pith. sign in

arxiv: 2503.03262 · v3 · submitted 2025-03-05 · 💻 cs.RO · cs.AI· cs.CV· cs.LG

Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions

Nadya Abdel Madjid , Abdulrahman Ahmad , Murad Mebrahtu , Yousef Babaa , Abdelmoamen Nasser , Sumbal Malik , Bilal Hassan , Naoufel Werghi
show 2 more authors
Jorge Dias Majid Khonji
This is my paper

Pith reviewed 2026-05-23 01:35 UTC · model grok-4.3

classification 💻 cs.RO cs.AIcs.CVcs.LG
keywords trajectory predictionautonomous drivingmotion forecastingtaxonomyreviewprediction pipelineautonomous vehiclesresearch gaps
0
0 comments X

The pith

A review of trajectory prediction methods organizes them into a taxonomy and identifies remaining challenges for autonomous driving.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper examines numerous recent techniques for forecasting the paths of surrounding vehicles and agents to enable safe autonomous navigation. It introduces a taxonomy that groups these methods according to their core characteristics. An overview of the typical prediction pipeline is presented, detailing common inputs like sensor data, outputs like future positions, and various modeling strategies. The work also examines current research trends and points out specific gaps that future efforts need to address. This matters because unresolved issues in prediction can directly impact collision avoidance in mixed traffic.

Core claim

By surveying a substantial portion of recent trajectory prediction methods, the authors propose a taxonomy to classify existing solutions and provide a general overview of the prediction pipeline covering input and output modalities, modeling features, and prediction paradigms. The paper discusses active research areas, addresses posed research questions, and highlights remaining research gaps and challenges in the field.

What carries the argument

The taxonomy classifying trajectory prediction solutions based on their approaches and the overview of the prediction pipeline.

If this is right

  • The classification helps distinguish between different prediction paradigms and their strengths.
  • Identified gaps guide future research directions in trajectory forecasting.
  • The pipeline overview aids in understanding how inputs from sensors lead to trajectory outputs.
  • Active areas indicate where improvements in accuracy and robustness are needed.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The taxonomy might serve as a framework for comparing new algorithms quantitatively.
  • Closing the highlighted gaps could improve the reliability of autonomous vehicles in complex urban scenarios.
  • Connections to multi-agent systems in robotics could be explored using similar classification.

Load-bearing premise

The selected body of recent methods is representative of the field and the proposed taxonomy accurately captures the meaningful differences among approaches without major omissions or overlaps.

What would settle it

Discovery of a significant number of trajectory prediction methods from the past decade that do not fit the proposed taxonomy or were overlooked in the review would challenge the paper's claims about coverage and classification.

Figures

Figures reproduced from arXiv: 2503.03262 by Abdelmoamen Nasser, Abdulrahman Ahmad, Bilal Hassan, Jorge Dias, Majid Khonji, Murad Mebrahtu, Nadya Abdel Madjid, Naoufel Werghi, Sumbal Malik, Yousef Babaa.

Figure 1
Figure 1. Figure 1: Factors impacting Trajectory Prediction: 1) cars waiting at a red light, demonstrating adherence to tra [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Structure of the review paper: the study comprises seven main sections. The first two sections - an overview of the prediction pipeline and a survey [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Overview of trajectory prediction pipeline: including input modalities (past trajectories, sensor data, and HD maps), key modeling features (target agent, [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Point clouds captured using a 64-layered Ouster LiDAR and 64-layered Kinetic LiDAR: (a) in a parking area, (b) on a campus, (c) during an Autonomous [PITH_FULL_IMAGE:figures/full_fig_p009_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: BEV representation aligning dynamic and static elements: raw point cloud data, HD map, and ground truth 3D bounding boxes. [PITH_FULL_IMAGE:figures/full_fig_p010_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Overview of prediction paradigms in autonomous driving: (a) Detect-Track-Predict: a modular pipeline where detections initialize and update tracklets, [PITH_FULL_IMAGE:figures/full_fig_p016_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Different fusion approaches for LiDAR and camera data: early fusion, late fusion and BEV fusion. tions being passed to the planner, potentially degrading overall system performance. While the Detect-Track-Predict paradigm is modular and in￾tuitive, its sequential nature causes errors to propagate across modules, with detection inaccuracies leading to unreliable tracklets and degraded predictions. Additiona… view at source ↗
Figure 8
Figure 8. Figure 8: Taxonomy of modeling methods for trajectory prediction, divided into two main branches: physics-based approaches and learning-based approaches. The [PITH_FULL_IMAGE:figures/full_fig_p019_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: ML approaches for trajectory prediction: (a) - GP modelling observed and predicted trajectories showing uncertainty bounds; (b) - HMM representing [PITH_FULL_IMAGE:figures/full_fig_p020_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Main DL approaches presented schematically in application to prediction where the input is past trajectory: (a) - RNN/ [PITH_FULL_IMAGE:figures/full_fig_p021_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Types of Uncertainty: the left side shows the categorization followed in the section and the right part demonstrates the flow of the prediction model and [PITH_FULL_IMAGE:figures/full_fig_p036_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: A general pipeline for anchor-based prediction models: (left) - goal anchor-based and (right) - trajectory anchor-based. [PITH_FULL_IMAGE:figures/full_fig_p039_12.png] view at source ↗
Figure 13
Figure 13. Figure 13: VLM-based trajectory prediction model: encoders for visual and textual inputs, a cross-modal attention mechanism to create a joint representation and [PITH_FULL_IMAGE:figures/full_fig_p042_13.png] view at source ↗
Figure 14
Figure 14. Figure 14: Collaboration between AVs: (a) - scenario for collaborative perception, vehicle [PITH_FULL_IMAGE:figures/full_fig_p045_14.png] view at source ↗
read the original abstract

