In order to make safe and reasonable decisions in some high-risk environments such as the mandatory lane change, we propose an IMM-based partially observable Markov decision process (POMDP) decision algorithm using the collision-risk function which combines the time-to-collision (TTC), the intervehicular time (IT), and the collision function for mandatory lane change. The newly proposed collision-risk function contains two parts: the vehicle impact factor and the collision function, which is used to assess the risk and determines whether the autonomous vehicle collides with surrounding vehicles. The IMM-base POMDP is used for decision-making and we apply the Monte Carlo Tree Search (MCTS) to solve the problem. In the decision-making process, the belief state is obtained by the Interacting Multiple Model (IMM) algorithm. With the collision-risk function and the probability distribution of the states of surrounding vehicles in the future, the proposed POMDP decision algorithm can determine whether the autonomous vehicle accelerates lane changing or decelerates lane changing, and obtain the acceleration corresponding to each path point. Finally, in order to verify the effectiveness of the algorithm, we perform a driver-in-the-loop simulation through Prescan. We use aggressive driver and conservative driver to control the rear vehicle of the target lane, respectively. Simulation results show that the proposed algorithm can accurately predict the accelerations of surrounding vehicles and make safe and reasonable decisions under two scenarios, which is superior to the general POMDP.
ShojaeiSRahmani HanzakiAAzadiS, et al. A novel decision-making unit for automated maneuver of articulated vehicles in real traffic situations. Proc IMechE, Part D: J Automobile Engineering2020; 234(1): 152–171.
2.
KimIHBongJHParkJ, et al. Prediction of driver’s intention of lane change by augmenting sensor information using machine learning techniques. Sensors (Switzerland)2017; 17(6): 1–18.
3.
YouCLuJFilevD, et al. Highway traffic modeling and decision making for autonomous vehicle using reinforcement learning. IEEE Intell Veh Symp Proc2018; 2018: 1227–1232.
4.
ZhengRLiuCGuoQ. A decision-making method for autonomous vehicles based on simulation and reinforcement learning. Proc Int Conf Mach Learn Cybern2013; 1: 362–369.
5.
YaoWZhaoHBonnifaitP, et al. Lane change trajectory prediction by using recorded human driving data. IEEE Intell Veh Symp Proc2013; 2013: 430–436.
6.
HouYEdaraPSunC. Modeling mandatory lane changing using bayes classifier and decision trees. IEEE Trans Intell Transp Syst2014; 15(2): 647–655.
7.
LinYMcPheeJAzadNL. Anti-jerk on-ramp merging using deep reinforcement learning. IEEE Intell Veh Symp Proc2020; 2020: 7–14.
8.
XuCZhaoWWangC. An integrated threat assessment algorithm for decision-making of autonomous driving vehicles. IEEE Trans Intell Transp Syst2020; 21(6): 2510–2521.
9.
WangHYuanSGuoM, et al. A deep reinforcement learning-based approach for autonomous driving in highway on-ramp merge. Proc IMechE, Part D: J Automobile Engineering2021; 235 (10-11): 2726-2739.
10.
WengJXueSYanX. Modeling vehicle merging behavior in work zone merging areas during the merging implementation period. IEEE Trans Intell Transp Syst2016; 17(4): 917–925.
11.
KitaH. A merging-giveway interaction model of cars in a merging section: a game theoretic analysis. Transp Res Part A Policy Pract1999; 33(3–4): 305–312.
12.
MengFSuJLiuC, et al. Dynamic decision making in lane change: game theory with receding horizon. In: 2016 UKACC international conference on control (CONTROL), Belfast, UK, 31 August–2 September 2016, pp.1–6. New York: IEEE.
13.
HouYEdaraPSunC. A genetic fuzzy system for modeling mandatory lane changing. IEEE Conf Intell Transp Syst Proc ITSC2012; 2012: 1044–1048.
14.
SongR. Driver intention prediction using model-added Bayesian network. Proc IMechE, Part D: J Automobile Engineering2020; 235(5): 1236–1244.
15.
SchulzJHubmannCLochnerJ, et al. Interaction-aware probabilistic behavior prediction in urban environments. IEEE Int Conf Intell Robot Syst2018; 2018: 3999–4006.
16.
