Trajectory prediction is a challenging problem in autonomous driving, due to changes in scene structure and multimodal distributions of future trajectories. This study proposes a novel trajectory prediction model (LGINet). The central innovation of LGINet is the Context-Aware Graph Attention (CAGA) layer, which achieves a balance between handling scene complexity and the ability to capture information, improving prediction performance. Unlike conventional attention mechanisms, CAGA uses Sparsemax to focus on key neighbors, reducing noise and enhancing computational efficiency. The multi-head attention mechanism enhances the ability of the model to capture interactions across both local and long-distance spatial scales. Experiments with the nuScenes dataset show that the proposed LGINet model outperforms existing prediction methods. Specifically, the MinADE5 value of LGINet is 1.23, the MR5,2 value is 0.49, and the MinFDE5 value is 2.39, demonstrating its effectiveness in generating diverse and accurate future trajectories for autonomous driving applications. Qualitative comparisons confirm that LGINet generates diverse trajectories aligned with scene structures and agent motion, highlighting its potential for autonomous driving.
TeetiIKhanSShahbazA, et al. Vision-based intention and trajectory prediction in autonomous vehicles: a survey. In: Proceedings of the thirty-first international joint conference on artificial intelligence (IJCAI-22), Burlington, Massachusetts, 2023, pp.5630–5637. Morgan Kaufmann: Vienna, Austria.
2.
MozaffariSAl-JarrahOYDianatiM, et al. Deep learning-based vehicle behavior prediction for autonomous driving applications: a review. IEEE Trans Intell Transp Syst2020; 23(1): 33–47.
3.
LuanZHuangYZhaoW, et al. A comprehensive lateral motion prediction method of surrounding vehicles integrating driver intention prediction and vehicle behavior recognition. Proc IMechE, Part D: J Automobile Engineering2023; 237(1): 61–74.
4.
MengZHeRWuJ, et al. GIVA: interaction-aware trajectory prediction based on GRU-Improved VGG-Attention Mechanism model for autonomous vehicles. Proc IMechE, Part D: J Automobile Engineering2025; 239: 128–141.
5.
ZhangXZhangWWuX, et al. Probabilistic trajectory prediction of heterogeneous traffic agents based on layered spatio-temporal graph. Proc IMechE, Part D: J Automobile Engineering2021; 235(9): 2413–2424.
6.
BharilyaVKumarN.Machine learning for autonomous vehicle’s trajectory prediction: a comprehensive survey, challenges, and future research directions. Veh Commun2024; 46: 100733.
7.
HuangRXueHPagnuccoP, et al. Multimodal trajectory prediction: a survey. arXiv preprint arXiv:2302. 10463, 2023.
8.
BerenguerADAlioscha-PerezMOvenekeMC, et al. Context-aware human trajectories prediction via latent variational model. IEEE Trans Circuits Syst Video Technol2020; 31(5): 1876–1889.
9.
LiangMYangBHuR, et al. Learning lane graph representations for motion forecasting. In: VedaldiABischofHBroxT, et al. (eds) Computer vision–ECCV 2020: 16th European conference, Glasgow, UK, August 23–28, 2020, proceedings, part II 16. Cham: Springer, 2020, pp.541–556.
10.
MessaoudKDeoNTrivediMM, et al. Trajectory prediction for autonomous driving based on multi-head attention with joint agent-map representation. In: 2021 IEEE intelligent vehicles symposium (IV), Nagoya, Japan, 11–17 July 2021, pp.165–170. New York: IEEE.
11.
GuanYLiaoHLiZ, et al. World models for autonomous driving: an initial survey. IEEE Trans Intell Veh. Epub ahead of print 8 May 2024. DOI: 10.1109/TIV.2024.3398357.
12.
XingZZhaoSGuoW, et al. Coal resources under carbon peak: segmentation of massive laser point clouds for coal mining in underground dusty environments using integrated graph deep learning model. Energy2023; 285: 128771.
13.
WuYZhaoSXingZ, et al. Detection of foreign objects intrusion into transmission lines using diverse generation model. IEEE Trans Power Deliv2023; 38: 3551–3560.
14.
HuangYDuJYangZ, et al. A survey on trajectory-prediction methods for autonomous driving. IEEE Trans Intell Veh2022; 7: 652–674.
15.
SalzmannTIvanovicBChakravartyP, et al. Trajectron++: dynamically-feasible trajectory forecasting with heterogeneous data. In: VedaldiABischofHBroxT, et al. (eds) Computer vision–ECCV 2020: 16th European conference, Glasgow, UK, August 23–28, 2020, proceedings, part XVIII 16. Cham: Springer, 2020, pp.683–700.
16.
GaoZBaoMGaoF, et al. Probabilistic multi-modal expected trajectory prediction based on LSTM for autonomous driving. Proc IMechE, Part D: J Automobile Engineering2024; 238: 2817–2828.
17.
GillesTSabatiniSTsishkouD, et al. HOME: heatmap output for future motion estimation. In: 2021 IEEE international intelligent transportation systems conference (ITSC), Indianapolis, IN, USA, 19–22 September 2021, pp.500–507. New York: IEEE.
18.
KimBParkSHLeeS, et al. LaPred: lane-aware prediction of multi-modal future trajectories of dynamic agents. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Nashville, TN, USA, 20–25 June 2021, pp.14636–14645. New York: IEEE.
19.
ChandraRGuanTPanugantiS, et al. Forecasting trajectory and behavior of road-agents using spectral clustering in graph-LSTMs. IEEE Robot Autom Lett2020; 5(3): 4882–4890.
20.