As the potential for autonomous vehicles to be integrated on a large scale into modern traffic systems continues to grow, ensuring safe navigation in dynamic environments is crucial for smooth integration. To guarantee safety and prevent collisions, autonomous vehicles must be capable of accurately predicting the trajectories of surrounding traffic agents. Over the past decade, significant efforts from both academia and industry have been dedicated to designing solutions for precise trajectory forecasting. These efforts have produced a diverse range of approaches, raising questions about the differences between these methods and whether trajectory prediction challenges have been fully addressed. This paper reviews a substantial portion of recent trajectory prediction methods proposing a taxonomy to classify existing solutions. A general overview of the prediction pipeline is also provided, covering input and output modalities, modeling features, and prediction paradigms existing in the literature. In addition, the paper discusses active research areas within trajectory prediction, addresses the posed research questions, and highlights the remaining research gaps and challenges.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. This paper reviews a substantial portion of recent trajectory prediction methods for autonomous driving. It proposes a taxonomy to classify existing solutions, provides a general overview of the prediction pipeline (covering input/output modalities, modeling features, and prediction paradigms), discusses active research areas, addresses posed research questions, and highlights remaining research gaps and challenges.

Significance. If the taxonomy is justified by the reviewed papers, the coverage is comprehensive without major omissions or overlaps, and the discussion of gaps is evidence-based, the survey would offer a useful structured overview to help organize the literature and guide future work in trajectory prediction for AVs.

major comments (2)
  1. [Taxonomy and classification section] The central claim that the proposed taxonomy accurately classifies existing solutions without major omissions or overlaps is load-bearing but not demonstrated in detail; the manuscript should explicitly map the reviewed methods to taxonomy categories with examples from specific papers to substantiate the classification scheme.
  2. [Introduction and review methodology] The claim of reviewing 'a substantial portion' of recent methods requires clearer criteria for paper selection (e.g., time period, venues, keywords) and a quantitative summary (number of papers per category) to allow assessment of representativeness.
minor comments (2)
  1. [Abstract] The abstract could be expanded to include the approximate number of reviewed papers and the covered time span for better context.
  2. [References] Ensure all cited works in the taxonomy discussion are consistently referenced with full bibliographic details.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive comments. We address each major comment below and will incorporate the suggested improvements into a revised manuscript.

read point-by-point responses

  1. Referee: [Taxonomy and classification section] The central claim that the proposed taxonomy accurately classifies existing solutions without major omissions or overlaps is load-bearing but not demonstrated in detail; the manuscript should explicitly map the reviewed methods to taxonomy categories with examples from specific papers to substantiate the classification scheme.

    Authors: We agree that the taxonomy would benefit from more explicit substantiation. In the revised version we will add a dedicated subsection (or table) that maps representative papers to each taxonomy category, citing specific methods and briefly noting how their design choices align with the category definitions. This will directly demonstrate coverage and lack of major overlaps. revision: yes

  2. Referee: [Introduction and review methodology] The claim of reviewing 'a substantial portion' of recent methods requires clearer criteria for paper selection (e.g., time period, venues, keywords) and a quantitative summary (number of papers per category) to allow assessment of representativeness.

