Modelling method for pedestrian safety behavior in shared road spaces of pedestrian-traditional vehicle-autonomous vehicle
-
摘要:
在未来自动驾驶汽车将与传统交通参与者共享道路资源的发展背景下,对人-车-智共享道路空间中的行人安全行为建模,对于自动驾驶汽车的仿真开发和可靠性、安全性测试等工作至关重要。针对该需求,分析行人的安全运动行为,在此基础上改进传统的行人社会力模型,提出共享道路空间中行人与周围其他行人、传统车辆和自动驾驶汽车交互运动的动量模型;采用人-车交互运动的数据集和遗传算法对模型的安全参数进行标定,并搭建典型的共享道路空间场景以验证模型的有效性。仿真结果表明:所提模型能够模拟出行人真实的安全运动行为,用于人-车-智共享道路空间仿真等任务中的模拟效果更佳。
Abstract:Under the development background that autonomous vehicles will share road resources with traditional traffic participants in the future, pedestrian safety behavior modelling in the shared road spaces of pedestrian-traditional vehicle-autonomous vehicle is crucial to the simulation development and reliability and safety testing of autonomous vehicles. To satisfy this demand, the safe movement behavior of pedestrians was analyzed firstly, and the traditional social force model of pedestrians was improved to build a momentum model of the interaction between pedestrians and other pedestrians, traditional vehicles, and autonomous vehicles in the shared road spaces. Then, a dataset of pedestrian-vehicle interaction motion and a genetic algorithm were adopted to calibrate the safety parameters of the model, and a typical shared road space scene was proposed to verify the effectiveness of the model. The simulation results indicate that the proposed model can simulate the safe movement behavior of pedestrians, and it has better effects in tasks such as shared road space simulation of pedestrian-traditional vehicle-autonomous vehicle.
-
Key words:
- shared road space /
- pedestrian /
- autonomous vehicle /
- safety /
- momentum
-
表 1 影响因子在不同情况下的取值范围
Table 1. Range of impact factor in different situations
${D_1}$取值范围 汽车外部标志 汽车驾驶模式 ${D_1} \leqslant 0$ 外部有显示决策行为的
实时标志有驾驶员且驾驶员与
行人有眼神交流${D_1} > 0$ 外部无显示决策行为的
实时标志无驾驶员或有驾驶员
但注意力不在周围路况${D_2}$取值范围 行人信任程度 行人心理特征 ${D_2} \leqslant 0$ 对自动驾驶汽车了解少,
持怀疑态度保守型性格 ${D_2} > 0$ 对自动驾驶汽车了解多,
相信避撞技术冲动型性格 ${D_3}$取值范围 行人犹豫时间 ${D_3} \leqslant 0$ 行动能力强,犹豫时间短,能及时改变行为 ${D_3} > 0$ 行动能力弱,犹豫时间长,不能及时改变行为 表 2 不同影响系数模拟生成的不同距离
Table 2. Different distances simulated under different impact factors
${D_{\eta}}$取值 距离平均值/m 距离最小值/m 0.5 11.2817 1.2729 1 11.2956 1.3355 2 11.3447 1.3618 表 3 不同模型模拟生成的不同距离
Table 3. Different distances simulated under different models
模型类型 距离平均值/m 距离最小值/m 动量模型 11.2956 1.3355 社会力模型 12.0049 1.2291 -
[1] CHENG H, JOHORA F T, SESTER M, et al. Trajectory modelling in shared spaces: expert-based vs. deep learning approach? [M]// Multi-Agent-Based Simulation XXI. Berlin: Springer, 2021: 13-27. [2] ALAHI A, GOEL K, RAMANATHAN V, et al. Social LSTM: human trajectory prediction in crowded spaces[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2016: 961-971. [3] CHENG H, SESTER M. Modeling mixed traffic in shared space using LSTM with probability density mapping[C]//Proceedings of the 21st International Conference on Intelligent Transportation Systems. Piscataway: IEEE Press, 2018: 3898-3904. [4] PANG S M, CAO J X, JIAN M Y, et al. BR-GAN: a pedestrian trajectory prediction model combined with behavior recognition[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(12): 24609-24620. doi: 10.1109/TITS.2022.3193442 [5] HUANG L, ZHUANG J H, CHENG X M, et al. STI-GAN: multimodal pedestrian trajectory prediction using spatiotemporal interactions and a generative adversarial network[J]. IEEE Access, 2021, 9: 50846-50856. doi: 10.1109/ACCESS.2021.3069134 [6] FELICIANI C, CROCIANI L, GORRINI A, et al. A simulation model for non-signalized pedestrian crosswalks based on evidence from on field observation[J]. Intelligenza Artificiale: the International Journal of the AIxIA, 2017, 11(2): 117-138. doi: 10.3233/IA-170110 [7] WU W J, CHEN R C, JIA H F, et al. Game theory modeling for vehicle-pedestrian interactions and simulation based on cellular automata[J]. International Journal of Modern Physics C, 2019, 30(4): 1950025. doi: 10.1142/S0129183119500256 [8] MA Y X, MANOCHA D, WANG W P. AutoRVO: local navigation with dynamic constraints in dense heterogeneous traffic[EB/OL]. (2018-11-14)[2023-06-15]. https://arxiv.org/abs/1804.02915v2. [9] CHARLTON J, GONZALEZ L R M, MADDOCK S, et al. Simulating crowds and autonomous vehicles[M]// Transactions on Computational Science XXXVII. Berlin: Springer, 2020: 129-143. [10] ANVARI B, BELL M G H, SIVAKUMAR A, et al. Modelling shared space users via rule-based social force model[J]. Transportation Research Part C: Emerging Technologies, 2015, 51: 83-103. doi: 10.1016/j.trc.2014.10.012 [11] CHAO Q W, DENG Z G, JIN X G. Vehicle–pedestrian interaction for mixed traffic simulation[J]. Computer Animation and Virtual Worlds, 2015, 26(3-4): 405-412. doi: 10.1002/cav.1654 [12] RINKE N, SCHIERMEYER C, PASCUCCI F, et al. A multi-layer social force approach to model interactions in shared spaces using collision prediction[J]. Transportation Research Procedia, 2017, 25: 1249-1267. doi: 10.1016/j.trpro.2017.05.144 [13] JOHORA F T, MÜLLER J P. Modeling interactions of multimodal road users in shared spaces[C]//Proceedings of the 21st International Conference on Intelligent Transportation Systems. Piscataway: IEEE Press, 2018: 3568-3574. [14] SCHÖNAUER R, STUBENSCHROTT M, SCHROM-FEIERTAG H, et al. Social and spatial behaviour in shared spaces[C]//Proceedings of the 17th International Conference on Urban Planning and Regional Development in the Information Society GeoMultimedia. Piscataway: IEEE Press, 2012: 759-767. [15] HELBING D, MOLNÁR P. Social force model for pedestrian dynamics[J]. Physical Review E, 1995, 51(5): 4282-4286. doi: 10.1103/PhysRevE.51.4282 [16] YANG D F, LI L H, REDMILL K, et al. Top-view trajectories: a pedestrian dataset of vehicle-crowd interaction from controlled experiments and crowded campus[C]//Proceedings of the IEEE Intelligent Vehicles Symposium. Piscataway: IEEE Press, 2019: 899-904. [17] YANG D F, ÖZGÜNER Ü, REDMILL K. A social force based pedestrian motion model considering multi-pedestrian interaction with a vehicle[J]. ACM Transactions on Spatial Algorithms and Systems, 2020, 6(2): 1-27. -