Pedestrian collision risk assessment is crucial for the protection of vulnerable road users (VRUs) in the Automatic Emergency Braking Pedestrians System (AEB-P). The challenge of pedestrian collision risk assessment is to accurately determine whether there is a collision risk between pedestrians and vehicles due to the uncertainty of pedestrian motion. Consequently, a collision risk assessment method based on motion prediction is proposed in this paper. Firstly, the extended Kalman filter (EKF) and Markov are used to estimate and predict the pedestrian state, respectively. According to the states, collision risk is evaluated through the collision sensitive boundary (CSB). Besides, a false alarm reduction algorithm, considering the impact of the past risk states, is proposed for reducing the false alarm rate, and it is suitable for some binary calculation methods for collision risk. Finally the Prescan and Simulink co-simulation model of the AEB-P system is established to evaluate the proposed architecture on the ETH/UCY dataset. The simulation results demonstrate that the proposed collision risk assessment method is safer and more effective than the current algorithms that do not consider motion uncertainty.
Jiménez-MejíasEMartínez-RuizVAmezcua-PrietoC, et al. Pedestrian-and driver-related factors associated with the risk of causing collisions involving pedestrians in Spain. Accid Anal Prev2016; 92: 211–218.
3.
SalamatiKSchroederBRouphailNM, et al. Simulator study of driver responses to pedestrian treatments at multilane roundabouts. Transp Res Rec2012; 2312(1): 67–75.
4.
AlonsoFEstebanCFausM, et al. Differences in the assessment of safe and risky driving behaviors: pedestrians versus drivers. Sage Open2022; 12(2): 21582440221102444.
5.
EmoAKFunkeMEMatthewsG.The effects of intersection threat and driver behaviors on pedestrian perceptions of safety. Proc Hum Factors Ergon Soc Annu Meet2011; 55(1): 1745–1749.
6.
PalacDScullyIDJonasRK, et al. Advanced Driver Assistance Systems (ADAS): who’s driving what and what’s driving use?Proc Hum Factors Ergon Soc Annu Meet2021; 65(1): 1220–1224.
7.
ZhangLYuanKChuH, et al. Pedestrian collision risk assessment based on state estimation and motion prediction. IEEE Trans Veh Technol2022; 71(1): 98–111.
8.
KalmanRE.A new approach to linear filtering and prediction problems. J Basic Eng1960; 82(1): 35–45.
9.
AmmounSNashashibiF. Real time trajectory prediction for collision risk estimation between vehicles. In: 2009 IEEE 5th international conference on intelligent computer communication and processing, Cluj-Napoca, Romania, 27–29 August 2009, pp.417–422. New York: IEEE.
10.
SchneiderNGavrilaDM.Pedestrian path prediction with recursive Bayesian filters: a comparative study. In: WeickertJHeinMSchieleB (eds) German conference on pattern recognition. Berlin, Heidelberg: Springer, 2013, pp.174–183.
11.
LiGWangWLiSE, et al. Effectiveness of flashing brake and hazard systems in avoiding rear-end crashes. Adv Mech Eng2014; 6: 792670.
12.
JiangZHuynhDQ.Multiple pedestrian tracking from monocular videos in an interacting multiple model framework. IEEE Trans Image Process2018; 27(3): 1361–1375.
13.
YilmazAJavedOShahM.Object tracking: a survey. ACM Comput Surv2006; 38(4): 13–es.
14.
KellerCGGavrilaDM.Will the pedestrian cross? A study on pedestrian path prediction. IEEE Trans Intell Transp Syst2013; 15(2): 494–506.
15.
VölzBBehrendtKMielenzH, et al. A data-driven approach for pedestrian intention estimation. In: 2016 IEEE 19th international conference on intelligent transportation systems (ITSC), Rio de Janeiro, Brazil, 1–4 November 2016, pp.2607–2612. New York: IEEE.
16.
YuanCWuXShenJ, et al. Identification of pedestrian motion feature in mixed traffic conditions and anti-collision algorithm of autonomous vehicle. Proc IMechE, Part D: J Automobile Engineering2024; 238(13): 3968–3981.
17.