    Authors: We accept this point. The revised introduction will explicitly state the search period (2015–2024), target venues, and keyword combinations used. We will also insert a quantitative summary (e.g., a table or paragraph) reporting the number of papers retained per taxonomy category, allowing readers to evaluate representativeness directly. revision: yes

Circularity Check

0 steps flagged

Review paper with no internal derivations or predictions

full rationale

This is a survey paper whose core contribution is a descriptive taxonomy and overview of existing trajectory prediction methods drawn from the literature. No original equations, fitted parameters, uniqueness theorems, or predictions are derived within the paper itself; all substantive content is attributed to external citations. The representativeness of the reviewed set is a matter of scholarly selection rather than a self-referential derivation that reduces to its own inputs. Consequently there are no load-bearing steps that can be shown to be circular by the paper's own text.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a literature review paper; the abstract introduces no new free parameters, mathematical axioms, or invented entities.

pith-pipeline@v0.9.0 · 5732 in / 1053 out tokens · 33956 ms · 2026-05-23T01:35:10.392647+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Frozen LLMs as Map-Aware Spatio-Temporal Reasoners for Vehicle Trajectory Prediction

    cs.CV 2026-04 unverdicted novelty 5.0

    A framework encodes observed trajectories and HD maps into tokens for frozen LLMs to perform spatio-temporal reasoning and predict future vehicle paths with a linear decoder.

Reference graph

Works this paper leans on

290 extracted references · 290 canonical work pages · cited by 1 Pith paper · 2 internal anchors

  1. [1]

    Salzmann, B

    T. Salzmann, B. Ivanovic, P. Chakravarty, M. Pavone, Trajectron++: Dynamically-feasible trajectory fore- casting with heterogeneous data, in: Computer Vision – ECCV 2020: 16th European Confer- ence, Glasgow, UK, August 23–28, 2020, Pro- ceedings, Part XVIII, Springer-Verlag, Berlin, Heidelberg, 2020, p. 683–700. URL:https: //doi.org/10.1007/978-3-030-5852...

    work page doi:10.1007/978-3-030-58523-5_40 2020

  2. [2]

    W. Chen, F. Wang, H. Sun, S2tnet: Spatio-temporal transformer networks for trajectory prediction in au- tonomous driving, in: V . N. Balasubramanian, I. Tsang (Eds.), Proceedings of The 13th Asian Con- ference on Machine Learning, volume 157 ofProceed- ings of Machine Learning Research, PMLR, 2021, pp. 454–469. URL:https://proceedings.mlr.press/ v157/chen21a.html

    work page 2021

  3. [3]

    Varadarajan, A

    B. Varadarajan, A. Hefny, A. Srivastava, K. S. Re- faat, N. Nayakanti, A. Cornman, K. Chen, B. Douil- lard, C. P. Lam, D. Anguelov, B. Sapp, Multipath++: Efficient information fusion and trajectory aggregation for behavior prediction, in: 2022 International Con- ference on Robotics and Automation (ICRA), IEEE Press, 2022, p. 7814–7821. URL:https://doi.org...

    work page doi:10.1109/icra46639.2022.9812107 2022

  4. [4]

    A Survey on Trajectory -Prediction Methods for Autonomous Driving,

    Y . Huang, J. Du, Z. Yang, Z. Zhou, L. Zhang, H. Chen, A survey on trajectory-prediction methods for autonomous driving, IEEE Transactions on Intelligent Vehicles 7 (2022) 652–674. doi:10.1109/TIV.2022.3167103

    work page doi:10.1109/tiv.2022.3167103 2022

  5. [5]

    Bharilya, N

    V . Bharilya, N. Kumar, Machine learning for au- tonomous vehicle’s trajectory prediction: A comprehen- sive survey, challenges, and future research directions, Vehicular Communications 46 (2024) 100733. URL: https://www.sciencedirect.com/science/ article/pii/S2214209624000081. doi:https: //doi.org/10.1016/j.vehcom.2024.100733

    work page doi:10.1016/j.vehcom.2024.100733 2024

  6. [6]

    J. Liu, X. Mao, Y . Fang, D. Zhu, M. Q. Meng, A survey on deep-learning approaches for vehicle trajec- tory prediction in autonomous driving, 2021 IEEE International Conference on Robotics and Biomimet- ics (ROBIO) (2021) 978–985. URL:https://api. semanticscholar.org/CorpusID:239049431

    work page 2021

  7. [7]

    Teeti, S

    I. Teeti, S. Khan, A. Shahbaz, A. Bradley, F. Cuz- zolin, Vision-based intention and trajectory predic- tion in autonomous vehicles: A survey, in: L. D. Raedt (Ed.), Proceedings of the Thirty-First Interna- tional Joint Conference on Artificial Intelligence, IJCAI 2022, Vienna, Austria, 23-29 July 2022, ijcai.org, 2022, pp. 5630–5637. URL:https://doi.org/...

    work page doi:10.24963/ijcai.2022/785 2022

  8. [8]

    F. Leon, M. Gavrilescu, A review of tracking and trajec- tory prediction methods for autonomous driving, Math- ematics 9 (2021). URL:https://www.mdpi.com/ 2227-7390/9/6/660. doi:10.3390/math9060660

    work page doi:10.3390/math9060660 2021

  9. [10]

