面向不确定性环境的自动驾驶运动规划:机遇与挑战

doi:10.16451/j.cnki.issn1003-6059.202301001

摘要
图/表
参考文献(0)
相关文章 (2)

全文: PDF (4027 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要

运动规划算法作为自动驾驶系统中的重要研究内容,愈发受到研究者们关注.然而目前多数算法仅考虑在确定性结构化环境中的应用,忽视动态交通环境中潜在的不确定性因素.文中面向不确定性环境,将运动规划算法总结为两类:部分可观测马尔可夫决策过程(POMDP)和概率占用栅格图(POGM),从理论基础、求解算法、实际应用三方面进行介绍.基于当前置信状态,POMDP计算使未来折扣奖励最大的策略.POGM使用概率表征对应栅格上的占用情况,衡量车流动态变化的可能性,良好表征不确定性情况.最后,总结不确定性环境中当前运动规划问题面临的主要挑战和未来可能的研究方向.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	张晓彤
	王嘉诚
	何景涛
	陈仕韬
	郑南宁

关键词 ：自动驾驶, 运动规划, 部分可观测马尔可夫决策过程(POMDP), 概率占用栅格图(POGM)

Abstract：

Motion planning algorithm, as an important part of autonomous driving systems, draws increasing attention from researchers. However, most existing motion planning algorithms only consider their application in deterministic structured environments, neglecting potential uncertainties in dynamic traffic environments. In this paper, motion planning algorithms are divided into two categories for the uncertain environment: partially observable Markov decision process and probability occupancy grid map.The two categories are introduced for three aspects: theoretical foundation, solution algorithm and practical application. The strategy with the maximum discounted reward in the future is calculated by partially observable Markov decision process based on the current confidence state. Probability occupancy grid map utilizes probability to represent the occupancy status of corresponding grids, measuring the possibility of dynamic changes in traffic flow, and well representing the uncertainty. Finally, the main challenges and future research directions for motion planning in uncertain environments are summarized .

Key words： Autonomous Driving Motion Planning Partially Observable Markov Decision Process(POMDP) Probability Occupancy Grid Map(POGM)

收稿日期: 2022-12-20

ZTFLH:

TP181

通讯作者: 郑南宁,博士,教授,主要研究方向为计算机视觉、模式识别.E-mail:nnzheng@mail.xjtu.edu.cn.

作者简介: 张晓彤,硕士研究生,主要研究方向为自动驾驶车辆的运动规划.E-mail:zxt19991118@stu.xjtu.edu.cn.王嘉诚,硕士研究生,主要研究方向为无人驾驶车辆的路径规划.E-mail:294022042@qq.com.何景涛,硕士研究生,主要研究方向为基于强化学习的自主导航.E-mail:.陈仕韬,博士,助教,主要研究方向为无人驾驶. E-mail:chenshitao@mail.xjtu.edu.cn.

引用本文:

张晓彤, 王嘉诚, 何景涛, 陈仕韬, 郑南宁. 面向不确定性环境的自动驾驶运动规划:机遇与挑战[J]. 模式识别与人工智能, 2023, 36(1): 1-21. ZHANG Xiaotong, WANG Jiacheng, HE Jingtao, CHEN Shitao, ZHENG Nanning. Motion Planning under Uncertainty for Autonomous Driving:Opportunities and Challenges. Pattern Recognition and Artificial Intelligence, 2023, 36(1): 1-21.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202301001 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2023/V36/I1/1

