pith. machine review for the scientific record. sign in

arxiv: 2604.12857 · v1 · submitted 2026-04-14 · 💻 cs.AI · cs.RO· cs.SY· eess.SY

Recognition: no theorem link

Artificial Intelligence for Modeling and Simulation of Mixed Automated and Human Traffic

Bart van Arem, Daphne Cornelisse, Eugene Vinitsky, Saeed Rahmani, Shiva Rasouli, Simeon C. Calvert

Authors on Pith no claims yet

Pith reviewed 2026-05-10 15:57 UTC · model grok-4.3

classification 💻 cs.AI cs.ROcs.SYeess.SY
keywords mixed autonomy trafficautonomous vehiclestraffic simulationAI behavior modelingsimulation platformsagent-based modelsphysics-informed methodsevaluation metrics
0
0 comments X

The pith

AI methods for mixed autonomous and human traffic simulation can be organized into a three-family taxonomy to address limitations in existing tools.

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

The paper surveys AI techniques to model driving behaviors in simulations involving both autonomous vehicles and human drivers. It argues that current tools lack the ability to capture complex interactions because they depend on basic rule-based systems. By creating a taxonomy with agent-level models, environment-level methods, and cognitive or physics-informed approaches, the work synthesizes progress across the field. This structure also points out where simulation platforms need improvement and suggests ways to advance mixed autonomy research. The review connects perspectives from traffic engineering and computer science to fill existing knowledge gaps.

Core claim

Existing simulation tools for traffic fall short in representing the complexity of mixed automated and human driving behaviors and interactions. To address this, the survey synthesizes AI methods into three families: agent-level behavior models that focus on individual vehicle decisions, environment-level simulation methods that handle broader scene dynamics, and cognitive and physics-informed methods that incorporate human-like reasoning or physical laws. It further examines evaluation protocols, datasets, and tools while outlining steps to bridge the divide between current capabilities and research requirements.

What carries the argument

A taxonomy dividing AI methods for mixed traffic simulation into agent-level behavior models, environment-level simulation methods, and cognitive and physics-informed methods.

If this is right

  • Current simulation platforms are shown to lack sufficient realism for testing mixed autonomy systems.
  • A chronological view of methods tracks how AI approaches have evolved to handle behavior and interaction modeling.
  • Specific directions are outlined for upgrading platforms to meet the demands of mixed traffic research.
  • Standardized evaluation protocols and metrics are reviewed to assess simulation quality more consistently.
  • The synthesis encourages closer collaboration between traffic engineering and computer science communities.

Where Pith is reading between the lines

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

  • Researchers entering the field could use the taxonomy to quickly locate relevant techniques for their own simulation projects.
  • The framework may prompt creation of hybrid models that draw strengths from more than one family to boost overall accuracy.
  • Prioritizing new datasets with rich mixed-traffic recordings could directly address one of the gaps the survey identifies.
  • Similar taxonomies might be developed for adjacent areas such as pedestrian flow or multi-agent robotics simulations.

Load-bearing premise

The taxonomy comprehensively covers all relevant AI methods in the field without significant omissions based on the surveyed literature.

What would settle it

Discovery of a widely adopted simulation platform that achieves high-fidelity mixed traffic modeling using only non-AI rule-based methods would undermine the need for the proposed taxonomy.

Figures

Figures reproduced from arXiv: 2604.12857 by Bart van Arem, Daphne Cornelisse, Eugene Vinitsky, Saeed Rahmani, Shiva Rasouli, Simeon C. Calvert.

Figure 1
Figure 1. Figure 1: FIGURE 1: Survey methodology, scope, and structure [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: FIGURE 2: Taxonomy of AI methods for modeling mixed-autonomy traffic [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: FIGURE 3: Timeline of model development in driving simulation and virtual evaluation [PITH_FULL_IMAGE:figures/full_fig_p031_3.png] view at source ↗
read the original abstract

Autonomous vehicles (AVs) are now operating on public roads, which makes their testing and validation more critical than ever. Simulation offers a safe and controlled environment for evaluating AV performance in varied conditions. However, existing simulation tools mainly focus on graphical realism and rely on simple rule-based models and therefore fail to accurately represent the complexity of driving behaviors and interactions. Artificial intelligence (AI) has shown strong potential to address these limitations; however, despite the rapid progress across AI methodologies, a comprehensive survey of their application to mixed autonomy traffic simulation remains lacking. Existing surveys either focus on simulation tools without examining the AI methods behind them, or cover ego-centric decision-making without addressing the broader challenge of modeling surrounding traffic. Moreover, they do not offer a unified taxonomy of AI methods covering individual behavior modeling to full scene simulation. To address these gaps, this survey provides a structured review and synthesis of AI methods for modeling AV and human driving behavior in mixed autonomy traffic simulation. We introduce a taxonomy that organizes methods into three families: agent-level behavior models, environment-level simulation methods, and cognitive and physics-informed methods. The survey analyzes how existing simulation platforms fall short of the needs of mixed autonomy research and outlines directions to narrow this gap. It also provides a chronological overview of AI methods and reviews evaluation protocols and metrics, simulation tools, and datasets. By covering both traffic engineering and computer science perspectives, we aim to bridge the gap between these two communities.

