Car-following and cut-in maneuvers are among the most frequent causes of road traffic accidents in mixed traffic environments involving human-driven and autonomous vehicles, often resulting in significant casualties. Autonomous driving technology has significant potential to reduce these traffic accidents. This paper proposes a risk assessment method that comprehensively considers autonomous vehicle (AV) driving style preference and surrounding disturbance vehicles (DVs) driving style. In addition, as a precursor to risk assessment, we have improved lane-changing intention recognition by integrating both frequency-domain and time-domain feature analysis. We design an Adaptive Threshold Wavelet Attention (ATWA) block integrated into a Transformer-based classifier. This block employs multi-level wavelet decomposition to extract frequency-domain features from vehicle trajectories, utilizing adaptive thresholds to suppress noise in low/high-frequency components while amplifying critical signals. Experimental results demonstrate that our model achieves encouraging accuracy on the NGSIM and HighD datasets, with an average inference time of 0.0043 s under 32 TOPS computational constraints, meeting real-time computing requirements. For risk assessment, we propose a driving style-aware decision-making strategy based on Conditional Random Fields (CRF). This method enhances interactive risks between the AV and the DV using a potential risk coefficient for the DV, dynamically adjusting braking responses according to the driving styles of the AV. PanoSim simulations validate that our method effectively prevents collisions in multi-scenarios while balancing safety and traffic efficiency. This work provides a comprehensive solution for autonomous systems, integrating high-precision intention recognition with personalized risk-responsive behaviors, thereby enhancing both safety and drivers’ acceptance in complex traffic environments.
World Health Organization. Global status report on road safety 2018. Technical report, World Health Organization, 2019.
2.
National Highway Traffic Safety Administration. Traffic safety facts: a compilation of motor vehicle crash data. Technical report, National Highway Traffic Safety Administration, 2020.
3.
KhattakZHSmithBLParkH, et al. Cooperative lane control application for fully connected and automated vehicles at multilane freeways. Transp Res Part C: Emerg Technol2020; 111: 294–317.
4.
ZhouRZhangGHuangH, et al. How would autonomous vehicles behave in real-world crash scenarios?Accid Anal Prev2024; 202: 107572.
5.
ShiQZhangH. An improved learning-based LSTM approach for lane change intention prediction subject to imbalanced data. Transp Res Part C: Emerg Technol2021; 133: 103414.
6.
ScheelOSchwarzLNavabN, et al. Situation assessment for planning lane changes: combining recurrent models and prediction. In: 2018 IEEE international conference on robotics and automation (ICRA), 2018, pp.2082–2088. IEEE.
7.
JiangTLiuYDongQ, et al. Intention-aware interactive transformer for real-time vehicle trajectory prediction in dense traffic. Transp Res Rec2023; 2677(3): 946–960.
8.
LiYJiangYWuX. TrajPT: a trajectory data-based pre-trained transformer model for learning multi-vehicle interactions. Transp Res Part C: Emerg Technol2025; 171: 105013.
9.
KimJHKumDS. Threat prediction algorithm based on local path candidates and surrounding vehicle trajectory predictions for automated driving vehicles. In: 2015 IEEE intelligent vehicles symposium (IV), 2015, pp.1220–1225. IEEE.
10.
HuangYZhaoWXuC, et al. An IMM-based POMDP decision algorithm using collision-risk function in mandatory lane change. Proc Inst Mech Eng Part D: J Automobile Eng2022; 236(7): 1500–1514.
11.
GlaserSVanholmeBMammarS, et al. Maneuver-based trajectory planning for highly autonomous vehicles on real road with traffic and driver interaction. IEEE Trans Intell Transp Syst2010; 11(3): 589–606.
12.
CooperDFFergusonN. Traffic studies at T-Junctions. 2. A conflict simulation Record. Traffic Eng Control1976; 17(7): 306–309.
13.
NohS. Decision-making framework for autonomous driving at road intersections: safeguarding against collision, overly conservative behavior, and violation vehicles. IEEE Trans Ind Electron2019; 66(4): 3275–3286.