    Z. Ding, H. Zhao, Incorporating driving knowledge in deep learning based vehicle trajectory prediction: A sur- vey, IEEE Transactions on Intelligent Vehicles (2023) 1–20. doi:10.1109/TIV.2023.3266446

    work page doi:10.1109/tiv.2023.3266446 2023

  10. [12]

    Rudenko, L

    A. Rudenko, L. Palmieri, M. Herman, K. M. Kitani, D. M. Gavrila, K. O. Arras, Hu- man motion trajectory prediction: A survey, Int. J. Rob. Res. 39 (2020) 895–935. URL: https://doi.org/10.1177/0278364920917446. doi:10.1177/0278364920917446

    work page doi:10.1177/0278364920917446 2020

  11. [13]

    B. I. Sighencea, R. I. Stanciu, C. D. C ˘aleanu, A re- view of deep learning-based methods for pedestrian tra- jectory prediction, Sensors 21 (2021). URL:https: //www.mdpi.com/1424-8220/21/22/7543

    work page 2021

  12. [14]

    Korbmacher, A

    R. Korbmacher, A. Tordeux, Review of pedestrian tra- jectory prediction methods: Comparing deep learning and knowledge-based approaches, IEEE Transactions on Intelligent Transportation Systems 23 (2022) 24126– 24144. doi:10.1109/TITS.2022.3205676

    work page doi:10.1109/tits.2022.3205676 2022

  13. [16]

    I. P. Gomes, D. F. Wolf, A review on intention-aware and interaction-aware trajectory prediction for autonomous vehicles, 2022. doi:10.36227/techrxiv.19337447. v1

    work page doi:10.36227/techrxiv.19337447 2022

  14. [17]

    In: Proceedings of the IEEE/CVF Conference on Computer 25 Vision and Pattern Recognition, pp

    H. Caesar, V . Bankiti, A. H. Lang, S. V ora, V . E. Liong, Q. Xu, A. Krishnan, Y . Pan, G. Baldan, O. Beijbom, nuScenes: A Multimodal Dataset for Autonomous Driv- ing , in: 2020 IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition (CVPR), IEEE Computer Society, Los Alamitos, CA, USA, 2020, pp. 11618– 11628. URL:https://doi.ieeecomputersociety...

    work page doi:10.1109/cvpr42600.2020.01164 2020

  15. [18]

    L. Ye, Z. Zhou, J. Wang, Improving the generaliz- ability of trajectory prediction models with frenét-based domain normalization, in: 2023 IEEE International Conference on Robotics and Automation (ICRA), IEEE, 2023, p. 11562–11568. URL:http://dx.doi.org/ 10.1109/ICRA48891.2023.10160788. doi:10.1109/ icra48891.2023.10160788

    work page doi:10.1109/icra48891.2023.10160788 2023

  16. [20]

    Zyner, S

    A. Zyner, S. Worrall, E. Nebot, A recurrent neural net- work solution for predicting driver intention at unsignal- ized intersections, IEEE Robotics and Automation Letters 3 (2018) 1759–1764. doi:10.1109/LRA.2018. 2805314

    work page doi:10.1109/lra.2018 2018

  17. [21]

    Zyner, S

    A. Zyner, S. Worrall, E. M. Nebot, Naturalistic driver intention and path prediction using recurrent neural net- works, IEEE Transactions on Intelligent Transportation Systems 21 (2018) 1584–1594. URL:https://api. semanticscholar.org/CorpusID:50783158

    work page 2018

  18. [22]

    S. Park, B. Kim, C. M. Kang, C. C. Chung, J. W. Choi, Sequence-to-sequence prediction of vehicle tra- jectory via lstm encoder-decoder architecture, 2018 IEEE Intelligent Vehicles Symposium (IV) (2018) 1672–

    work page 2018

  19. [23]

    URL:https://api.semanticscholar.org/ CorpusID:3653452

    work page

  20. [24]

    D. J. Phillips, T. A. Wheeler, M. J. Kochenderfer, Gen- eralizable intention prediction of human drivers at in- tersections, 2017 IEEE Intelligent Vehicles Sympo- sium (IV) (2017) 1665–1670. URL:https://api. semanticscholar.org/CorpusID:27006002

    work page 2017

  21. [25]

    S. Dai, L. Li, Z. Li, Modeling vehicle interactions via modified lstm models for trajectory prediction, IEEE Access 7 (2019) 38287–38296. doi:10.1109/ACCESS. 2019.2907000

    work page doi:10.1109/access 2019

  22. [26]