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. The paper is a survey synthesizing AI methods for modeling and simulating mixed automated and human-driven traffic. It introduces a three-family taxonomy (agent-level behavior models, environment-level simulation methods, and cognitive/physics-informed methods), reviews shortcomings of existing simulation platforms for mixed-autonomy research, provides a chronological overview of methods, and discusses evaluation protocols, metrics, tools, and datasets while bridging traffic engineering and computer science perspectives.

Significance. If the taxonomy is coherently justified and the literature coverage representative, the survey could serve as a useful reference for AV validation research by organizing disparate methods and highlighting platform gaps that hinder realistic mixed-traffic simulation. The multi-community perspective and focus on evaluation add practical value for guiding future platform development.

major comments (2)
  1. [Taxonomy introduction] The central taxonomy claim requires clearer delineation of category boundaries; e.g., the section introducing the three families does not specify decision criteria for assigning a method that combines agent behavior with physics constraints to one family versus another, risking overlap that weakens the synthesis.
  2. [Platform analysis] The analysis of simulation platform gaps (which underpins the call for new directions) relies on the reviewed literature but does not include a systematic comparison table or subsection quantifying how many of the cited works were tested in each platform, making it difficult to assess whether the identified shortcomings are representative.
minor comments (2)
  1. [Chronological overview] The chronological overview would benefit from an explicit timeline figure or table to improve readability and allow readers to trace method evolution across the three families.
  2. [Evaluation protocols] Ensure that all evaluation metrics discussed are accompanied by at least one concrete example from the reviewed papers showing how the metric was applied in a mixed-traffic setting.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback and the recommendation for minor revision. We address each major comment below with point-by-point responses, indicating the changes we will incorporate to strengthen the manuscript.

read point-by-point responses

  1. Referee: [Taxonomy introduction] The central taxonomy claim requires clearer delineation of category boundaries; e.g., the section introducing the three families does not specify decision criteria for assigning a method that combines agent behavior with physics constraints to one family versus another, risking overlap that weakens the synthesis.

    Authors: We agree that explicit decision criteria are needed to clarify category boundaries and minimize ambiguity for hybrid approaches. In the revised manuscript, we will expand the taxonomy introduction section with a dedicated paragraph that states the primary assignment criteria: (1) the dominant modeling focus (individual agent behavior versus scene-level dynamics), (2) the core methodological emphasis (purely data-driven versus incorporation of cognitive or physics-based constraints), and (3) the primary application scope (agent-centric versus environment-centric simulation). We will also include two to three concrete examples of boundary cases, such as physics-informed agent models, and explain their placement to illustrate how overlaps are resolved. revision: yes

  2. Referee: [Platform analysis] The analysis of simulation platform gaps (which underpins the call for new directions) relies on the reviewed literature but does not include a systematic comparison table or subsection quantifying how many of the cited works were tested in each platform, making it difficult to assess whether the identified shortcomings are representative.

    Authors: We acknowledge that a quantitative summary would improve the ability to evaluate the representativeness of the platform shortcomings. In the revised version, we will add a new subsection and accompanying table that tabulates the simulation platforms employed across the reviewed works, including counts or proportions for each major platform where this information is explicitly available in the cited literature. The table will be accompanied by a brief discussion of its scope and any limitations arising from papers that do not report platform details. revision: yes

Circularity Check

0 steps flagged

No significant circularity; survey synthesizes external literature

full rationale

This paper is a literature survey that reviews and organizes existing AI methods for mixed-autonomy traffic simulation into a three-family taxonomy (agent-level, environment-level, cognitive/physics-informed). No new derivations, equations, fitted parameters, or quantitative predictions are claimed. The taxonomy is an organizing framework drawn from reviewed external works rather than a self-derived result. No self-definitional steps, fitted-input predictions, or load-bearing self-citations that reduce the central synthesis claim to unverified inputs appear. Claims rest on coverage of prior literature, which is independently checkable outside the paper.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No free parameters, axioms, or invented entities; the paper is a literature survey relying on cited external works rather than new derivations.

pith-pipeline@v0.9.0 · 5583 in / 941 out tokens · 60852 ms · 2026-05-10T15:57:50.023675+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

