Interaction-aware and driving style-aware trajectory prediction for heterogeneous vehicles in mixed traffic environment

Zhang, QixiangXing, YangWang, JinxiangFang, ZhenwuLiu, YahuiYin, Guodong2025-06-112025-06-112025Zhang Q, Xing Y, Wang J, et al., (2025) Interaction-aware and driving style-aware trajectory prediction for heterogeneous vehicles in mixed traffic environment. IEEE Transactions on Intelligent Transportation Systems, Available online 1 April 20251524-9050https://doi.org/10.1109/tits.2025.3553697https://dspace.lib.cranfield.ac.uk/handle/1826/24018Trajectory prediction (TP) of surrounding vehicles (SVs) is crucial for autonomous vehicles (AVs) to understand traffic situations and achieve safe-efficient decision-making and motion planning. However, different drivers’ personalized driving preferences will bring uncertainties for long-term TP in the mixed traffic environment. To this end, this paper proposes a TP model with interaction awareness and driving style awareness for long-term TP of heterogeneous SVs. Firstly, the driving conditions in the highD dataset are distinguished, and three different driving styles of the vehicle in the car-following condition are obtained based on an unsupervised clustering algorithm. Then, an encoder-decoder architecture based on novel lane attention and multi-head attention mechanisms is proposed, where the encoder analyzes historical trajectory patterns and the decoder generates future trajectory sequences. The lane attention mechanism enhances the spatial perception capability of vehicles towards the target lane, and the multi-head attention mechanism extracts high-dimensional global interaction information about the heterogeneous vehicle group (HVG) surrounding the target vehicle (TV). Experimental results show that the proposed model outperforms state-of-the-art models in root-mean-square-error (RMSE) for long-term TP and exhibits excellent adaptability to diverse driving tasks. Moreover, this paper verifies that the driving style topology within the HVG has multiple impacts on the TP accuracy of the TV.pp. xx-xxenAttribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/TrajectoryTVAttention mechanismsPredictive modelsEncodingAccuracyVehiclesLong short term memoryVehicle dynamicsComputational modelingTrajectory predictionmixed traffic environmentheterogeneous vehiclespersonalized drivingvehicle interactions3509 Transportation, Logistics and Supply Chains46 Information and Computing Sciences35 Commerce, Management, Tourism and ServicesLogistics & Transportation4602 Artificial intelligence4603 Computer vision and multimedia computationInteraction-aware and driving style-aware trajectory prediction for heterogeneous vehicles in mixed traffic environmentArticle1558-0016672762ahead-of-printahead-of-print