SchmidtJJordanJGritschnederF, et al. CRAT-Pred: vehicle trajectory prediction with crystal graph convolutional neural networks and multi-head self-attention. In: 2022 international conference on robotics and automation (ICRA), Philadelphia, PA, USA, 23–27 May 2022, pp.7799–7805. New York: IEEE.
21.
GiraseHGangHMallaS, et al. LOKI: long term and key intentions for trajectory prediction. In: Proceedings of the IEEE/CVF international conference on computer vision, Montreal, QC, Canada, 10–17 October 2021, pp.9803–9812. New York: IEEE.
GhoulAMessaoudKYahiaouiI, et al. A lightweight goal-based model for trajectory prediction. In: 2022 IEEE 25th international conference on intelligent transportation systems (ITSC), Macau, China, 8–12 October 2022, pp.4209–4214. New York: IEEE.
24.
BhattacharyyaAReinoDOFritzM, et al. Euro-PVI: pedestrian vehicle interactions in dense urban centers. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Nashville, TN, USA, 20–25 June 2021, pp.6408–6417. New York: IEEE.
25.
YuanYWengXOuY, et al. AgentFormer: agent-aware transformers for socio-temporal multi-agent forecasting. In: Proceedings of the IEEE/CVF international conference on computer vision, Montreal, QC, Canada, 10–17 October 2021, pp.9813–9823. New York: IEEE.
26.
SongHLuanDDingW, et al. Learning to predict vehicle trajectories with model-based planning. Proc Mach Learn Res2022; 164: 1035–1045.
27.
ChoKHaTLeeG, et al. Deep predictive autonomous driving using multi-agent joint trajectory prediction and traffic rules. In: 2019 IEEE/RSJ international conference on intelligent robots and systems (IROS), Macau, China, 3–8 November 2019, pp.2076–2081. New York: IEEE.
28.
JiangZMaYShiB, et al. Social NSTransformers: low-quality pedestrian trajectory prediction. IEEE Trans Artif Intell2024; 5: 5575–5588.
29.
Phan-MinhTGrigoreECBoultonFA, et al. CoverNet: multimodal behavior prediction using trajectory sets. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Seattle, WA, USA, 13–19 June 2020, pp.14074–14083. New York: IEEE.
30.
CuiHRadosavljevicVChouF, et al. Multimodal trajectory predictions for autonomous driving using deep convolutional networks. In: 2019 international conference on robotics and automation (ICRA), Montreal, QC, Canada, 20–24 May 2019, pp.2090–2096. New York: IEEE.
ZengWLiangMLiaoR, et al. LaneRCNN: distributed representations for graph-centric motion forecasting. In 2021 IEEE/RSJ International conference on intelligent robots and systems (IROS), Prague, Czech Republic, 27 September–1 October 2021, pp.532–539. New York: IEEE.
33.
ChenYIvanovicBPavoneM. ScePT: scene-consistent, policy-based trajectory predictions for planning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, New Orleans, LA, USA, 18–24 June 2022, pp.17103–17112. New York: IEEE.
34.
GaoJSunCZhaoH, et al. VectorNet: encoding HD maps and agent dynamics from vectorized representation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Seattle, WA, USA, 13–19 June 2020, pp.11525–11533. New York: IEEE.
35.
GillesTSabatiniSTsishkouD, et al. GOHOME: graph-oriented heatmap output for future motion estimation. In: 2022 international conference on robotics and automation (ICRA), Philadelphia, PA, USA, 23–27 May 2022, pp.9107–9114. New York: IEEE.
36.
VeličkovićPCucurullPCasanovaA, et al. Graph attention networks. arXiv preprint arXiv:1710.10903, 2017.
37.
CaesarHBankitiVLangAL, et al. nuScenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Seattle, WA, USA, 13–19 June 2020, pp.11621–11631. New York: IEEE.
38.
ChaiYSappBBansalM, et al. Multipath: multiple probabilistic anchor trajectory hypotheses for behavior prediction. arXiv preprint arXiv:1910.05449, 2019.
39.
LuoCSunLDabiriD, et al. Probabilistic multi-modal trajectory prediction with lane attention for autonomous vehicles. In: 2020 IEEE/RSJ international conference on intelligent robots and systems (IROS), Las Vegas, NV, USA, 24 October 2020–24 January 2021, pp.2370–2376. New York: IEEE.
40.
KhandelwalSQiWSinghJ, et al. What-if motion prediction for autonomous driving. arXiv preprint arXiv:2008.10587, 2020.
41.
NarayananSMoslemiRPittalugaF, et al. Divide-and-conquer for lane-aware diverse trajectory prediction. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Nashville, TN, USA, 20–25 June 2021, pp.15799–15808. New York: IEEE.
42.
GillesTSabatiniSTsishkouD, et al. Thomas: trajectory heatmap output with learned multi-agent sampling. arXiv preprint arXiv:2110.06607, 2021.
43.
WangCWangYXuM, et al. Stepwise goal-driven networks for trajectory prediction. IEEE Robot Autom Lett2022; 7: 2716–2723.
44.
GrimmDSchörnerPDreßlerM, et al. Holistic graph-based motion prediction. In: 2023 IEEE international conference on robotics and automation (ICRA), London, UK, 29 May–2 June 2023, pp.2965–2972. New York: IEEE.
45.
GrimmDZipflMHertleinF, et al. Heterogeneous graph-based trajectory prediction using local map context and social interactions. In: 2023 IEEE 26th international conference on intelligent transportation systems (ITSC), Bilbao, Spain, 24–28 September 2023, pp.2901–2907. New York: IEEE.
46.
ZhangZHuaZChenM, et al. G2LTraj: a global-to-local generation approach for trajectory prediction. arXiv preprint arXiv:2404.19330, 2024.