236 extracted references · 30 canonical work pages · 5 internal anchors

  1. [1]

    Modeling automated driving in microscopic traffic simulations for traffic performance evaluations: Aspects to consider and state of the practice

    Haneen Farah, Irene Postigo, Bahman Madadi, Matin Moarefianpour, Gerben van Beukel, Bart van Arem, and Johan Olstam. Modeling automated driving in microscopic traffic simulations for traffic performance evaluations: Aspects to consider and state of the practice. IEEE Open Journal of Intelligent Transportation Systems, 3:536–546, 2022

    2022

  2. [2]

    Gpudrive: Data-driven, multi-agent driving simulation at 1 million fps

    Saman Kazemkhani, Aarav Pandya, Daphne Cornelisse, Brennan Shacklett, and Eugene Vinitsky. Gpudrive: Data-driven, multi-agent driving simulation at 1 million fps. InInternational Conference on Learning Representations (ICLR), 2025. Poster

    2025

  3. [3]

    Microscopic traffic simulation using sumo

    Pablo Álvarez López, Michael Behrisch, Laura Bieker-Walz, Jakob Erdmann, Yun-Pang Flötteröd, Robert Hilbrich, Leonhard Lücken, Johannes Rummel, Peter Wagner, and Evamarie Wießner. Microscopic traffic simulation using sumo. In2018 21st International Conference on Intelligent Transportation Systems (ITSC), pages 2575–2582. IEEE, 2018

    2018

  4. [4]

    Ptv vissim – multimodal traffic simulation software

    PTV Group. Ptv vissim – multimodal traffic simulation software. Available at: https://www.ptvgroup.com/en-us/products/ptv-vissim

  5. [5]

    Carla: An open urban driving simulator

    Alexey Dosovitskiy, German Ros, Felipe Codevilla, Antonio Lopez, and Vladlen Koltun. Carla: An open urban driving simulator. In Conference on Robot Learning, pages 1–16. PMLR, 2017

    2017

  6. [6]

    Congested traffic states in empirical observations and microscopic simulations

    Martin Treiber, Ansgar Hennecke, and Dirk Helbing. Congested traffic states in empirical observations and microscopic simulations. Physical Review E, 62(2):1805, 2000

    2000

  7. [7]

    General lane- changing model mobil for car-following models.Transportation Research Record, 1999(1):86–94, 2007

    Arne Kesting, Martin Treiber, and Dirk Helbing. General lane- changing model mobil for car-following models.Transportation Research Record, 1999(1):86–94, 2007

    1999

  8. [8]

    Social behavior for autonomous vehicles.Proceedings of the National Academy of Sciences, 116(50):24972–24978, 2019

    Wilko Schwarting, Javier Alonso-Mora, and Daniela Rus. Social behavior for autonomous vehicles.Proceedings of the National Academy of Sciences, 116(50):24972–24978, 2019

    2019

  9. [9]

    Herbert A. Simon. A behavioral model of rational choice.The Quarterly Journal of Economics, 69(1):99–118, 1955

    1955

  10. [10]

    A language agent for au- tonomous driving

    Jiageng Mao, Junjie Ye, Yuxi Qian, Marco Pavone, and Yue Wang. A language agent for autonomous driving.arXiv preprint arXiv:2311.10813, 2023

    work page arXiv 2023

  11. [11]

    Dilu: A knowledge- driven approach to autonomous driving with large language models

    Licheng Wen, Daocheng Fu, Xin Li, Xinyu Cai, Tao Ma, Pinlong Cai, Min Dou, Botian Shi, Liang He, and Yu Qiao. Dilu: A knowledge- driven approach to autonomous driving with large language models. In International Conference on Learning Representations (ICLR), 2024

    2024

  12. [12]

    Stochastic trajectory prediction via motion indeterminacy diffusion

    Tianpei Gu, Guangyi Chen, Junlong Li, Chunze Lin, Yongming Rao, Jie Zhou, and Jiwen Lu. Stochastic trajectory prediction via motion indeterminacy diffusion. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 17113– 17122, 2022

    2022

  13. [13]

    Motiondiffuser: Controllable multi- agent motion prediction using diffusion

    Chiyu Jiang, Andre Cornman, Cheolho Park, Benjamin Sapp, Yin Zhou, and Dragomir Anguelov. Motiondiffuser: Controllable multi- agent motion prediction using diffusion. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 9644–9653, 2023

    2023

  14. [14]

    ALVINN: An autonomous land vehicle in a neural network

    Dean A Pomerleau. ALVINN: An autonomous land vehicle in a neural network. InAdvances in Neural Information Processing Systems, volume 1, 1989

    1989

  15. [15]

