Key technologies of multi-agent collaborative high definition map construc-tion

doi:10.11947/j.AGCS.2021.20210259

Abstract

Abstract: The higher the automatic driving degree, the higher requirements of a high definition map. Intelligent high definition maps can provide information for L5 level autonomous vehicles, which is an important direction for the development of high definition maps in the future. According to the current high definition map construction methods, the definition of multi-agent collaborative intelligent high definition map construction is proposed. Its construction framework and key technologies: multi-agent routing for data collection, multi-source heterogeneous integration data fusion and expression, road scene cognition, intelligent high definition map fusion, intelligent high-definition update are studied, and their corresponding appropriate technical schemes are proposed. Besides, the challenges in the further construction process are analyzed.

Key words: high definition map, path planning, road scene understanding, multi-source heterogeneous data processing

CLC Number:

P208

CHEN Long, LIU Kunhua, ZHOU Baoding, LI Qingquan. Key technologies of multi-agent collaborative high definition map construc-tion[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(11): 1447-1456.

References

[1] Navigation Data Standard.Publishing high-accuracy map standard for companies: industrial consortium pushes autonomous driving[EB/OL]. [2016-09-14]. https://www.Nds-association.org/wp-content/uploads/20160914-PR-E.pdf.
[2] DUPUIS M, STROBL M, GREZLIKOWSKI H. OpenDRIVE 2010 and beyond-status and future of the de facto standard for the description of road networks[C]//Proceedings of 2010 Driving Simulation Conference Europe. Paris, France: [s.n.], 2010: 231-242.
[3] 贺勇, 路昊, 王春香, 等. 基于多传感器的车道级高精细地图制作方法[J]. 长安大学学报(自然科学版), 2015, 35(S1):274-278. HE Yong, LU Hao, WANG Chunxiang, et al. Generation of precise lane-level maps based on multi-sensors[J]. Journal of Chang’an University (Natural Science Edition), 2015, 35(S1):274-278.
[4] LIU C, JIANG K, YANG D, et al. Design of a multi-layer lane-level map for vehicle route planning[C]//Proceedings of 2017 MATEC web of conferences. Les Ulis Cedex, France: EDP Sciences, 2017.
[5] SHIMADA H, YAMAGUCHI A, TAKADA H, et al. Implementation and evaluation of local dynamic map in safety driving systems[J]. Journal of Transportation Technologies, 2015, 5(2): 102.
[6] 刘经南,詹骄,郭迟,等.智能高精地图数据逻辑结构与关键技术[J].测绘学报,2019,48(8):939-953. DOI: 10.11947/j.AGCS.2019.20190125. LIU Jingnan, ZHAN Jiao, GUO Chi, et al. Data logic structure and key technologies on intelligent high-precision map[J]. Act Geodaetica et Cartographica Sinica, 2019,48(8):939-953. DOI: 10.11947/j.AGCS.2019.20190125.
[7] 李德仁. 移动测量技术及其应用[J]. 地理空间信息, 2006, 4(4): 1-5. LI Deren. Mobile mapping technology and its applications[J]. Geospatial Information, 2006, 4(4): 1-5.
[8] AL-FURHUD M A, AHMED Z H. Genetic algorithms for the multiple travelling salesman problem[J]. International Journal of Advanced Computer Science and Applications (IJACSA), 2020, 11(7): 553-560.
[9] CUEVAS A M C, MARTINEZ J A S, SAUCEDO J A M. A two stage method for the multiple traveling salesman problem[J]. International Journal of Applied Metaheuristic Computing (IJAMC), 2020, 11(3): 79-91.
[10] 万里鹏, 兰旭光, 张翰博, 等. 深度强化学习理论及其应用综述[J]. 模式识别与人工智能, 2019, 32(1): 67-81. WAN Lipeng, LAN Xuguang, ZHANG Hanbo, et al. A review of deep reinforcement learning theory and application[J]. Pattern Recognition and Artificial Intelligence, 2019, 32(1): 67-81.
[11] HU Y, YAO Y, LEE W S. A reinforcement learning approach for optimizing multiple traveling salesman problems over graphs[J]. Knowledge-Based Systems, 2020, 204: 106244.
[12] CARION N, USUNIER N, SYNNAEVE G, et al. A structured prediction approach for generalization in cooperative multi-agent reinforcement learning[J]. Advances in neural information processing systems, 2019, 32: 8130-8140.
[13] ZANGINA U, BUYAMIN S, AMAN M N, et al. Autonomous mobility of a fleet of vehicles for precision pesticide application[J]. Computers and Electronics in Agriculture, 2021, 186: 106217.
[14] LUO Z, POON M, ZHANG Z, et al. The multi-visit traveling salesman problem with multi-drones[J]. Transportation Research Part C: Emerging Technologies, 2021, 128: 103172.
[15] KRAEMER L, BANERJEE B. Multi-agent reinforcement learning as a rehearsal for decentralized planning[J]. Neurocomputing, 2016, 190: 82-94.
[16] ALLEN M W, HAHN D, MACFARLAND D C. Heuristics for multiagent reinforcement learning in decentralized decision problems[C]//Proceedings of 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL). Orlando, FL, USA: IEEE, 2014: 1-8.