FernandoTDenmanSSridharanS, et al. GD-GAN: generative adversarial networks for trajectory prediction and group detection in crowds. In: JawaharCLiHMoriG, et al. (eds) Computer vision–ACCV 2018: 14th Asian conference on computer vision, Perth, Australia, December 2–6, 2018, revised selected papers, part I 14. Cham: Springer, 2019, pp.314–330.
18.
HelbingDMolnarP.Social force model for pedestrian dynamics. Phys Rev E1995; 51(5): 4282.
19.
VemulaAMuellingKOhJ.Social attention: modeling attention in human crowds. In: 2018 IEEE international conference on robotics and automation (ICRA), Brisbane, QLD, Australia, 21–25 May 2018, pp.4601–4607. New York: IEEE.
20.
XueHHuynhDQReynoldsM.PoPPL: pedestrian trajectory prediction by LSTM with automatic route class clustering. IEEE Trans Neural Netw Learn Syst2020; 32(1): 77–90.
21.
FernandoTDenmanSSridharanS, et al. Soft+ hardwired attention: an LSTM framework for human trajectory prediction and abnormal event detection. Neural Netw2018; 108: 466–478.
22.
GreeneDLiuJReichJ, et al. An efficient computational architecture for a collision early-warning system for vehicles, pedestrians, and bicyclists. IEEE Trans Intell Transp Syst2011; 12(4): 942–953.
23.
ChenJWangKXiongZ.Collision probability prediction algorithm for cooperative overtaking based on TTC and conflict probability estimation method. Int J Veh Des2018; 77(4): 195–210.
TharanathanADeLuciaPR.Time-to-collision judgments of constant and non-constant velocities: implications for rear-end collisions. Proc Hum Factors Ergon Soc Annu Meet2006; 50(22): 2463–2467.
26.
KellerCGDangTFritzH, et al. Active pedestrian safety by automatic braking and evasive steering. IEEE Trans Intell Transp Syst2011; 12(4): 1292–1304.
27.
TamkeADangTBreuelG. A flexible method for criticality assessment in driver assistance systems. In: 2011 IEEE intelligent vehicles symposium (IV), Baden-Baden, Germany, 5–9 June 2011, pp.697–702. New York: IEEE.
28.
HillenbrandJSpiekerAMKroschelK.A multilevel collision mitigation approach—its situation assessment, decision making, and performance tradeoffs. IEEE Trans Intell Transp Syst2006; 7(4): 528–540.
29.
WinklerSWernekeJVollrathM.Timing of early warning stages in a multi stage collision warning system: drivers’ evaluation depending on situational influences. Transp Res Part F Traffic Psychol Behav2016; 36: 57–68.
30.
AliYSharmaAHaqueMM, et al. The impact of the connected environment on driving behavior and safety: a driving simulator study. Accid Anal. Prev2020; 144: 105643.
31.
TaoLWatanabeYLiY, et al. Collision risk assessment service for connected vehicles: leveraging vehicular state and motion uncertainties. IEEE Internet Things J2021; 8(14): 11548–11560.
32.
QuinteroRParraILorenzoJ, et al. Pedestrian intention recognition by means of a Hidden Markov Model and body language. In: 2017 IEEE 20th international conference on intelligent transportation systems (ITSC), Yokohama, Japan, 16–19 October 2017, pp.1–7. New York: IEEE.
33.
Quintero MínguezRParra AlonsoIFernández-LlorcaD, et al. Pedestrian path, pose, and intention prediction through Gaussian process dynamical models and pedestrian activity recognition. IEEE Trans Intell Transp Syst2019; 20(5): 1803–1814.
34.
KatrakazasCQuddusMChenWH.A new integrated collision risk assessment methodology for autonomous vehicles. Accid Anal Prev2019; 127: 61–79.
35.
AlthoffMMergelA.Comparison of Markov chain abstraction and Monte Carlo simulation for the safety assessment of autonomous cars. IEEE Trans Intell Transp Syst2011; 12(4): 1237–1247.
36.
LuBLiGYuH, et al. Adaptive potential field-based path planning for complex autonomous driving scenarios. IEEE Access2020; 8: 225294–225305.
37.
MatsumiRRaksincharoensakPNagaiM.Autonomous braking control system for pedestrian collision avoidance by using potential field. IFAC Proc Vol2013; 46(21): 328–334.