    W. Ding, S. Shen, Online vehicle trajectory predic- tion using policy anticipation network and optimization- based context reasoning, 2019 International Confer- ence on Robotics and Automation (ICRA) (2019) 9610–

    work page 2019

  23. [27]

    URL:https://api.semanticscholar.org/ CorpusID:67856564

    work page

  24. [28]

    Diehl, T

    F. Diehl, T. Brunner, M. Truong-Le, A. Knoll, Graph neural networks for modelling traffic participant in- teraction, 2019 IEEE Intelligent Vehicles Sym- posium (IV) (2019) 695–701. URL:https://api. semanticscholar.org/CorpusID:67856289

    work page 2019

  25. [29]

    Y . Hu, W. Zhan, M. Tomizuka, Probabilistic predic- tion of vehicle semantic intention and motion, 2018 IEEE Intelligent Vehicles Symposium (IV) (2018) 307–

    work page 2018

  26. [30]

    URL:https://api.semanticscholar.org/ CorpusID:4754151

    work page

  27. [31]

    W. Ding, J. Chen, S. Shen, Predicting vehicle be- haviors over an extended horizon using behavior in- teraction network, 2019 International Conference on Robotics and Automation (ICRA) (2019) 8634–

    work page 2019

  28. [32]

    URL:https://api.semanticscholar.org/ CorpusID:67856192

    work page

  29. [34]

    X. Song, K. Chen, X. Li, J. Sun, B. Hou, Y . Cui, B. Zhang, G. Xiong, Z. Wang, Pedestrian trajectory prediction based on deep convolutional lstm network, 52 IEEE Transactions on Intelligent Transportation Sys- tems 22 (2021) 3285–3302. doi:10.1109/TITS.2020. 2981118

    work page doi:10.1109/tits.2020 2021

  30. [35]

    Ma, et al., An intelligence-based approach for predic- tion of microscopic pedestrian walking behavior, IEEE Transactions on Intelligent Transportation Systems 20 (2019) 3964–3980

    Y . Ma, et al., An intelligence-based approach for predic- tion of microscopic pedestrian walking behavior, IEEE Transactions on Intelligent Transportation Systems 20 (2019) 3964–3980

    work page 2019

  31. [36]

    Carrasco, D

    S. Carrasco, D. F. Llorca, M. Á. Sotelo, Scout: Socially-consistent and understandable graph attention network for trajectory prediction of vehicles and vrus, 2021 IEEE Intelligent Vehicles Symposium (IV) (2021) 1501–1508. URL:https://api.semanticscholar. org/CorpusID:231918397

    work page 2021

  32. [37]

    Y . He, H. Yu, X. Liu, Z. Yang, W. Sun, Y . Wang, Q. Fu, Y . Zou, A. Mian, Deep learning based 3d segmentation: A survey, CoRR abs/2103.05423 (2021). URL:https://arxiv.org/abs/2103.05423. arXiv:2103.05423

    work page arXiv 2021

  33. [38]

    R. Qian, X. Lai, X. Li, 3d object detection for au- tonomous driving: A survey, Pattern Recognition 130 (2022) 108796

    work page 2022

  34. [39]

    J. Mao, S. Shi, X. Wang, H. Li, 3d object detection for autonomous driving: A comprehensive survey, Inter- national Journal of Computer Vision 131 (2023) 1909– 1963

    work page 2023

  35. [40]

    P. K. Vinodkumar, D. Karabulut, E. Avots, C. Ozci- nar, G. Anbarjafari, A survey on deep learning based segmentation, detection and classification for 3d point clouds, Entropy 25 (2023)

    work page 2023

  36. [41]

    G. P. Meyer, A. Laddha, E. Kee, C. Vallespi-Gonzalez, C. K. Wellington, Lasernet: An efficient probabilistic 3d object detector for autonomous driving, in: 2019 IEEE/CVF Conference on Computer Vision and Pat- tern Recognition (CVPR), IEEE Computer Society, Los Alamitos, CA, USA, 2019, pp. 12669–12678

    work page 2019

  37. [42]

    Li, 3d fully convolutional network for vehicle de- tection in point cloud, in: 2017 IEEE/RSJ Interna- tional Conference on Intelligent Robots and Systems (IROS), 2017, pp

    B. Li, 3d fully convolutional network for vehicle de- tection in point cloud, in: 2017 IEEE/RSJ Interna- tional Conference on Intelligent Robots and Systems (IROS), 2017, pp. 1513–1518. doi:10.1109/IROS. 2017.8205955

    work page doi:10.1109/iros 2017

  38. [43]

    H. Wang, B. Wang, B. Liu, X. Meng, G. Yang, Pedestrian recognition and tracking using 3d lidar for autonomous vehicle, Robotics and Autonomous Systems 88 (2017) 71–78. URL: https://www.sciencedirect.com/science/ article/pii/S0921889015302633. doi:https: //doi.org/10.1016/j.robot.2016.11.014

    work page doi:10.1016/j.robot.2016.11.014 2017

  39. [44]