    End to End Learning for Self-Driving Cars

    Mariusz Bojarski, Davide Del Testa, Daniel Dworakowski, Bernhard Firner, Beat Flepp, Prasoon Goyal, Lawrence D Jackel, Mathew Monfort, Urs Muller, Jiakai Zhang, et al. End to end learning for self-driving cars.arXiv preprint arXiv:1604.07316, 2016

    work page internal anchor Pith review arXiv 2016

  16. [16]

    End-to-end driving via conditional imitation learning

    Felipe Codevilla, Matthias Müller, Antonio López, Vladlen Koltun, and Alexey Dosovitskiy. End-to-end driving via conditional imitation learning. In2018 IEEE international conference on robotics and automation (ICRA), pages 4693–4700. IEEE, 2018

    2018

  17. [17]

    37 Rios-Torres, J

    Shai Shalev-Shwartz, Shaked Shammah, and Amnon Shashua. Safe, multi-agent reinforcement learning for autonomous driving.arXiv preprint arXiv:1610.03295, 2016. VOLUME , 37 Rahmaniet al.: Artificial Intelligence for Modeling and Simulation of Mixed Automated and Human Traffic

    work page arXiv 2016

  18. [18]

    Learning to drive in a day

    Alex Kendall, Jeffrey Hawke, David Janz, Przemyslaw Mazur, Daniele Reda, John-Mark Allen, Vinh-Dieu Lam, Alex Bewley, and Amar Shah. Learning to drive in a day. In2019 International Conference on Robotics and Automation (ICRA), pages 8248–8254. IEEE, 2019

    2019

  19. [19]

    Gaia-2: A controllable multi-view generative world model for autonomous driving,

    Lloyd Russell, Anthony Hu, Lorenzo Bertoni, George Fedoseev, Jamie Shotton, Elahe Arani, and Gianluca Corrado. Gaia-2: A controllable multi-view generative world model for autonomous driving.arXiv preprint arXiv:2503.20523, 2025. Technical report

    work page arXiv 2025

  20. [20]

    Choose your simulator wisely: A review on open-source simulators for autonomous driving.IEEE Transactions on Intelligent Vehicles, 9(5):4861–4876, 2024

    Yueyuan Li, Wei Yuan, Songan Zhang, Weihao Yan, Qiyuan Shen, Chunxiang Wang, and Ming Yang. Choose your simulator wisely: A review on open-source simulators for autonomous driving.IEEE Transactions on Intelligent Vehicles, 9(5):4861–4876, 2024

    2024

  21. [21]

    Xuan Di and Rongye Shi. A survey on autonomous vehicle control in the era of mixed-autonomy: From physics-based to AI-guided driving policy learning.Transportation Research Part C: Emerging Technologies, 125:103008, 2021

    2021

  22. [22]

    Planning and decision-making for autonomous vehicles.Annual Review of Control, Robotics, and Autonomous Systems, 1(1):187–210, 2018

    Wilko Schwarting, Javier Alonso-Mora, and Daniela Rus. Planning and decision-making for autonomous vehicles.Annual Review of Control, Robotics, and Autonomous Systems, 1(1):187–210, 2018

    2018

  23. [23]

    Qi, Yin Zhou, Zoey Yang, Aurélien Chouard, Pei Sun, Jiquan Ngiam, Vijay Vasudevan, Alexander McCauley, Jonathon Shlens, and Dragomir Anguelov

    Scott Ettinger, Shuyang Cheng, Benjamin Caine, Chenxi Liu, Hang Zhao, Sabeek Pradhan, Yuning Chai, Ben Sapp, Charles R. Qi, Yin Zhou, Zoey Yang, Aurélien Chouard, Pei Sun, Jiquan Ngiam, Vijay Vasudevan, Alexander McCauley, Jonathon Shlens, and Dragomir Anguelov. Large scale interactive motion forecasting for autonomous driving: The Waymo open motion datas...

    2021

  24. [24]

    Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting

    Benjamin Wilson, William Qi, Tanmay Agarwal, John Lambert, Jagjeet Singh, Siddhesh Khandelwal, Bowen Pan, Ratnesh Kumar, Andrew Hartnett, Jhony Kaesemodel Pontes, et al. Argoverse 2: Next generation datasets for self-driving perception and forecasting.arXiv preprint arXiv:2301.00493, 2023

    work page internal anchor Pith review arXiv 2023

  25. [25]

    arXiv preprint arXiv:2106.11810 (2021) 3, 7

    Holger Caesar, Juraj Kabzan, Kok Seang Tan, Whye Kit Fong, Eric Wolff, Alex Lang, Luke Fletcher, Oscar Beijbom, and Sammy Omari. nuplan: A closed-loop ml-based planning benchmark for autonomous vehicles.arXiv preprint, 2021. arXiv:2106.11810

    work page arXiv 2021

  26. [26]