14.
XuDLyuNYangL. A proactive risk prediction framework for cut-in maneuvers incorporating inherent driving styles. IEEE Trans Intell Transp Syst2025; 26: 23084–23099.
15.
HeXHaoJChenX, et al. Robust multiobjective reinforcement learning considering environmental uncertainties. IEEE Trans Neural Netw Learn Syst2025; 36(4): 6368–6382.
16.
RhifMBen AbbesAFarahIR, et al. Wavelet transform application for/in non-stationary time-series analysis: a review. Appl Sci2019; 9(7): 1345.
17.
FangHTHuangDS. Noise reduction in lidar signal based on discrete wavelet transform. Opt Commun2004; 233(1-3): 67–76.
18.
WangCGaoRX. Wavelet transform with spectral post-processing for enhanced feature extraction. In: IMTC/2002. Proceedings of the 19th IEEE instrumentation and measurement technology conference, 2002, Vol. 1, pp. 315–320. IEEE.
19.
ShoughiADowlatshahiMBAmiriA, et al. Automatic ECG classification using discrete wavelet transform and one-dimensional convolutional neural network. Computing2024; 106(4): 1227–1248.
20.
ChenGDaiKYangK, et al. Bracketing image restoration and enhancement with high-low frequency decomposition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition; 2024; p. 6097–6107.
21.
XueQXingYLuJ. An integrated lane change prediction model incorporating traffic context based on trajectory data. Transp Res Part C: Emerg Technol2022; 141: 103738.
22.
WangWZhangYYangC, et al. A human–machine shared dual fuzzy authority allocation control strategy for automatic driving vehicle considering driver intention judgement. Expert Syst Appl2025; 274: 126971.
23.
DouYYanFFengD. Lane changing prediction at highway lane drops using support vector machine and artificial neural network classifiers. In: 2016 IEEE international conference on advanced intelligent mechatronics (AIM), 2016, pp.901–906. IEEE.
24.
SchlechtriemenJWedelAHillenbrandJ, et al. A lane change detection approach using feature ranking with maximized predictive power. In: 2014 IEEE intelligent vehicles symposium proceedings, 2014, pp.108–114. IEEE.
25.
LyuNWenJDuanZ, et al. Vehicle trajectory prediction and cut-in collision warning model in a connected vehicle environment. IEEE Trans Intell Transp Syst2022; 23(2): 966–981.
26.
Van HoudtGMosqueraCNápolesG. A review on the long short-term memory model. Artif Intell Rev2020; 53(8): 5929–5955.
27.
XingYLvCWangH, et al. An ensemble deep learning approach for driver lane change intention inference. Transp Res Part C: Emerg Technol2020; 115: 102615.
28.
CaiJJiangHWangJ. Implementation of the human-like lane changing driver model based on Bi-LSTM. Discrete Dyn Nat Soc2022; 2022(1): 9934292.
29.
MaXTaoZWangY, et al. Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transp Res Part C: Emerg Technol2015; 54: 187–197.
30.
YuanRAbdel-AtyMGuX, et al. A unified modeling framework for lane change intention recognition and vehicle status prediction. Physica A2023; 632: 129332.
31.
GopaliSAbriFSiami-NaminiS, et al. A comparison of TCN and LSTM models in detecting anomalies in time series data. In: 2021 IEEE international conference on big data (Big Data), 2021, pp.2415–2420. IEEE.
32.
LiFJZhangCYChenCLP. Sts-dgnn: vehicle trajectory prediction via dynamic graph neural network with spatial–temporal synchronization. IEEE Trans Instrum Meas2023; 72: 1–13.
33.
YeLWangZChenX, et al. Gsan: graph self-attention network for learning spatial–temporal interaction representation in autonomous driving. IEEE Internet Things J2022; 9(12): 9190–9204.
34.
VaswaniAShazeerNParmarN, et al. Attention is all you need. In: Advances in Neural Information Processing Systems2017, Vol. 30.
35.