    H. Wang, X. Lou, Y . Cai, L. Chen, A 64-line lidar-based road obstacle sensing algorithm for intelligent vehicles, Scientific Programming 2018 (2018) 6385104. URL: https://doi.org/10.1155/2018/6385104. doi:10. 1155/2018/6385104

    work page doi:10.1155/2018/6385104 2018

  40. [45]

    N. Peri, J. Luiten, M. Li, A. Ošep, L. Leal-Taixé, D. Ra- manan, Forecasting from lidar via future object detec- tion, in: 2022 IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition (CVPR), 2022, pp. 17181– 17190. doi:10.1109/CVPR52688.2022.01669

    work page doi:10.1109/cvpr52688.2022.01669 2022

  41. [46]

    W. Luo, B. Yang, R. Urtasun, Fast and furious: Real time end-to-end 3d detection, tracking and motion forecasting with a single convolutional net, in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recogni- tion (CVPR), IEEE Computer Society, Los Alamitos, CA, USA, 2018, pp. 3569–3577. URL:https: //doi.ieeecomputersociety.org/10.1109/ CVPR.2018.0...

    work page doi:10.1109/cvpr.2018.00376 2018

  42. [47]

    B. Völz, K. Behrendt, H. Mielenz, I. Gilitschenski, R. Siegwart, J. Nieto, A data-driven approach for pedestrian intention estimation, in: 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), 2016, pp. 2607–2612. doi:10.1109/ ITSC.2016.7795975

    work page arXiv 2016

  43. [48]

    H. Wu, J. Deng, C. Wen, X. Li, C. Wang, Casa: A cas- cade attention network for 3d object detection from lidar point clouds, IEEE Transactions on Geoscience and Re- mote Sensing (2022)

    work page 2022

  44. [49]

    H. Wu, C. Wen, S. Shi, X. Li, C. Wang, Virtual sparse convolution for multimodal 3d object detection, in: 2023 IEEE/CVF Conference on Computer Vision and Pat- tern Recognition (CVPR), IEEE Computer Society, Los Alamitos, CA, USA, 2023, pp. 21653–21662

    work page 2023

  45. [50]

    Y . Sun, W. Zuo, M. Liu, See the future: A semantic segmentation network predicting ego-vehicle trajectory with a single monocular camera, IEEE Robotics and Automation Letters 5 (2020) 3066–3073. doi:10.1109/ LRA.2020.2975414

    work page arXiv 2020

  46. [51]

    Neumann, A

    L. Neumann, A. Vedaldi, Pedestrian and ego-vehicle trajectory prediction from monocular camera, in: Pro- ceedings of the IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition (CVPR), 2021, pp. 10204– 10212

    work page 2021

  47. [52]

    MANGLIK, X

    A. MANGLIK, X. WENG, E. OHN-BAR, K. KITANI, Future near-collision prediction from monocular video: Feasibility, dataset, and challenges, IEEE/RSJ Inter- national Conference on Intelligent Robots and Systems (2019)

    work page 2019

  48. [53]

    Rizzoli, F

    G. Rizzoli, F. Barbato, P. Zanuttigh, Multimodal seman- tic segmentation in autonomous driving: A review of current approaches and future perspectives, Technolo- gies 10 (2022). 53

    work page 2022

  49. [54]

    X. Yan, S. Hu, Y . Mao, Y . Ye, H. Yu, Deep multi- view learning methods: A review, Neurocomputing 448 (2021) 106–129

    work page 2021

  50. [55]

    Loukkal, Y

    A. Loukkal, Y . Grandvalet, T. Drummond, Y . Li, Driv- ing among flatmobiles: Bird-eye-view occupancy grids from a monocular camera for holistic trajectory plan- ning, in: Proceedings of the IEEE/CVF Winter Con- ference on Applications of Computer Vision (W ACV), 2021, pp. 51–60

    work page 2021

  51. [56]

    Zhong, H

    J. Zhong, H. Sun, W. Cao, Z. He, Pedestrian motion trajectory prediction with stereo-based 3d deep pose es- timation and trajectory learning, IEEE Access 8 (2020) 23480–23486. doi:10.1109/ACCESS.2020.2969994

    work page doi:10.1109/access.2020.2969994 2020

  52. [57]

    Bhattacharyya, M

    A. Bhattacharyya, M. Fritz, B. Schiele, Long-term on-board prediction of people in traffic scenes under uncertainty, 2018 IEEE/CVF Conference on Com- puter Vision and Pattern Recognition (2017) 4194–

    work page 2018

  53. [58]