    The waymo open sim agents challenge.Advances in Neural Information Processing Systems (NeurIPS), Track on Datasets and Benchmarks,

    Nico Montali, John Lambert, Paul Mougin, Alex Kuefler, Nick Rhinehart, Michelle Li, Cole Gulino, Tristan Emrich, Zoey Yang, Shimon Whiteson, Brandyn White, and Dragomir Anguelov. The waymo open sim agents challenge.Advances in Neural Information Processing Systems (NeurIPS), Track on Datasets and Benchmarks,

  27. [27]

    A survey of deep learning applications to autonomous vehicle control.IEEE Transactions on Intelligent Transportation Systems, 22(2):712–733, 2021

    Sampo Kuutti, Richard Bowden, Yaochu Jin, Phil Barber, and Saber Fallah. A survey of deep learning applications to autonomous vehicle control.IEEE Transactions on Intelligent Transportation Systems, 22(2):712–733, 2021

    2021

  28. [28]

    A survey of deep learning techniques for autonomous driving

    Sorin Grigorescu, Bogdan Trasnea, Tiberiu Cocias, and Gigel Mace- sanu. A survey of deep learning techniques for autonomous driving. Journal of Field Robotics, 37(3):362–386, 2020

    2020

  29. [29]

    Ravi Kiran, Ibrahim Sobh, Victor Talpaert, Patrick Mannion, Ahmad A

    B. Ravi Kiran, Ibrahim Sobh, Victor Talpaert, Patrick Mannion, Ahmad A. Al Sallab, Senthil Yogamani, and Patrick Pérez. Deep reinforcement learning for autonomous driving: A survey.IEEE Transactions on Intelligent Transportation Systems, 23(6):4909–4926, 2022

    2022

  30. [30]

    End-to-end autonomous driving: Challenges and frontiers.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12):10164–10183, 2024

    Li Chen, Penghao Wu, Kashyap Chitta, Bernhard Jaeger, Andreas Geiger, and Hongyang Li. End-to-end autonomous driving: Challenges and frontiers.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12):10164–10183, 2024

    2024

  31. [31]

    Lin, and Zhigang Deng

    Qianwen Chao, Huikun Bi, Weizi Li, Tianlu Mao, Zhaoqi Wang, Ming C. Lin, and Zhigang Deng. A survey on visual traffic simulation: Models, evaluations, and applications in autonomous driving.Computer Graphics Forum, 39(1):287–308, 2020

    2020

  32. [32]

    Data- driven traffic simulation: A comprehensive review.IEEE Transactions on Intelligent Vehicles, 9(4):4730–4748, 2024

    Di Chen, Meixin Zhu, Hai Yang, Xuesong Wang, and Ye Wang. Data- driven traffic simulation: A comprehensive review.IEEE Transactions on Intelligent Vehicles, 9(4):4730–4748, 2024

    2024

  33. [33]

    A survey on safety-critical driving scenario generation— a methodological perspective.IEEE Transactions on Intelligent Transportation Systems, 24(7):6971–6988, 2023

    Wenhao Ding, Chejian Xu, Mansur Arief, Haohong Lin, Bo Li, and Ding Zhao. A survey on safety-critical driving scenario generation— a methodological perspective.IEEE Transactions on Intelligent Transportation Systems, 24(7):6971–6988, 2023

    2023

  34. [34]

    ChauffeurNet: Learning to drive by imitating the best and synthesizing the worst

    Mayank Bansal, Alex Krizhevsky, and Abhijit Ogale. ChauffeurNet: Learning to drive by imitating the best and synthesizing the worst. InRobotics: Science and Systems, 2019

    2019

  35. [35]

    Gordon, and J

    Stéphane Ross, Geoffrey J. Gordon, and J. Andrew Bagnell. A reduc- tion of imitation learning and structured prediction to no-regret online learning. InProceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (AISTATS), volume 15 of Proceedings of Machine Learning Research, pages 627–635, 2011

    2011

  36. [36]

    Multi-modal fusion transformer for end-to-end autonomous driving

    Aditya Prakash, Kashyap Chitta, and Andreas Geiger. Multi-modal fusion transformer for end-to-end autonomous driving. InIEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7077– 7087, 2021

    2021

  37. [37]

    Urban driver: Learning to drive from real-world demonstrations using policy gradients

    Oliver Scheel, Luca Bergamini, Maciej Wolczyk, Bła ˙zej Osi ´nski, and Peter Ondruska. Urban driver: Learning to drive from real-world demonstrations using policy gradients. InProceedings of the 5th Conference on Robot Learning (CoRL), volume 164 ofProceedings of Machine Learning Research, pages 718–728. PMLR, 2022