[1] THRUN S, MONTEMERLO M, DAHLKAMP H, et al. Stanley: The Robot That Won the DARPA Grand Challenge // BUEHLER M, IAGNEMNA K, SINGH S, eds. The 2005 DARPA Grand Cha-llenge. Berlin, Germany: Springer, 2007: 1-43.
[2] 秦志嫒,白文岭,贾宁.智能网联汽车企业技术路径解析.汽车与配件, 2019(9): 31-33.
(QIN Z Y, BAI W L, JIA N.Analysis of Technical Path of Intelli-gent Networked Vehicle Enterprises. Automobile and Parts, 2019(9): 31-33.)
[3] PALMEIRO A R, VAN DER KINT S, VISSERS L, et al. Interaction between Pedestrians and Automated Vehicles: A Wizard of Oz Experiment. Transportation Research Part F(Traffic Psychology and Behaviour), 2018, 58: 1005-1020.
[4] JUN M, CHAUDHRY A I, ANDREA R D.The Navigation of Autonomous Vehicles in Uncertain Dynamic Environments: A Case Study // Proc of the 41st IEEE Conference on Decision and Control. Washington, USA: IEEE, 2002: 3770-3775.
[5] KIBALOV V, SHIPITKO O.Safe Speed Control and Collision Pro-bability Estimation Under Ego-Pose Uncertainty for Autonomous Vehicle // Proc of the 23rd IEEE International Conference on Intelligent Transportation Systems. Washington, USA: IEEE, 2020. DOI: 10.1109/ITSC.45102.2020.9294531.
[6] BERNSTEIN D S, GIVAN R, IMMERMAN N, et al. The Comple-xity of Decentralized Control of Markov Decision Processes. Mathematics of Operations Research, 2002, 27(4): 819-840.
[7] 房俊恒. 基于点的值迭代算法在POMDP问题中的研究.硕士学位论文.苏州:苏州大学, 2015.
(FANG J H.Research on Point-Based Value Iteration Algorithm in POMDP Domains. Master Dissertation. Suzhou, China: Soochow University, 2015.)
[8] PINEAU J, GORDON G, THRUN S.Point-Based Value Iteration: An Anytime Algorithm for POMDPs // Proc of the 18th International Joint Conference on Artificial Intelligence. San Francisco, USA: Morgan Kaufmann, 2003: 1025-1030.
[9] BAI H Y, CAI S J, YE N, et al. Intention-Aware Online POMDP Planning for Autonomous Driving in a Crowd // Proc of the IEEE International Conference on Robotics and Automation. Washington, USA: IEEE, 2015: 454-460.
[10] LUO Y F, CAI P P, BERA A, et al. PORCA: Modeling and Planning for Autonomous Driving Among Many Pedestrians. IEEE Robotics and Automation Letters, 2018, 3(4): 3418-3425.
[11] CAI P P, LUO Y F, SAXENA A, et al. LeTS-Drive: Driving in a Crowd by Learning from Tree Search[C/OL].[2022-11-16]. https://arxiv.org/pdf/1905.12197.pdf.
[12] MONAHAN G E.State of the Art-A Survey of Partially Observable Markov Decision Processes: Theory, Models, and Algorithms. Management Science, 1982, 28(1): 1-16.
[13] JORRITSMA P H M. Incremental Region Enhanced Neural Q-Learning for Solving Model-Based POMDPs. Bachelor Dissertation. Groningen, The Netherlands: University of Groningen, 2011.
[14] HORÁK K, BOŠANSKý B, CHATTERJEE K. Goal-HSVI: Heuristic Search Value Iteration for Goal-POMDPs // Proc of the 27th International Joint Conference on Artificial Intelligence. San Francisco, USA: IJCAI, 2018: 4764-4770.
[15] 杜波. 启发式概率值迭代算法:一种求解POMDP问题的近似框架.硕士学位论文.南京:南京大学, 2014.
(DU B.Heuristic Probabilistic Value Iteration: An Approximation Framework for POMDPs. Master Dissertation. Nanjing, China: Nanjing University, 2014.)
[16] 孙湧,仵博,冯延蓬.基于策略迭代和值迭代的POMDP算法.计算机研究与发展, 2008, 45(10): 1763-1768.
(SUN Y, WU B, FENG Y P.A Policy- and Value- Iteration Algorithm for POMDP. Journal of Computer Research and Development, 2008, 45(10): 1763-1768.)
[17] CHEN Y C, KOCHENDERFER M J, SPAAN M T J. Improving Offline Value-Function Approximations for POMDPs by Reducing Discount Factors // Proc of the IEEE/RSJ International Conference on Intelligent Robots and Systems. Washington, USA: IEEE, 2018: 3531-3536.