GaoKLiXChenB, et al. Dual transformer based prediction for lane change intentions and trajectories in mixed traffic environment. IEEE Trans Intell Transp Syst2023; 24(6): 6203–6216.
36.
HuangTFuRSunQ, et al. Driver lane change intention prediction based on topological graph constructed by driver behaviors and traffic context for human-machine co-driving system. Transp Res Part C: Emerg Technol2024; 160: 104497.
37.
WenQZhouTZhangC, et al. Transformers in time series: a survey. arXiv preprint arXiv:220207125, 2022.
SheikhMSPengY. Improved collision risk assessment for autonomous vehicles at on-ramp merging areas. IEEE Access2023; 11: 130974–130989.
40.
ZhangLXiaoWZhangZ, et al. Surrounding vehicles motion prediction for risk assessment and motion planning of autonomous vehicle in highway scenarios. IEEE Access2020; 8: 209356–209376.
41.
LiGYangYZhangT, et al. Risk assessment based collision avoidance decision-making for autonomous vehicles in multi-scenarios. Transp Res Part C: Emerg Technol2021; 122: 102820.
42.
ZhengLSayedT. Comparison of traffic conflict indicators for crash estimation using peak over threshold approach. Transp Res Rec2019; 2673(5): 493–502.
43.
LyuNXieTWenJ, et al. A real-time conflict risk prediction modeling based on causal inference and graph-model: applied to multi-configuration expressway diversion zones. Transp Res Part C: Emerg Technol2025; 178: 105219.
44.
OppenheimAV. Discrete-time signal processing. Pearson Education India, 1999.
45.
MaXCZhouYHLuJ, et al. Assessing the impact of car-following driving style on traffic conflict risk using asymmetric behavior model and explainable machine learning. Accid Anal Prev2025; 211: 107904.
46.
LiGLiSEChengB, et al. Estimation of driving style in naturalistic highway traffic using maneuver transition probabilities. Transp Res Part C: Emerg Technol2017; 74: 113–125.
47.
FuCSayedT. Comparison of threshold determination methods for the deceleration rate to avoid a crash (DRAC)-based crash estimation. Accid Anal Prev2021; 153: 106051.
48.
HancockMWWrightB. A policy on geometric design of highways and streets. Vol. 3. American Association of State Highway and Transportation Officials, 2013, pp.20.
49.
LiKWangXXuY, et al. Lane changing intention recognition based on speech recognition models. Transp Res Part C: Emerg Technol2016; 69: 497–514.
50.
AdavikottuAVelagaNR. Modeling the impact of driving aggression on lane change performance measures: steering compensatory behavior, lane change execution duration and crash probability. Transp Res Part F: Traffic Psychol Behav2024; 103: 526–553.
51.
KusanoKDGablerHC. Safety benefits of forward collision warning, brake assist, and autonomous braking systems in rear-end collisions. IEEE Trans Intell Transp Syst2012; 13(4): 1546–1555.
52.
HeXHuangWLvC. Trustworthy autonomous driving via defense-aware robust reinforcement learning against worst-case observational perturbations. Transp Res Part C: Emerg Technol2024; 163: 104632.
53.
WangKYangYWangS, et al. Research on car-following model considering driving style. Math Probl Eng2022; 2022: 1–9.
54.
XieDFFangZZJiaB, et al. A data-driven lane-changing model based on deep learning. Transp Res Part C: Emerg Technol2019; 106: 41–60.
55.
LiuHWangTLiW, et al. Lane-change intention recognition considering oncoming traffic: novel insights revealed by advances in deep learning. Accid Anal Prev2024; 198: 107476.
56.
LiYLiuFXingL, et al. A deep learning framework to explore influences of data noises on lane-changing intention prediction. IEEE Trans Intell Transp Syst2024; 25(7): 6514–6526.
57.
XuTZhangZWuX, et al. Recognition of lane-changing behaviour with machine learning methods at freeway off-ramps. Physica A2021; 567: 125691.
58.
DoroudgarSChuangHMPerryPJ, et al. Driving performance comparing older versus younger drivers. Traffic Inj Prev2017; 18(1): 41–46.