    2022

  38. [38]

    Covernet: Multimodal behavior prediction using trajectory sets

    Tung Phan-Minh, Elena Corina Grigore, Freddy A Boulton, Oscar Beijbom, and Eric M Wolff. Covernet: Multimodal behavior prediction using trajectory sets. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 14074– 14083, 2020

    2020

  39. [39]

    Multipath: Multiple probabilistic anchor trajectory hy- potheses for behavior prediction

    Yuning Chai, Benjamin Sapp, Mayank Bansal, and Dragomir Anguelov. Multipath: Multiple probabilistic anchor trajectory hy- potheses for behavior prediction. InConference on Robot Learning (CoRL), pages 86–99, 2020

    2020

  40. [40]

    Tnt: Target-driven trajectory prediction

    Hang Zhao, Jiyang Gao, Tian Lan, Chen Sun, Benjamin Sapp, Balakrishnan Varadarajan, Yue Shen, Yi Shen, Yuning Chai, Cordelia Schmid, Congcong Li, and Dragomir Anguelov. Tnt: Target-driven trajectory prediction. InConference on Robot Learning (CoRL), pages 895–904, 2021

    2021

  41. [41]

    Densetnt: End-to-end trajectory prediction from dense goal sets

    Junru Gu, Chen Sun, and Hang Zhao. Densetnt: End-to-end trajectory prediction from dense goal sets. InProceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 15283– 15292, 2021

    2021

  42. [42]

    Lapred: Lane-aware prediction of multi-modal future trajectories of dynamic agents

    ByeoungDo Kim, Seong Hyeon Park, Seokhwan Lee, Elbek Khoshimjonov, Dongsuk Kum, Junsoo Kim, Jeong Soo Kim, and Jun Won Choi. Lapred: Lane-aware prediction of multi-modal future trajectories of dynamic agents. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 14636–14645, 2021

    2021

  43. [43]

    Learning to predict vehicle trajectories with model-based planning

    Haoran Song, Di Luan, Wenchao Ding, Michael Y Wang, and Qifeng Chen. Learning to predict vehicle trajectories with model-based planning. InConference on Robot Learning, pages 1035–1045. PMLR, 2022

    2022

  44. [44]

    End-to-end urban driving by imitating a reinforcement learning coach

    Zhejun Zhang, Alexander Liniger, Dengxin Dai, Fisher Yu, and Luc Van Gool. End-to-end urban driving by imitating a reinforcement learning coach. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 15222–15232, 2021

    2021

  45. [45]

    Imitation is not enough: Robustifying imitation with reinforcement learning for challenging driving scenarios

    Eli Bronstein, Supratik Srinivasan, Sushant Paul, Aman Sinha, Matthew O’Kelly, Payam Nikdel, and Shimon Whiteson. Imitation is not enough: Robustifying imitation with reinforcement learning for challenging driving scenarios. In2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 5711–

  46. [46]

    Think2drive: Efficient reinforcement learning by thinking in latent world model for quasi-realistic autonomous driving (in carla-v2)

    Qifeng Li, Xiaosong Jia, Li Chen, Junchi Yan, Ping Luo Liu, and Hongyang Li. Think2drive: Efficient reinforcement learning by thinking in latent world model for quasi-realistic autonomous driving (in carla-v2). InEuropean Conference on Computer Vision, pages 41–57. Springer, 2024

    2024

  47. [47]

    Human as AI mentor: Enhanced human-in-the-loop reinforcement learning for safe and efficient autonomous driving.Communications in Transportation Research, 4:100127, 2024

    Zilin Huang, Zihao Sheng, Chengyuan Ma, and Sikai Chen. Human as AI mentor: Enhanced human-in-the-loop reinforcement learning for safe and efficient autonomous driving.Communications in Transportation Research, 4:100127, 2024

    2024

  48. [48]

    Maximum entropy inverse reinforcement learning

    Brian D Ziebart, Andrew L Maas, J Andrew Bagnell, and Anind K Dey. Maximum entropy inverse reinforcement learning. InAAAI Conference on Artificial Intelligence, volume 8, pages 1433–1438, 2008

    2008

  49. [49]

    Generative adversarial imitation learning.Advances in neural information processing systems, 29, 2016

    Jonathan Ho and Stefano Ermon. Generative adversarial imitation learning.Advances in neural information processing systems, 29, 2016

    2016

  50. [50]

    Imitating driver behavior with generative adversarial networks

    Alex Kuefler, Jeremy Morton, Timothy Wheeler, and Mykel Kochen- derfer. Imitating driver behavior with generative adversarial networks. In2017 IEEE Intelligent Vehicles Symposium (IV), pages 204–211. IEEE, 2017