[18] THRUN S.Monte Carlo POMDPs // Proc of the 12th International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 1999: 1064-1070.
[19] SILVER D, VENESS J.Monte-Carlo Planning in Large POMDPs // Proc of the 23rd International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2010, II: 2164-2172.
[20] NYLUND K L, ASPAROUHOV T, MUTHÉN B O. Deciding on the Number of Classes in Latent Class Analysis and Growth Mixture Modeling: A Monte Carlo Simulation Study. Structural Equation Modeling: A Multidisciplinary Journal, 2007, 14(4): 535-569.
[21] 郑红燕,仵博,冯延蓬,等.基于信念点裁剪策略树的POMDP求解算法.信息与控制, 2013, 42(1): 53-57.
(ZHENG H Y, WU B, FENG Y P, et al. Belief Point-Based POMDP Solution for Policy Tree Pruning. Information and Control, 2013, 42(1): 53-57.)
[22] WOLF T B, KOCHENDERFER M J.Aircraft Collision Avoidance Using Monte Carlo Real-Time Belief Space Search. Journal of Intelligent and Robotic Systems, 2011, 64: 277-298.
[23] 章宗长,陈小平.杂合启发式在线POMDP规划.软件学报, 2013, 24(7): 1589-1600.
(ZHANG Z C, CHEN X P.Hybrid Heuristic Online Planning for POMDPs. Journal of Software, 2013, 24(7): 1589-1600.)
[24] ZHANG Z Z, HSU D, LEE W S.Covering Number for Efficient Heuristic-Based POMDP Planning // Proc of the 31st International Conference on Machine Learning. San Diego, USA: JMLR, 2014: 28-36.
[25] 石轲. 基于马尔可夫决策过程理论的Agent决策问题研究.硕士学位论文.合肥:中国科学技术大学, 2010.
(SHI K.Research on Agent Decision Problem Based on Markov Decision Process Theory. Master Dissertation. Hefei, China: University of Science and Technology of China, 2010.)
[26] KARKUS P, HSU D, LEE W S.QMDP-Net: Deep Learning for Planning under Partial Observability // Proc of the 31st International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2017: 4697-4707.
[27] YUN C, CHOI S.Visual Localization and POMDP for Autonomous Indoor Navigation[J/OL]. [2022-11-16].https://documents.pub/document/visual-localization-and-pomdp-for-autonomous-indoor-.html.
[28] VLASSIS N, LITTMAN M L, BARBER D.On the Computational Complexity of Stochastic Controller Optimization in POMDPs. ACM Transactions on Computation Theory, 2012, 4(4). DOI: 10.1145/2382559.2382563.
[29] TUTTLE E, GHAHRAMANI Z.Propagating Uncertainty in POMDP Value Iteration with Gaussian Processes[C/OL]. [2022-11-16].https://citeseerx.ist.psu.edu/doc/10.1.1.400.6737.
[30] WASHINGTON R.BI-POMDP: Bounded, Incremental, Partially-Observable Markov-Model Planning // Proc of the European Conference on Planning. Berlin, Germany: Springer, 1997: 440-451.
[31] ROSS S, PINEAU J, CHAIB-DRAA B.Online Policy Improvement in Large POMDPs via an Error Minimization Search[C/OL]. [2022-11-16].https://www.cs.cmu.edu/~sross1/publications/Ross-NESCAI07-AEMS.pdf.
[32] YE N, SOMANI A, HSU D, et al. DESPOT: Online POMDP Planning with Regularization. Journal of Artificial Intelligence Research, 2017, 58(1): 231-266.
[33] MNIH V, KAVUKCUOGLU K, SILVER D, ,et al. Playing Atari with Deep Reinforcement Learning[C/OL]. [2022-11-16]. https://arxiv.org/pdf/1312.. Playing Atari with Deep Reinforcement Learning[C/OL]. [2022-11-16]. https://arxiv.org/pdf/1312.5602.pdf.
[34] WANG Z Y, SCHAUL T, HESSEL M, et al. Dueling Network Architectures for Deep Reinforcement Learning // Proc of the 33rd International Conference on Machine Learning. San Diego, USA: JMLR, 2016: 1995-2003.