    URL:https://api.semanticscholar.org/ CorpusID:19515346

    work page

  54. [59]

    N. A. Madjid, A. Sharma, B. Hassan, N. Werghi, J. Dias, M. Khonji, Multi-target tracker for low light vision, in: 2023 21st International Conference on Advanced Robotics (ICAR), IEEE, 2023, pp. 252–257

    work page 2023

  55. [60]

    H. H. Meinel, Evolving automotive radar — from the very beginnings into the future, The 8th Euro- pean Conference on Antennas and Propagation (Eu- CAP 2014) (2014) 3107–3114. URL:https://api. semanticscholar.org/CorpusID:24735994

    work page 2014

  56. [61]

    Reina, D

    G. Reina, D. Johnson, J. Underwood, Radar sensing for intelligent vehicles in urban environments, Sensors 15 (2015) 14661–14678

    work page 2015

  57. [62]

    Hasch, Driving towards 2020: Automotive radar technology trends, IEEE MTT-S International Confer- ence on Microwaves for Intelligent Mobility (ICMIM) (2015) 1–4

    J. Hasch, Driving towards 2020: Automotive radar technology trends, IEEE MTT-S International Confer- ence on Microwaves for Intelligent Mobility (ICMIM) (2015) 1–4. URL:https://api.semanticscholar. org/CorpusID:14729074

    work page 2020

  58. [63]

    Kim, S.-H

    S. Kim, S.-H. Lee, S. Doo, B. Shim, Moving target classification in automotive radar systems using convo- lutional recurrent neural networks, 2018 26th Euro- pean Signal Processing Conference (EUSIPCO) (2018) 1482–1486. URL:https://api.semanticscholar. org/CorpusID:54435182

    work page 2018

  59. [64]

    Steinhauser, P

    D. Steinhauser, P. Held, A. Kamann, A. Koch, T. Brand- meier, Micro-doppler extraction of pedestrian limbs for high resolution automotive radar, 2019 IEEE Intelligent Vehicles Symposium (IV) (2019) 764–769

    work page 2019

  60. [65]

    Major, D

    B. Major, D. Fontijne, A. Ansari, R. T. Sukhavasi, R. Gowaiker, M. A. Hamilton, S. Lee, S. K. Grzechnik, S. Subramanian, Vehicle detection with automotive radar using deep learning on range-azimuth-doppler tensors, 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) (2019) 924–932

    work page 2019

  61. [66]

    Palffy, E

    A. Palffy, E. Pool, S. Baratam, J. F. P. Kooij, D. M. Gavrila, Multi-class road user detection with 3+1d radar in the view-of-delft dataset, IEEE Robotics and Automa- tion Letters 7 (2022) 4961–4968

    work page 2022

  62. [67]

    D. Lee, Y . P. Kwon, S. McMains, J. K. Hedrick, Convo- lution neural network-based lane change intention pre- diction of surrounding vehicles for acc, 2017 IEEE 20th International Conference on Intelligent Transporta- tion Systems (ITSC) (2017) 1–6. URL:https://api. semanticscholar.org/CorpusID:3902524

    work page 2017

  63. [68]

    H. Cui, V . Radosavljevic, F.-C. Chou, T.-H. Lin, T. Nguyen, T.-K. Huang, J. Schneider, N. Djuric, Multi- modal trajectory predictions for autonomous driving us- ing deep convolutional networks, in: 2019 International Conference on Robotics and Automation (ICRA), IEEE Press, 2019, p. 2090–2096. doi:10.1109/ICRA.2019. 8793868

    work page doi:10.1109/icra.2019 2019

  64. [69]

    N. Deo, M. M. Trivedi, Convolutional social pooling for vehicle trajectory prediction, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018

    work page 2018

  65. [70]

    T. Zhao, Y . Xu, M. Monfort, W. Choi, C. L. Baker, Y . Zhao, Y . Wang, Y . N. Wu, Multi-agent tensor fu- sion for contextual trajectory prediction, in: IEEE Con- ference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, Computer Vision Foundation/IEEE, 2019, pp. 12126– 12134. doi:10.1109/CVPR.2019.01240

    work page doi:10.1109/cvpr.2019.01240 2019

  66. [71]

    N. Lee, W. Choi, P. Vernaza, C. B. Choy, P. H. S. Torr, M. Chandraker, Desire: Distant future prediction in dynamic scenes with interacting agents, 2017 IEEE Conference on Computer Vision and Pattern Recogni- tion (CVPR) (2017) 2165–2174. URL:https://api. semanticscholar.org/CorpusID:8394584

    work page 2017

  67. [72]