[17] LIN T, DEBORD M J, ESTABRIDIS K, et al. Decentralized multi-agents by imitation of a centralized controller[C]//Proceedings of 2019 International Conference on Robotics and Automation (ICRA). Montreal, Canada: IEEE, 2019: 7990-7996.
[18] KONG X, XIN B, Wang Y, et al. Collaborative deep reinforcement learning for joint object search[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Hawaii, USA: IEEE, 2017: 1695-1704.
[19] NGUYEN T T, NGUYEN N D, NAHAVANDI S. Deep reinforcement learning for multiagent systems: a review of challenges, solutions, and applications[J]. IEEE transactions on cybernetics, 2020, 50(9): 3826-3839.
[20] BOROSON, ELIZABETH R, NORA A. 3D keypoint repeatability for heterogeneous multi-robot SLAM[C]//Proceedings of 2019 International Conference on Robotics and Automation (ICRA). Montreal, Canada: IEEE, 2019: 6337-6343.
[21] CADENA C, CARLONE L, CARRILLO H, et al. Past, present, and future of simultaneous localization and mapping: toward the robust-perception age[J]. IEEE Transactions on robotics, 2016, 32(6): 1309-1332.
[22] WANG K, GAO F, SHEN S. Real-time scalable dense surfel mapping[C]//Proceedings of 2019 International Conference on Robotics and Automation (ICRA). Montreal, Canada: IEEE, 2019: 6919-6925.
[23] CHEN L, ZHAN W, TIAN W, et al. Deep integration: a multi-label architecture for road scene recognition[J]. IEEE Transactions on Image Processing, 2019, 28(10): 4883-4898.
[24] CHEN J, LEI B, SONG Q, et al. A hierarchical graph network for 3D object detection on point clouds[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WDC: IEEE, 2020: 392-401.
[25] 陈世增, 李必军, 周继苗. 利用双灭点估计的车道线检测[J]. 测绘通报, 2020(1): 16-20. CHEN Shizeng, LI Bijun, ZHOU Jimiao. Lane detection with double vanishing points estimation[J]. Bulletin of Surveying and Mapping, 2020(1): 16-20.
[26] LONG S U N, TAO W U, GUANGCAI S U N, et al. Object detection research of SAR image using improved faster region-based convolutional neural network[J]. Journal of Geodesy and Geoinformation Science, 2020, 3(3): 18-28.
[27] ZHONG Z, LIN Z Q, BIDART R, et al. Squeeze-and-attention networks for semantic segmentation[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WDC, USA: IEEE, 2020: 13065-13074.
[28] ZHOU D, FANG J, SONG X, et al. Joint 3D instance segmentation and object detection for autonomous driving[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WDC, USA: IEEE, 2020: 1839-1849.
[29] ZHAO L, MO Q, LIN S, et al. UCTGAN: Diverse image inpainting based on unsupervised cross-space translation[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WDC, USA: IEEE, 2020: 5741-5750.
[30] HUANG Z, YU Y, XU J, et al. PF-Net: Point fractal network for 3D point cloud completion[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WDC, USA: IEEE, 2020: 7662-7670.
[31] GONG K, GAO Y, LIANG X, et al. Graphonomy: Universal human parsing via graph transfer learning[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. California, USA: IEEE, 2019: 7450-7459.
[32] XU H, FANG L, LIANG X, et al. Universal-rcnn: universal object detector via transferable graph r-cnn[C]//Proceedings of 2020 AAAI Conference on Artificial Intelligence. New York, USA: AAAI, 2020, 34(7): 12492-12499.
[33] YU W, ZHOU J, YU W, et al. Heterogeneous graph learning for visual commonsense reasoning[J]. Advances in Neural Information Processing Systems, 2019(32): 2769-2779.
[34] MCCORMAC J, HANDA A, DAVISON A, et al. Semantic fusion: dense 3D semantic mapping with convolutional neural networks[C]//Proceedings of 2017 IEEE International Conference on Robotics and automation (ICRA). Singapore: IEEE, 2017: 4628-4635.
[35] CAMPOS C, ELVIRA R, RODRÍGUEZ J J G, et al. ORB-SLAM3: an accurate open-source library for visual, visual-inertial, and multimap SLAM[J]. IEEE Transactions on Robotics, 2021, 42(9): 1-17.
[36] GAO X, WANG R, DEMMEL N, et al. LDSO: direct sparse odometry with loop closure[C]//Proceedings of 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Madrid, Spain: IEEE, 2018: 2198-2204.
[37] ATANASOV N, BOWMAN S L, DANIILIDIS K, et al. A unifying view of geometry, semantics, and data association in SLAM[C]//Proceedings of 2018 International Joint Conference on Artificial Intelligence (IJCAI). Stockholm, Sweden: IJCAI, 2018: 5204-5208.
[38] ZHANG S Q, ZHANG Q, LIN J. Efficient communication in multi-agent reinforcement learning via variance based control[C]//Proceedings of 2019 International Conference on Neural Information Processing Systems.Vancouver, Canada: MIT, 2019: 3235-3244.
[39] LI H, OTA K, DONG M. Learning IoT in edge: deep learning for the internet of things with edge computing[J]. IEEE network, 2018, 32(1): 96-101.