[35] VAN HASSELT V, GUEZ A, SILVER D.Deep Reinforcement Learning with Double Q-Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 2016, 30(1): 2094-2100.
[36] HESSEL M, MODAYIL J, VAN HASSELT H, et al. Rainbow: Combining Improvements in Deep Reinforcement Learning // Proc of the 32nd AAAI Conference on Artificial Intelligence and 30th Innovative Applications of Artificial Intelligence Conference and 8th AAAI Symposium on Educational Advances in Artificial Intelligence. Palo Alto, USA: AAAI, 2018: 3215-3222.
[37] HAARNOJA T, ZHOU A, HARTIKAINEN K, et al. Soft Actor-Critic Algorithms and Applications[C/OL].[2022-11-16]. https://arxiv.org/pdf/1812.05905.pdf.
[38] LILLICRAP T P, HUNT J J, PRITZEL A, et al. Continuous Control with Deep Reinforcement Learning[C/OL].[2022-11-16]. https://arxiv.org/pdf/1509.02971.pdf.
[39] EGOROV M. Deep Reinforcement Learning with POMDPs[C/OL]. [2022-11-16]. http://cs229.stanford.edu/proj2015/363_report.pdf.
[40] HAUSKNECHT M, STONE P.Deep Recurrent Q-Learning for Partially Observable MDPs[C/OL]. [2022-11-16].https://arxiv.org/pdf/1507.06527.pdf.
[41] HOCHREITER S, SCHMIDHUBER J.Long Short-Term Memory. Neural Computation, 1997, 9(8): 1735-1780.
[42] FOERSTER J N, ASSAEL Y M, DE FREITAS N, et al. Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks[C/OL].[2022-11-16]. https://arxiv.org/pdf/1602.02672.pdf.
[43] ZHU P F, LI X, POUPART P, et al. On Improving Deep Rein-forcement Learning for POMDPs[C/OL].[2022-11-16]. https://arxiv.org/pdf/1704.07978.pdf.
[44] IGL M, ZINTGRAF L, LE T A, et al. Deep Variational Reinforcement Learning for POMDPs. Proceedings of Machine Learning Research, 2018, 80: 2117-2126.
[45] LE T A, IGL M, RAINFORTH T, et al. Auto-Encoding Sequential Monte Carlo[C/OL].[2022-11-16]. https://arxiv.org/pdf/1705.10306.pdf.
[46] WANG Y B, LIU B, WU J J, et al. DualSMC: Tunneling Diffe-rentiable Filtering and Planning under Continuous POMDPs // Proc of the 29th International Joint Conference on Artificial Intelligence. San Francisco, USA: IJCAI, 2020: 4190-4198.
[47] SINGH G, PERI S, KIM J, et al. Structured World Belief for Reinforcement Learning in POMDP. Proceedings of Machine Learning Research, 2021, 139: 9744-9755.
[48] CHEN X Y, MU Y M, LUO P, et al. Flow-Based Recurrent Belief State Learning for POMDPs. Proceedings of Machine Learning Research, 2022, 162: 3444-3468.
[49] DINH L, SOHL-DICKSTEIN J, BENGIO S.Density Estimation Using Real NVP[C/OL]. [2022-11-16].https://arxiv.org/pdf/1605.08803.pdf.
[50] TASSA Y, DORON Y, MULDAL A, et al. DeepMind Control Suite[C/OL].[2022-11-16]. https://arxiv.org/pdf/1801.00690.pdf.
[51] FERRER G, GARRELL A, SANFELIU A.Robot Companion: A Social-Force Based Approach with Human Awareness-Navigation in Crowded Environments // Proc of the IEEE/RSJ International Conference on Intelligent Robots and Systems. Washington, USA: IEEE, 2014: 1688-1694.
[52] LÖHNER R. On the Modeling of Pedestrian Motion. Applied Ma-thematical Modelling, 2010, 34(2): 366-382.
[53] HELBING D, MOLNÁR P. Social Force Model for Pedestrian Dynamics. Physical Review E, 1995, 51(5): 4282-4286.
[54] SEDIGHI S, VAN NGUYEN D, KUHNERT K D.Guided Hybrid A-Star Path Planning Algorithm for Valet Parking Applications // Proc of the 5th International Conference on Control, Automation and Robotics. Washington, USA: IEEE, 2019: 570-575.
[55] CONLTER R C.Implementation of the Pure Pursuit Path Tracking Algorithm. Technical Report, CMU-RI-TR-92-01. Pittsburgh, USA: Carnegie Mellon University, 1992.
