Abstract: lane changing assistance in autonomous vehicles is a popular research topic. Scene modeling of the driving area is a prerequisite for lane changing decision problems. A road environment representation method based on a dynamic occupancy grid is proposed in this study. The model encapsulates the data such as vehicle speed, obstacles, lane lines, and traffic rules into a form of spatial drivability probability. This information is compiled into a hash table, and the grid map is mapped into a hash map by means of hash function. A vehicle behavior decision cost equation is established with the model to help drivers make accurate vehicle lane changing decisions based on the principle of least cost, while considering influencing factors such as vehicle drivability, safety, and power. The feasibility of the lane changing assistance strategy is verified through vehicle tests, and the results show that the lane changing assistance system based on a probabilistic model of dynamic occupancy grids can provide lane changing assistance to drivers taking into consideration the dynamics and safety.

基于动态占用网格改进概率模型的换道辅助策略

[1]Coue C, Fraichard T, Bessiere P, et al., 2003. Using Bayesian programming for multi-sensor multi-target tracking in automotive applications. IEEE Int Conf on Robotics and Automation, p.2104-2109.

[2]Danescu R, Oniga F, Nedevschi S, 2011. Modeling and tracking the driving environment with a particle-based occupancy grid. IEEE Trans Intell Transp Syst, 12(4):1331-1342.

[3]Elfes A, 1989. Using occupancy grids for mobile robot perception and navigation. Computer, 22(6):46-57.

[4]Gao J, Murphey YL, Zhu HH, 2019. Personalized detection of lane changing behavior using multisensor data fusion. Computing, 101(4):1837-1860.

[5]Hui F, Mu KN, Zhao XM, 2018. Assistant driving decision method of vehicle lane change based on dynamic probability grid and Bayesian decision network. J Traff Transp Eng, 18(2):148-158.

[6]Kim DJ, Lee SH, Chung CC, 2019. Object vehicle motion prediction based on dynamic occupancy grid map utilizing cascaded support vector machine. Proc 19^th Int Conf on Control, Automation and Systems, p.496-500.

[7]Kumar P, Perrollaz M, Lefèvre S, et al., 2013. Learning-based approach for online lane change intention prediction. IEEE Intelligent Vehicles Symp, p.797-802.

[8]Moravec HP, 1988. Sensor fusion in certainty grids for mobile robots. AI Mag, 9(2):61-74.

[9]Nadarajan P, Botsch M, 2016. Probability estimation for predicted-occupancy grids in vehicle safety applications based on machine learning. IEEE Intelligent Vehicles Symp, p.1285-1292.

[10]National Highway Traffic Safety Administration, 2021. Traffic Safety Facts 2019: A Compilation of Motor Vehicle Crash Data (Report No. DOT HS 813 141).

[11]Nègre A, Rummelhard L, Laugier C, 2014. Hybrid sampling Bayesian occupancy filter. IEEE Intelligent Vehicles Symp Proceeding, p.1307-1312.

[12]Oh SI, Kang HB, 2016. Fast occupancy grid filtering using grid cell clusters from LIDAR and stereo vision sensor data. IEEE Sens J, 16(19):7258-7266.

[13]Richter E, Lindner P, Wanielik G, et al., 2009. Advanced occupancy grid techniques for lidar based object detection and tracking. Proc 12^th Int IEEE Conf on Intelligent Transportation Systems, p.1-5.

[14]Robbiano C, Chong EKP, Azimi-Sadjadi MR, et al., 2020. Bayesian learning of occupancy grids. IEEE Trans Intell Transp Syst, early access.

[15]Sivaraman S, Trivedi MM, 2014. Dynamic probabilistic drivability maps for lane change and merge driver assistance. IEEE Trans Intell Transp Syst, 2014(5):2063-2073.

[16]Schreier M, Willert V, Adamy J, 2016. Compact representation of dynamic driving environments for ADAS by parametric free space and dynamic object maps. IEEE Trans Intell Transp Syst, 17(2):367-384.

[17]Schubert R, Schulze K, Wanielik G, 2010. Situation assessment for automatic lane-change maneuvers. IEEE Trans Intell Transp Syst, 11(3):607-616.

[18]Sencan O, Temeltas H, 2018. A quantized approach for occupancy grids for autonomous vehicles: Q-Trees. Adv Rob, 32(11):575-589.

[19]Smirnov N, Liu YZ, Validi A, et al., 2021. A game theory-based approach for modeling autonomous vehicle behavior in congested, urban lane-changing scenarios. Sensors, 21(4):1523.

[20]Wang JJ, Zhang QC, Zhao DB, et al., 2019. Lane change decision-making through deep reinforcement learning with rule-based constraints. Int Joint Conf on Neural Networks, p.1-6.

[21]Yatim NA, Buniyamin N, Noh ZM, et al., 2020. Occupancy grid map algorithm with neural network using array of infrared sensors. J Phys, 1502:012053.