    P. Li, S. Ding, X. Chen, N. Hanselmann, M. Cordts, J. Gall, Powerbev: a powerful yet lightweight framework for instance prediction in bird’s-eye view, in: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI ’23,

    work page

  68. [73]

    2023/120

    URL:https://doi.org/10.24963/ijcai. 2023/120. doi:10.24963/ijcai.2023/120

    work page doi:10.24963/ijcai 2023

  69. [74]

    Chang, J

    M.-F. Chang, J. W. Lambert, P. Sangkloy, J. Singh, S. Bak, A. Hartnett, D. Wang, P. Carr, S. Lucey, D. Ra- manan, J. Hays, Argoverse: 3d tracking and forecasting with rich maps, in: Conference on Computer Vision and Pattern Recognition (CVPR), 2019

    work page 2019

  70. [75]

    Wilson, W

    B. Wilson, W. Qi, T. Agarwal, J. Lambert, J. Singh, S. Khandelwal, B. Pan, R. Kumar, A. Hartnett, J. K. Pontes, D. Ramanan, P. Carr, J. Hays, Argoverse 2: 54 Next generation datasets for self-driving perception and forecasting, in: Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS Datasets and Benchmarks 20...

    work page 2021

  71. [77]

    Schlauch, C

    C. Schlauch, C. Wirth, N. Klein, Informed priors for knowledge integration in trajectory prediction, in: D. Koutra, C. Plant, M. Gomez Rodriguez, E. Baralis, F. Bonchi (Eds.), Machine Learning and Knowledge Dis- covery in Databases: Research Track, Springer Nature Switzerland, Cham, 2023, pp. 392–407

    work page 2023

  72. [78]

    Djuric, H

    N. Djuric, H. Cui, Z. Su, S. Wu, H. Wang, F.-C. Chou, L. S. Martin, S. Feng, R. Hu, Y . Xu, A. Dayan, S. Zhang, B. C. Becker, G. P. Meyer, C. Vallespi-Gonzalez, C. K. Wellington, Multixnet: Multiclass multistage multi- modal motion prediction, 2021 IEEE Intelligent Vehi- cles Symposium (IV) (2020) 435–442. URL:https:// api.semanticscholar.org/CorpusID:219259836

    work page 2021

  73. [79]

    J. Gao, C. Sun, H. Zhao, Y . Shen, D. Anguelov, C. Li, C. Schmid, Vectornet: Encoding hd maps and agent dy- namics from vectorized representation, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recog- nition (CVPR) (2020) 11522–11530. URL:https:// api.semanticscholar.org/CorpusID:218581144

    work page 2020

  74. [80]

    Liang, B

    M. Liang, B. Yang, R. Hu, Y . Chen, R. Liao, S. Feng, R. Urtasun, Learning lane graph representations for mo- tion forecasting, in: ECCV , 2020

    work page 2020

  75. [81]

    Z. Zhou, J. Wang, Y .-H. Li, Y .-K. Huang, Query-centric trajectory prediction, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recogni- tion, 2023, pp. 17863–17873

    work page 2023

  76. [82]

    Y . Liu, T. Yuan, Y . Wang, Y . Wang, H. Zhao, Vectormap- net: end-to-end vectorized hd map learning, in: Proceed- ings of the 40th International Conference on Machine Learning, ICML’23, JMLR.org, 2023

    work page 2023

  77. [83]

    Q. Li, Y . Wang, Y . Wang, H. Zhao, Hdmapnet: An online hd map construction and evaluation framework, 2022 International Conference on Robotics and Automa- tion (ICRA) (2021) 4628–4634. URL:https://api. semanticscholar.org/CorpusID:235829810

    work page 2022

  78. [84]

    Philion, S

    J. Philion, S. Fidler, Lift, splat, shoot: Encoding im- ages from arbitrary camera rigs by implicitly unproject- ing to 3d, in: Proceedings of the European Conference on Computer Vision, 2020

    work page 2020

  79. [85]

    In: Proceedings of the IEEE/CVF Conference on Computer 25 Vision and Pattern Recognition, pp

    T. Roddick, R. Cipolla, Predicting semantic map rep- resentations from images using pyramid occupancy net- works, in: 2020 IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition (CVPR), 2020, pp. 11135– 11144. doi:10.1109/CVPR42600.2020.01115

    work page doi:10.1109/cvpr42600.2020.01115 2020

  80. [86]

    Y . Zhou, H. Zhang, J. Yu, Y . Yang, S. Jung, S.-I. Park, B. Yoo, Himap: Hybrid representation learning for end-to-end vectorized hd map construction, in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, Los Alamitos, CA, USA, 2024, pp. 15396–15406. URL:https://doi.ieeecomputersociety. org/10.1109/CVPR5273...

    work page doi:10.1109/cvpr52733.2024.01458 2024

Showing first 80 references.