JeongYKimSYiK. Surround vehicle motion prediction using LSTM-RNN for motion planning of autonomous vehicles at multi-lane turn intersections. IEEE Open J Intell Transp Syst2020; 1: 2–14.
17.
LaugierCParomtchikIEPerrollazM, et al. Probabilistic analysis of dynamic scenes and collision risks assessment to improve driving safety. IEEE Intell Transp Syst Mag2011; 3(4): 4–19.
18.
ZhaoDGaoYZhangZ, et al. Prediction of vehicle motion based on Markov model. In: 2017 International conference on computer systems, electronics and control (ICCSEC), Dalian, China, 25–27 December 2017, pp.205–209. New York: IEEE.
19.
HouLXinLLiSE, et al. Interactive trajectory prediction of surrounding road users for autonomous driving using structural-LSTM network. IEEE Trans Intell Transp Syst2019; 2019: 1–11.
20.
FossenSFossenTI. Extended kalman filter design and motion prediction of ships using live automatic identification system (AIS) Data. In: Proceedings 2018 2nd European conference on electrical engineering and computer science (EECS), Bern, Switzerland, 20–22 December 2018, pp.464–470. New York: IEEE.
21.
PengXDongHZhangB. Echo State Network ship motion modeling prediction based on Kalman filter. In: 2017 IEEE international conference on mechatronics and automation (ICMA), Takamatsu, Japan, 6–9 August 2017, pp.95–100. New York: IEEE.
22.
ChoCHChongSYSongTL. IMM filtering for vehicle tracking in cluttered environments with glint noise. In: 2017 International cnference on control, automation and information sciences (ICCAIS), Chiang Mai, Thailand, 31October–1November2017, pp.98–105. New York: IEEE.
23.
LiuMHeYLiJ, et al. IMM filter based local graph matching for plant cell lineage estimation. In: Proceedings of international conference on image processing (ICIP), Beijing, China, 17–20 September 2018, pp.2030–2034. New York: IEEE.
24.
SeahCEHwangI. State estimation for stochastic linear hybrid systems with continuous-state-dependent transitions: an IMM approach. IEEE Trans Aerosp Electron Syst2009; 45(1): 376–392.
25.
KimJKumD. Collision risk assessment algorithm via lane-based probabilistic motion prediction of surrounding vehicles. IEEE Trans Intell Transp Syst2018; 19(9): 2965–2976.
26.
HuangHWangJFeiC, et al. A probabilistic risk assessment framework considering lane-changing behavior interaction. Sci China Inf Sci2020; 63(9): 94–108.
HillenbrandJSpiekerAMKroschelK. A multilevel collision mitigation approach – its situation assessment, decision making, and performance tradeoffs. IEEE Trans Intell Transp Syst2006; 7(4): 528–540.
29.
NohSAnK. Decision-making framework for automated driving in highway environments. IEEE Trans Intell Transp Syst2018; 19(1): 58–71.
30.
KimJHKumDS. Threat prediction algorithm based on local path candidates and surrounding vehicle trajectory predictions for automated driving vehicles. IEEE Intell Veh Symp Proc2015; 2015: 1220–1225.
31.
FalconePAliMSjöbergJ. Predictive threat assessment via reachability analysis and set invariance theory. IEEE Trans Intell Transp Syst2011; 12(4): 1352–1361.
32.
KimKWKimHSChoiYK. Optimization of cubic polynomial joint trajectories and sliding mode controllers for robots using evolution strategy. In: Proceedings of the IECON’97 23rd international conference on industrial electronics, control, and instrumentation, New Orleans, LA, USA, 14 November 1997, vol. 3, pp.1444–1447. New York: IEEE.
33.
KimBYiKYooHJ, et al. An IMM/EKF approach for enhanced multitarget state estimation for application to integrated risk management system. IEEE Trans Veh Technol2015; 64(3): 876–889.
34.
SilverDVenessJ. Monte-Carlo planning in large POMDPs. In: Advances in Neural Information Process Systems 23, 24th Annual Conference on Neural Information Process Systems 2010 NIPS2010, Vancouver, British Columbia, Canada, 6–9 December 2010, pp. 2164–2172. Tallinn: Curran Associates, Inc.
35.
LuYBiL. Human behavior model-based predictive control of longitudinal brain-controlled driving. IEEE Trans Intell Transp Syst2021; 22(3): 1361–1374.