[56] CAI P P, LUO Y F, HSU D, et al. HyP-DESPOT: A Hybrid Pa-rallel Algorithm for Online Planning Under Uncertainty[C/OL].[2022-11-16]. https://arxiv.org/pdf/1802.06215v1.pdf.
[57] BOUTON M, COSGUN A, KOCHENDERFER M J.Belief State Planning for Autonomously Navigating Urban Intersections // Proc of the IEEE Intelligent Vehicles Symposium. Washington, USA: IEEE, 2017: 825-830.
[58] LIN X, ZHANG J C, SHANG J, et al. Decision Making Through Occluded Intersections for Autonomous Driving // Proc of the IEEE Intelligent Transportation Systems Conference. Washington, USA: IEEE, 2019: 2449-2455.
[59] HUBMANN C, QUETSCHLICH N, SCHULZ J, et al. A POMDP Maneuver Planner for Occlusions in Urban Scenarios // Proc of the IEEE Intelligent Vehicles Symposium. Washington, USA: IEEE, 2019: 2172-2179.
[60] PRUEKPRASERT S, ZHANG X Y, DUBUT J, et al. Decision Making for Autonomous Vehicles at Unsignalized Intersection in Presence of Malicious Vehicles // Proc of the IEEE Intelligent Transportation Systems Conference. Washington, USA: IEEE, 2019: 2299-2304.
[61] MEGHJANI M, LUO Y F, HO Q H, et al. Context and Intention Aware Planning for Urban Driving // Proc of the IEEE/RSJ International Conference on Intelligent Robots and Systems. Washington, USA: IEEE, 2019: 2891-2898.
[62] ULBRICH S, MAURER M.Probabilistic Online POMDP Decision Making for Lane Changes in Fully Automated Driving // Proc of the 16th International IEEE Conference on Intelligent Transportation Systems. Washington, USA: IEEE, 2013: 2063-2070.
[63] MENTASTI S, MATTEUCCI M.Multi-layer Occupancy Grid Ma-pping for Autonomous Vehicles Navigation // Proc of the AEIT International Conference of Electrical and Electronic Technologies for Automotive. Washington, USA: IEEE, 2019. DOI: 10.23919/EETA.2019.8804556.
[64] KHONJI M, JASOUR A, WILLIAMS B C.Approximability of Constant-Horizon Constrained POMDP // Proc of the 28th International Joint Conference on Artificial Intelligence. San Francisco, USA: IJCAI, 2019: 5583-5590.
[65] DING W C, ZHANG L, CHEN J, et al. Safe Trajectory Generation for Complex Urban Environments Using Spatio-Temporal Se-mantic Corridor. IEEE Robotics and Automation Letters, 2019, 4(3): 2997-3004.
[66] CHEN X Y L, LI S J, MERSCH B, et al. Moving Object Segmentation in 3D LiDAR Data: A Learning-Based Approach Exploiting Sequential Data. IEEE Robotics and Automation Letters, 2021, 6(4): 6529-6536.
[67] LAGHMARA H, BOUDALI M T, LAURAIN T, et al. Obstacle Avoidance, Path Planning and Control for Autonomous Vehicles // Proc of the IEEE Intelligent Vehicles Symposium. Washington, USA: IEEE, 2019: 529-534.
[68] YANG Z C, GAO Z H, GAO F, et al. Lane Changing Assistance Strategy Based on an Improved Probabilistic Model of Dynamic Occu-pancy Grids. Frontiers of Information Technology and Electronic Engineering, 2021, 22(11): 1492-1504.
[69] ELFES A.Using Occupancy Grids for Mobile Robot Perception and Navigation. Computer, 1989, 22(6): 46-57.
[70] MERHY B A, PAYEUR P, PETRIU E M.Application of Segmented 2-D Probabilistic Occupancy Maps for Robot Sensing and Navigation. IEEE Transactions on Instrumentation and Measurement, 2008, 57(12): 2827-2837.
[71] TSARDOULIAS E G, ILIAKOPOULOU A, KARGAKOS A, et al. A Review of Global Path Planning Methods for Occupancy Grid Maps Regardless of Obstacle Density. Journal of Intelligent and Robotic Systems, 2016, 84(1/2/3/4): 829-858.