59.
ChanFKFuACYuC. Haar wavelets for efficient similarity search of time-series: with and without time warping. IEEE Trans Knowl Data Eng2003; 15(3): 686–705.
60.
ZhangLDuZZhaoS, et al. Development and verification of traffic confrontation simulation test platform based on PanoSim. In: 2020 IEEE 4th information technology,networking, electronic and automation control conference (ITNEC), 2020, Vol. 1, pp.1814–1818. IEEE.
61.
ZhangTTJinPJMcQuadeST, et al. Car-following models: a multidisciplinary review. IEEE Trans Intell Vehicles2025; 10: 92–116.
62.
ZhuXHuWDengZ, et al. Interaction-aware cut-in trajectory prediction and risk assessment in mixed traffic. IEEE/CAA J Autom Sin2022; 9(10): 1752–1762.
63.
WangXYangMHurwitzD. Analysis of cut-in behavior based on naturalistic driving data. Accid Anal Prev2019; 124: 127–137.
64.
HeXWuJHuangZ, et al. Fear-neuro-inspired reinforcement learning for safe autonomous driving. IEEE Trans Pattern Anal Mach Intell2024; 46(1): 267–279.
65.
CandelaEDoustalyOParadaL, et al. Risk-aware controller for autonomous vehicles using model-based collision prediction and reinforcement learning. Artif Intell2023; 320: 103923.
66.
GippsPG. A model for the structure of lane-changing decisions. Transp Res Part B: Methodol1986; 20(5): 403–414.
67.
IzquierdoRQuintanarAParraI, et al. Experimental validation of lane-change intention prediction methodologies based on CNN and LSTM. In: 2019 IEEE intelligent transportation systems conference (ITSC), 2019, pp.3657–3662. IEEE.
68.
LuYMaHSmartE, et al. Real-time performance-focused localization techniques for autonomous vehicle: a review. IEEE Trans Intell Transp Syst2022; 23(7): 6082–6100.
69.
ChakrabortySTomsettRRaghavendraR, et al. Interpretability of deep learning models: A survey of results. In: 2017 IEEE smartworld, ubiquitous intelligence & computing, advanced & trusted computed, scalable computing & communications, cloud & big data computing, Internet of people and smart city innovation, 2017, pp.1–6. IEEE.
70.
MozaffariSAl-JarrahOYDianatiM, et al. Deep learning-based vehicle behavior prediction for autonomous driving applications: a review. IEEE Trans Intell Transp Syst2022; 23(1): 33–47.
71.
ChenJZhouYLiangH. Effects of ACC and CACC vehicles on traffic flow based on an improved variable time headway spacing strategy. IET Intell Transp Syst2019; 13(9): 1365–1373.
72.
MaYLiWTangK, et al. Driving style recognition and comparisons among driving tasks based on driver behavior in the online car-hailing industry. Accid Anal Prev2021; 154: 106096.
73.
DengMGuoY. A study of safety acceptance and behavioral interventions for autonomous driving technologies. Sci Rep2022; 12(1): 17891.
74.
JingPXuGChenY, et al. The determinants behind the acceptance of autonomous vehicles: a systematic review. Sustainability2020; 12(5): 1719.
75.
RosiqueFNavarroPJFernándezC, et al. A systematic review of perception system and simulators for autonomous vehicles research. Sensors2019; 19(3): 648.
76.
VargasJAlsweissSTokerO, et al. An overview of autonomous vehicles sensors and their vulnerability to weather conditions. Sensors2021; 21(16): 5397.
77.
LinJYangPZhangN, et al. Low-latency edge video analytics for on-road perception of autonomous ground vehicles. IEEE Trans Ind Inform2023; 19(2): 1512–1523.
78.
GilroySJonesEGlavinM. Overcoming occlusion in the automotive environment—a review. IEEE Trans Intell Transp Syst2021; 22(1): 23–35.
79.
XuWDuXLiR, et al. Attention-enhanced strongsort for robust vehicle tracking in complex environments. Sci Rep2025; 15(1): 17472.
