2–19.
Zhang Z, Han S, Yi H, Duan F, Kang F, Sun Z, Solé-Casals J, Caiafa C. A brain-controlled vehicle system based on steady state visual evoked potentials. Cognit Comput. 2022.
An Y, Shi J, Gu D, Liu Q. Visual-LiDAR SLAM based on unsupervised multi-channel deep neural networks. Cogn Comput. 2022;14(4):1496–508.
Yumer E, Abdel-Qader Y. Multi-vehicle cooperative perception using LiDAR: a comprehensive review and future directions. IEEE Trans Intell Veh. 2021;6(2):164–81.
Abdel-Qader Y, Yumer E. Multi-vehicle cooperative perception using LiDAR: low-level fusion, feature-level fusion, and high-level fusion. Sensors. 2021;21(6):2114.
Nguyen C, de Lucas M, Dario P. Multi-vehicle cooperative perception using LiDAR-based low-level sensor fusion and graph optimization. Robot Autonom Syst. 2021;143:104235.
Liu K, Huang Y, Zhao F, Wang Z. Cooperative perception for autonomous vehicles using LiDAR and V2X communication. IEEE Trans Veh Technol. 2020;69(3):2821–33.
Zhang C, Zhang X, Wang B. A feature-level fusion approach for multi-vehicle cooperative perception using LiDAR and radar sensors. Sens Actuators A. 2023;324:112859.
Chen Q, Zhang J, Chen R, Shen W. Multi-vehicle cooperative perception and localization based on high-level fusion of LiDAR and map data. J Adv Transport. 2022.
Zhao J, Chen Q, Shen W. Multi-vehicle cooperative perception and localization based on high-level fusion of LiDAR and camera data. In: Proceedings of the 15th International Conference on Machine Vision (ICMV 2022); 2022. vol. 8934, p. 893401.
Pratibha C, Kumar A, Kamboj V. Partition-based clustering for real-time processing of LiDAR point clouds in autonomous vehicles. Sensors. 2021;21(9):3083.
Shang R, Ara B, Zada I, Nazir S, Ullah Z, Khan SU. Analysis of simple k-mean and parallel k-mean clustering for software products and organizational performance using education sector dataset. Sci Program. 2021;1–20:2021.
Daniel K, Friedrich F. Cognitive clustering of traffic scenarios for autonomous driving. In: IEEE Transactions on Intelligent Transportation Systems, vol. 21. 2020.
Liu S, Wang Y, Zhang T, Huang H. Real-time multi-LiDAR-based dynamic object detection with hierarchical clustering. IEEE Trans Intell Veh. 2021;6(2):148–58.
Zhang X, Zhang L, Zhang Y, Yingjie W, Jiao L. A cognitive hierarchical clustering algorithm for object detection on autonomous driving scenes. IEEE Access. 2020;8:99216–26.
Yoo S, Kim S, Kim K. A novel distance-based clustering algorithm for LiDAR point cloud in autonomous driving systems. Sensors. 2021;21(8):2896.
Lin C, Yu W. Real-time obstacle detection and avoidance for autonomous vehicles using LiDAR and distance-based clustering algorithm. In: 2020 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), IEEE; 2020. p. 963–7.
Ester M, Kriegel H-P, Sander J, Xu X. A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, KDD’96, AAAI Press; 1996. p. 226–31.
Yoon H, Jeong J, Jang M, Kim J, Lee K, Lee S. Cognitive-based cluster analysis for improving object detection performance in autonomous vehicles. IEEE Trans Intell Transp Syst. 2019;20(7):2718–30.
Li S-S. An improved DBSCAN algorithm based on the neighbor similarity and fast nearest neighbor query. IEEE Access. 2020;8:47468–76.
Chen W, Li C, Huang F, Liu Y, El-Sheimy N. Efficient real-time detection of pedestrians using 3D LiDAR and grid-based clustering algorithm. IEEE Trans Veh Technol. 2021;70(9):8833–43.
Yang H, Wang Z, Lin L, Liang H, Huang W, Xu F. Two-layer-graph clustering for real-time 3D LiDAR point cloud segmentation. Appl Sci. 2020;10(23):11.
Klasing K, Wollherr D, Buss M. A clustering method for efficient segmentation of 3D laser data. In: 2008 IEEE International Conference on Robotics and Automation. 2008. p. 4043–8.
Zhu L, Zhang K, Ma L, Liu W. Cognitive inspired clustering for scene segmentation in autonomous driving. IEEE Trans Intell Transp Syst. 2019;20(2):596–606.
Li Y, Zhang K, Zhu L, Liu W. A cognitive clustering algorithm for multi-layer object detection in autonomous driving. IEEE Trans Intell Transp Syst. 2019;21(4):1672–82.
Rajamäki J, Mademlis I, Riekki J. A cognitive architecture for multi-vehicle cooperative perception. IEEE Trans Cognit Develop Syst. 2017;9(3):241–53.
Hurl B, Cohen R, Czarnecki K, Waslander S. TruPercept: trust modelling for autonomous vehicle cooperative perception from synthetic data. In: 2020 IEEE Intelligent Vehicles Symposium (IV). 2020. p. 341–7.
Duan X, Jiang H, Tian D, Zou T, Zhou J, Cao Y. V2I based environment perception for autonomous vehicles at intersections. China Commun. 2021;18(7):1–12.
Chen Q, Tang S, Hochstetler J, Guo J, Li Y, Xiong J, Yang Q, Fu S. Low-latency high-level data sharing for connected and autonomous vehicular networks. In: 2019 IEEE International Conference on Industrial Internet (ICII). 2019. p. 287–96.
Metzner A, Wickramarathne T. Exploiting vehicle-to-vehicle communications for enhanced situational awareness. In: 2019 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA). 2019. p. 88–92.
Xu R, Xiang H, Xia X, Han X, Liu J, Ma J. OPV2V: an open benchmark dataset and fusion pipeline for perception with vehicle-to-vehicle communication. CoRR. abs/2109.07644. 2021.
Ma Y, Liu Y, Dai M, Yang Y. A LiDAR based height difference threshold segmentation method for ground extraction in autonomous driving. Sensors. 2021;21(7):2569.
Guo H, Wang Y, Mao K, Li T, Zhou J, Mao J. Ground feature extraction from LiDAR data using height difference threshold segmentation. Remote Sens Lett. 2022;13(4):382–90.
Li C, Zhang X, Zhao Q, Tong X. Improved height difference threshold segmentation method for LiDAR-based ground extraction. Remote Sens. 2023;15(2):389.
Shen Z, Liang H, Lin L, Wang Z, Huang W, Yu J. Fast ground segmentation for 3D LiDAR point cloud based on jump-convolution-process. Remote Sens. 2021;13(16).
Grubbs FE. Procedures for detecting outlying observations in samples. Technometrics. 1969;11(1):1–21.
Funding
This work was partially supported by the Youth Innovation Promotion Association of the Chinese Academy of Sciences (Grant No. Y2021115).
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Material preparation, data collection, and analysis were performed by XK, HZ, BY, and BL. The first draft of the manuscript was written by XK, and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Ethics Approval
This article does not contain any studies involving human participants and/or animals by any of the authors.
Competing Interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Kuang, X., Zhu, H., Yu, B. et al. Fast Clustering for Cooperative Perception Based on LiDAR Adaptive Dynamic Grid Encoding. Cogn Comput 16, 546–565 (2024). https://doi.org/10.1007/s12559-023-10211-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12559-023-10211-x