[72] YANG K, GAN S K, HUH J, et al. Optimal Spline-Based RRT Path Planning Using Probabilistic Map // Proc of the 14th International Conference on Control, Automation and Systems. Washington, USA: IEEE, 2014: 643-646.
[73] PENDLETON S D, LIU W, ANDERSEN H, et al. Numerical Approach to Reachability-Guided Sampling-Based Motion Planning Under Differential Constraints. IEEE Robotics and Automation Letters, 2017, 2(3): 1232-1239.
[74] KARAMAN S, WALTER M R, PEREZ A, et al. Anytime Motion Planning Using the RRT* // Proc of the IEEE International Conference on Robotics and Automation. Washington, USA: IEEE, 2011: 1478-1483.
[75] FULGENZI C, SPALANZANI A, LAUGIER C, et al. Risk Based Motion Planning and Navigation in Uncertain Dynamic Environment[C/OL].[2022-11-20]. https://hal.inria.fr/inria-00526601/file/PPRRT.pdf.
[76] MA H, MENG F, YE C W, et al. Bi-Risk-RRT Based Efficient Motion Planning for Autonomous Ground Vehicles. IEEE Transactions on Intelligent Vehicles, 2022, 7(3): 722-733.
[77] YANG H X, XU X M, HONG J C.Automatic Parking Path Pla-nning of Tracked Vehicle Based on Improved A* and DWA Algorithms. IEEE Transactions on Transportation Electrification, 2022. DOI: 10.1109/TTE.2022.3199255.
[78] PAN Z C, YUAN M X, WANG R H, et al. D²WA: “Dynamic” DWA for Motion Planning of Mobile Robots in Dynamic Environments. International Journal of Dynamics and Control, 2022. DOI: 10.1007/s40435-022-01092-3.
[79] KOENIG S, LIKHACHEV M, FURCY D.Lifelong Planning A*. Artificial Intelligence, 2004, 155(1/2): 93-146.
[80] STENTZ A.Optimal and Efficient Path Planning for Partially Known Environments // Proc of the IEEE International Conference on Robotics and Automation. Washington, USA: IEEE, 1994: 3310-3317.
[81] YANG L, QI J T, SONG D L, et al. Survey of Robot 3D Path Planning Algorithms. Journal of Control Science and Engineering, 2016. DOI: 10.1155/2016/7426913.
[82] KIM D, KWON Y, YOON S E.Dancing PRM*: Simultaneous Planning of Sampling and Optimization with Configuration Free Space Approximation // Proc of the IEEE International Conference on Robotics and Automation. Washington, USA: IEEE, 2018: 7071-7078.
[83] WANG Y J, LIU Z X, ZUO Z Q, et al. Trajectory Planning and Safety Assessment of Autonomous Vehicles Based on Motion Prediction and Model Predictive Control. IEEE Transactions on Vehi-cular Technology, 2019, 68(9): 8546-8556.
[84] SAROYA M, BEST G, HOLLINGER G A.Roadmap Learning for Probabilistic Occupancy Maps with Topology-Informed Growing Neural Gas. IEEE Robotics and Automation Letters, 2021, 6(3): 4805-4812.
[85] OK K, ANSARI S, GALLAGHER B, et al. Path Planning with Uncertainty: Voronoi Uncertainty Fields // Proc of the IEEE International Conference on Robotics and Automation. Washington, USA: IEEE, 2013: 4596-4601.
[86] MCLEOD S, XIAO J.Navigating Dynamically Unknown Environments Leveraging Past Experience // Proc of the International Conference on Robotics and Automation. Washington, USA: IEEE, 2019: 29-35.
[87] JIMÉNEZ V, GODOY J, ARTUÑEDO A, et al. Object-Wise Com-parison of LiDAR Occupancy Grid Scan Rendering Methods. Robotics and Autonomous Systems, 2023, 161. DOI: 10.1016/j.robot.2023.104363.
[88] SUN N, FAN Z Q, QIU Q, et al. Map Construction Fusing Environmental Information and Motion Constraints // Proc of the Chinese Intelligent Automation Conference. Berlin, Germany: Springer, 2021: 637-644.
[89] ELHAFSI A, IVANOVIC B, JANSON L, et al. Map-Predictive Motion Planning in Unknown Environments // Proc of the IEEE International Conference on Robotics and Automation. Washington, USA: IEEE, 2020: 8552-8558.