    2017

  51. [51]

    Multi-agent imitation learning for driving simulation

    Raunak P Bhattacharyya, Derek J Phillips, Blake Wulfe, Jeremy Mor- ton, Alex Kuefler, and Mykel J Kochenderfer. Multi-agent imitation learning for driving simulation. In2018 IEEE/RSJ International 38 VOLUME , Conference on Intelligent Robots and Systems (IROS), pages 1534–

  52. [52]

    Learning robust rewards with adverserial inverse reinforcement learning

    Justin Fu, Katie Luo, and Sergey Levine. Learning robust rewards with adverserial inverse reinforcement learning. InInternational Conference on Learning Representations, 2018

    2018

  53. [53]

    Simulating emergent properties of human driving behavior using multi- agent reward augmented imitation learning

    Raunak P Bhattacharyya, Derek J Phillips, Changliu Liu, Jayesh K Gupta, Katherine Driggs-Campbell, and Mykel J Kochenderfer. Simulating emergent properties of human driving behavior using multi- agent reward augmented imitation learning. In2019 International Conference on Robotics and Automation (ICRA), pages 789–795. IEEE, 2019

    2019

  54. [54]

    End-to-end interpretable neural motion planner

    Wenyuan Zeng, Wenjie Luo, Simon Suo, Abbas Sadat, Bin Yang, Sergio Casas, and Raquel Urtasun. End-to-end interpretable neural motion planner. InIEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8660–8669, 2019

    2019

  55. [55]

    Planning- oriented autonomous driving

    Yihan Hu, Jiazhi Yang, Li Chen, Keyu Li, Chonghao Sima, Xizhou Zhu, Siqi Chai, Senyao Du, Tianwei Lin, Wenhai Wang, et al. Planning- oriented autonomous driving. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 17853– 17862, 2023

    2023

  56. [56]

    V AD: Vectorized scene representation for efficient autonomous driving

    Bo Jiang, Shaoyu Chen, Qing Xu, Bencheng Liao, Jiajie Chen, Helong Zhou, Qian Zhang, Wenyu Liu, Chang Huang, and Xinggang Wang. V AD: Vectorized scene representation for efficient autonomous driving. InIEEE/CVF International Conference on Computer Vision, pages 8340–8350, 2023

    2023

  57. [57]

    Sparsedrive: End-to-end autonomous driving via sparse scene representation

    Wenchao Sun, Xuewu Lin, Yining Shi, Chuang Zhang, Haoran Wu, and Sifa Zheng. Sparsedrive: End-to-end autonomous driving via sparse scene representation. In2025 IEEE International Conference on Robotics and Automation (ICRA), pages 8795–8801. IEEE, 2025

    2025

  58. [58]

    Safety-enhanced autonomous driving using interpretable sensor fusion transformer

    Hao Shao, Letian Wang, RuoBing Chen, Hongsheng Li, and Yu Liu. Safety-enhanced autonomous driving using interpretable sensor fusion transformer. InConference on Robot Learning, pages 726–737, 2023

    2023

  59. [59]

    Think twice before driving: Towards scalable decoders for end-to-end autonomous driving

    Xiaosong Jia, Penghao Wu, Li Chen, Jiangwei Xie, Conghui He, Junchi Yan, and Hongyang Li. Think twice before driving: Towards scalable decoders for end-to-end autonomous driving. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 21983–21994, 2023

    2023

  60. [60]

    NA VSIM: Data- driven non-reactive autonomous vehicle simulation and benchmarking

    Daniel Dauner, Marcel Hallgarten, Tianyu Li, Xinshuo Weng, Zhiyu Huang, Zetong Yang, Hongyang Li, Igor Gilitschenski, Boris Ivanovic, Marco Pavone, Andreas Geiger, and Kashyap Chitta. NA VSIM: Data- driven non-reactive autonomous vehicle simulation and benchmarking. InAdvances in Neural Information Processing Systems (NeurIPS), 2024

    2024

  61. [61]

    Recurrent world models facilitate policy evolution

    David Ha and Jürgen Schmidhuber. Recurrent world models facilitate policy evolution. InAdvances in Neural Information Processing Systems 31, pages 2451–2463. Curran Associates, Inc., 2018

    2018

  62. [62]

    Dream to control: Learning behaviors by latent imagination

    Danijar Hafner, Timothy Lillicrap, Jimmy Ba, and Mohammad Norouzi. Dream to control: Learning behaviors by latent imagination. InInternational Conference on Learning Representations (ICLR), 2020

    2020

  63. [63]