38.
MatsumiRRaksincharoensakPNagaiM.Study on autonomous intelligent drive system based on potential field with hazard anticipation. J Robot Mechatron2015; 27(1): 5–11.
39.
AbdullahZHeerwanPZakariaM, et al. Investigation of the combination of kinematic path planning and artificial potential field path planning with PI controller for autonomous emergency braking pedestrian (AEB-P) system. In: KhairuddinIMAbdullahMANasirAF, et al. (eds) Enabling Industry 4.0 through advances in mechatronics: selected articles from iM3F2021, Malaysia. Singapore: Springer, 2022, pp.285–297.
40.
LiLGanJYiZ, et al. Risk perception and the warning strategy based on safety potential field theory. Accid Anal Prev2020; 148: 105805.
41.
AyoubJWangZLiM, et al. Cause-and-effect analysis of ADAS: a comparison study between literature review and complaint data. In: Proceedings of the 14th international conference on automotive user interfaces and interactive vehicular applications, Seoul, Republic of Korea, 17–20 September 2022, pp.139–149. New York: ACM.
42.
GulinoMSVichiGCecchettoF, et al. A combined comfort and safety-based approach to assess the performance of advanced driver assistance functions. Eur Transp Res Rev2025; 17(1): 6.
43.
YangHZhangDWangD, et al. Data-driven confidence model for ADAS object detection. SAE technical paper 2020-01-0695, 2020.
44.
BaoYWangXYuR.Evaluation of false alarm alarms in truck FCW based on calibration of RSS model under different driving scenarios. Int J Transp Sci Technol2024; 15: 35–50.
45.
JiaoYCalvertSCVan LintH.Minimising missed and false alarms: a vehicle spacing based approach to conflict detection. In: 2024 IEEE intelligent vehicles symposium (IV), Jeju Island, Republic of Korea, 2–5 June 2024, pp.1982–1987. New York: IEEE.
46.
PellegriniSEssASchindlerK, et al. You’ll never walk alone: modeling social behavior for multi-target tracking. In: 2009 IEEE 12th international conference on computer vision, Kyoto, Japan, 29 September–2 October 2009, pp.261–268. New York: IEEE.
47.
RasmussenCEWilliamsCK.Gaussian processes for machine learning. Cambridge, MA: MIT Press, 2006.
48.
LiuJWangZHouY, et al. Data-driven energy management and velocity prediction for four-wheel-independent-driving electric vehicles. eTransportation2021; 9: 100119.
49.
WangPZhouMDingZ. A VRU collision warning system with Kalman-filter-based positioning accuracy improvement. In: 2021 IEEE international conference on information communication and software engineering (ICICSE), Chengdu, China, 19–21 March 2021, pp.191–198. New York: IEEE.
50.
GrewalMS.Kalman filtering. In: LovricM (ed.) International encyclopedia of statistical science. Berlin, Heidelberg: Springer Berlin Heidelberg, 2011, pp.705–708.
51.
ShinJYeonKKimS, et al. Comparative study of Markov chain with recurrent neural network for short term velocity prediction implemented on an embedded system. IEEE Access2021; 9: 24755–24767.
52.
XiaoLGaoF.A comprehensive review of the development of adaptive cruise control systems. Veh Syst Dyn2010; 48(10): 1167–1192.
53.
YangWZhangXLeiQ, et al. Research on longitudinal active collision avoidance of autonomous emergency braking pedestrian system (AEB-P). Sensors2019; 19(21): 4671.
54.
LieGZejianRPingshuG, et al. Advanced emergency braking controller design for pedestrian protection oriented automotive collision avoidance system. ScientificWorldJournal2014; 2014(1): 218246.
55.
WdowiczDPtakM.Numerical approaches to pedestrian impact simulation with human body models: a review. Arch Comput Methods Eng2023; 30(8): 4687–4709.
56.
PtakM.Method to assess and enhance vulnerable road user safety during impact loading. Appl Sci2019; 9(5): 1000.
57.
SimmsCWoodD.Pedestrian and cyclist impact: a biomechanical perspective. Vol. 166. Dordrecht: Springer Science & Business Media, 2009.