[90] BUI H D, LU Y J, PLAKU E.Improving the Efficiency of Sampling-Based Motion Planners via Runtime Predictions for Motion-Planning Problems with Dynamics // Proc of the IEEE/RSJ International Conference on Intelligent Robots and Systems. Washington, USA: IEEE, 2022: 4486-4491.
[91] JUNG Y, SEO S W, KIM S W.Fast Point Clouds Upsampling with Uncertainty Quantification for Autonomous Vehicles // Proc of the International Conference on Robotics and Automation. Washington, USA: IEEE, 2022: 7776-7782.
[92] WANG L Z, YE H K, WANG Q H, et al. Learning-Based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environments // Proc of the IEEE/RSJ International Conference on Intelligent Robots and Systems. Washington, USA: IEEE, 2021: 4509-4516.
[93] DU TOIT N E, BURDICK J W. Probabilistic Collision Checking With Chance Constraints. IEEE Transactions on Robotics, 2011, 27(4): 809-815.
[94] ZHU H, ALONSO-MORA J.Chance-Constrained Collision Avoidance for MAVs in Dynamic Environments. IEEE Robotics and Automation Letters, 2019, 4(2): 776-783.
[95] DADKHAH N, METTLER B.Survey of Motion Planning Literature in the Presence of Uncertainty: Considerations for UAV Guidance. Journal of Intelligent and Robotic Systems, 2012, 65: 233-246.
[96] AOUDE G S, LUDERS B D, JOSEPH J M, et al. Probabilistically Safe Motion Planning to Avoid Dynamic Obstacles with Uncertain Motion Patterns. Autonomous Robots, 2013, 35: 51-76.
[97] SODHI P, HO B J, KAESS M.Online and Consistent Occupancy Grid Mapping for Planning in Unknown Environments // Proc of the IEEE/RSJ International Conference on Intelligent Robots and Systems. Washington, USA: IEEE, 2019: 7879-7886.
[98] ARTUÑEDO A, VILLAGRA J, GODOY J, et al. Motion Planning Approach Considering Localization Uncertainty. IEEE Transactions on Vehicular Technology, 2020, 69(6): 5983-5994.
[99] LAU B, SPRUNK C, BURGARD W.Efficient Grid-Based Spatial Representations for Robot Navigation in Dynamic Environments. Robotics and Autonomous Systems, 2013, 61(10): 1116-1130.
[100] LÜZOW L, MENG Y, ARMIJOS A C, et al. Density Planner: Minimizing Collision Risk in Motion Planning with Dynamic Obstacles Using Density-Based Reachability[C/OL].[2022-11-16]. https://arxiv.org/pdf/2210.02131.pdf.
[101] BANFI J, WOO L, CAMPBELL M.Is It Worth to Reason About Uncertainty in Occupancy Grid Maps During Path Planning? // Proc of the International Conference on Robotics and Automation. Washington, USA: IEEE, 2022: 11102-11108.
[102] CHOHAN N, NAZARI M A, WYMEERSCH H, et al. Robust Trajectory Planning of Autonomous Vehicles at Intersections with Communication Impairments // Proc of the 57th Annual Allerton Conference on Communication, Control, and Computing. Washington, USA: IEEE, 2019: 832-839.
[103] JABR B A, AGGARWAL R, KUMAR M.Optimal Allocation of Autonomous Vehicles Using Chance-Constraints for Mapping a Semi-Structured Environment // Proc of the AIAA SCITECH Forum. Reston, USA: AIAA, 2022. DOI: 10.2514/6.2022-1413.
[104] SOUZA A, MAIA R S, AROCA R V, et al. Probabilistic Robotic Grid Mapping Based on Occupancy and Elevation Information // Proc of the 16th International Conference on Advanced Robotics. Washington, USA: IEEE, 2013. DOI: 10.1109/ICAR/2013.6766467
[105] BRAND M, MASUDA M, WEHNER N, et al. Ant Colony Optimization Algorithm for Robot Path Planning // Proc of the Inter-national Conference on Computer Design Ant Colony Optimization Algorithm for Robot Path Planning // Proc of the Inter-national Conference on Computer Design and Applications. Washing-ton, USA: IEEE, 2010: V3-436-V3-440.
[106] PUSSE F, KLUSCH M.Hybrid Online POMDP Planning and Deep Reinforcement Learning for Safer Self-Driving Cars // Proc of the IEEE Intelligent Vehicles Symposium. Washington, USA: IEEE, 2019: 1013-1020.
[107] 章宗长. 部分可观察马氏决策过程的复杂性理论及规划算法研究.博士学位论文.合肥: 中国科学技术大学, 2012.
(ZHANG Z C.Complexity Theory and Planning Algorithms in Partially Observable Markov Decision Processes. Ph.D. Dissertation. Hefei, China: University of Science and Technology of China, 2012.)
[108] 郑建阳. 无先验知识的部分可观测环境规划问题研究.硕士学位论文.厦门:厦门大学, 2019.
(ZHENG J Y.Research on Planning in Partially Observable Domains without Prior Knowledge. Master Dissertation. Xiamen, China: Xiamen University, 2019.)
[109] BARBOSA F S, LACERDA B, DUCKWORTH P, et al. Risk-Aware Motion Planning in Partially Known Environments // Proc of the 60th IEEE Conference on Decision and Control. Washington, USA: IEEE, 2021: 5220-5226.
[110] ZHITNIKOV A, INDELMAN V.Risk Aware Belief-Dependent Constrained POMDP Planning[C/OL]. [2022-11-16].https://arxiv.org/pdf/2209.02679v1.pdf.
[111] LEE K, KUM D.Collision Avoidance/Mitigation System: Motion Planning of Autonomous Vehicle via Predictive Occupancy Map. IEEE Access, 2019, 7: 52846-52857.
[112] FISHER A, CANNIZZARO R, COCHRANE M, et al. ColMap: A Memory-Efficient Occupancy Grid Mapping Framework. Robo-tics and Autonomous Systems, 2021, 142. DOI: 10.1016/j.robot.2021.103755.
[113] MARBLE J D, BEKRIS K E.Asymptotically Near-Optimal Pla-nning with Probabilistic Roadmap Spanners. IEEE Transactions on Robotics, 2013, 29(2): 432-444.
[114] 郭靖. 基于马氏决策理论的智能体决策问题研究.硕士学位论文.广州:广东工业大学, 2012.
(GUO J.Research on Agent Decision Issues Problem Based on Markov Decision Theory. Master Dissertation. Guangzhou, China: Guangdong University of Technology, 2012.)
[115] SCHEFTELOWITSCH D.The Complexity of Uncertainty in Mar-kov Decision Processes // Proc of the SIAM Conference on Control and Its Applications. Philadelphia, USA: SIAM, 2015: 303-310.
[116] DOYEN L, MASSART T, SHIRMOHAMMADI M.The Complexity of Synchronizing Markov Decision Processes. Journal of Computer and System Sciences, 2019, 100: 96-129.
[117] LEE H R, LEE T.Multi-agent Reinforcement Learning Algorithm to Solve a Partially-Observable Multi-agent Problem in Disaster Response. European Journal of Operational Research, 2021, 291(1): 296-308.
[118] THOMAS J, HERNÁNDEZ M P, PARLIKAD A K, et al. Network Maintenance Planning via Multi-agent Reinforcement Lear-ning // Proc of the IEEE International Conference on Systems, Man, and Cybernetics. Washington, USA: IEEE, 2021: 2289-2295.
[119] CUI J X, QIU H, CHEN D, et al. COOPERNAUT: End-to-End Driving with Cooperative Perception for Networked Vehicles // Proc of the IEEE/CVF Conference on Computer Vision and Pa-ttern Recognition. Washington, USA: IEEE, 2022: 17231-17241.
[120] AITTAHAR S, FRANÇOIS-LAVET V, LODEWEYCKX S, et al. Imitative Learning for Online Planning in Microgrids // Proc of the International Workshop on Data Analytics for Renewable Energy Integration. Berlin, Germany: Springer, 2015: 1-15.
[121] TIGAS P, FILOS A, MCALLISTER R, et al. Robust Imitative Planning: Planning from Demonstrations Under Uncertainty[C/OL]. [2022-11-16]. http://neurips.wad.vision/files/papers/Robust%20Imitative%20Planning:%20Planning%20from%20Demonstrations%20Under%20Uncertainty.pdf.