    Mastering Diverse Domains through World Models

    Danijar Hafner, Jurgis Pasukonis, Jimmy Ba, and Timothy P. Lillicrap. Mastering diverse domains through world models.arXiv preprint arXiv:2301.04104, 2023

    work page internal anchor Pith review arXiv 2023

  64. [64]

    Model-based imita- tion learning for urban driving

    Anthony Hu, Gianluca Corber, Matthias Muller, Dragomir Anguelov, Sergio Casas, Raquel Urtasun, and Alex Kendall. Model-based imita- tion learning for urban driving. InAdvances in Neural Information Processing Systems, volume 35, pages 20703–20716, 2022

    2022

  65. [65]

    Adawm: Adaptive world model based planning for autonomous driving

    Hang Wang, Xin Ye, Feng Tao, Chenbin Pan, Abhirup Mallik, Burhaneddin Yaman, Liu Ren, and Junshan Zhang. Adawm: Adaptive world model based planning for autonomous driving. InInternational Conference on Learning Representations (ICLR), 2025

    2025

  66. [66]

    Imagine-2-drive: Leveraging high-fidelity world models via multi-modal diffusion policies

    Anant Garg and K Madhava Krishna. Imagine-2-drive: Leveraging high-fidelity world models via multi-modal diffusion policies. In2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 4188–4195. IEEE, 2025

    2025

  67. [67]

    Languagempc: Large language models as deci- sion makers for autonomous driving,

    Hao Sha, Yao Mu, Yuxuan Jiang, Li Chen, Chenfeng Xu, Ping Luo, Shengbo Eben Li, Masayoshi Tomizuka, Wei Zhan, and Mingyu Ding. Languagempc: Large language models as decision makers for autonomous driving.arXiv preprint arXiv:2310.03026, 2023

    work page arXiv 2023

  68. [68]

    GPT-Driver: Learning to drive with GPT

    Jiageng Mao, Yuxi Qian, Hang Zhao, and Yue Wang. GPT-Driver: Learning to drive with GPT. InAdvances in Neural Information Processing Systems (NeurIPS), 2023

    2023

  69. [69]

    Wong, Zhenguo Li, and Hengshuang Zhao

    Zhenhua Xu, Yujia Zhang, Enze Xie, Zhen Zhao, Yong Guo, Kwan- Yee K. Wong, Zhenguo Li, and Hengshuang Zhao. DriveGPT4: Interpretable end-to-end autonomous driving via large language model. IEEE Robotics and Automation Letters, 2024

    2024

  70. [70]

    Learning by cheating

    Dian Chen, Brady Zhou, Vladlen Koltun, and Philipp Krähenbühl. Learning by cheating. InConference on Robot Learning, pages 66–75, 2020

    2020

  71. [71]

    Dart: Noise injection for robust imitation learning

    Michael Laskey, Jonathan Lee, Roy Fox, Anca Dragan, and Ken Goldberg. Dart: Noise injection for robust imitation learning. In Proceedings of the 1st Conference on Robot Learning (CoRL), volume 78 ofProceedings of Machine Learning Research, pages 143–156, 2017

    2017

  72. [72]

    Sidrane, Katherine R

    Michael Kelly, Chelsea R. Sidrane, Katherine R. Driggs-Campbell, and Mykel J. Kochenderfer. HG-DAgger: Interactive imitation learning with human experts. In2019 International Conference on Robotics and Automation (ICRA), 2019

    2019

  73. [73]

    Mega-dagger: Imitation learning with multiple imperfect experts

    Xiatao Sun, Shuo Yang, Mingyan Zhou, Kunpeng Liu, and Rahul Mangharam. Mega-dagger: Imitation learning with multiple imperfect experts. In2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), pages 1–8. IEEE, 2024

    2024

  74. [74]

    Exploring the limitations of behavior cloning for autonomous driving

    Felipe Codevilla, Eder Santana, Antonio M López, and Adrien Gaidon. Exploring the limitations of behavior cloning for autonomous driving. InIEEE/CVF International Conference on Computer Vision, pages 9329–9338, 2019

    2019

  75. [75]

    End-to-end model-free reinforcement learning for urban driving using implicit affordances

    Marin Toromanoff, Emilie Wirbel, and Fabien Moutarde. End-to-end model-free reinforcement learning for urban driving using implicit affordances. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7153–7162, 2020

    2020

  76. [76]

    Safe reinforcement learning for autonomous vehicles through parallel constrained policy optimization

    Long Wen, Junqiang Duan, Shengbo Li, Shaobing Xu, and Huei Peng. Safe reinforcement learning for autonomous vehicles through parallel constrained policy optimization. InIEEE International Conference on Intelligent Transportation Systems (ITSC), pages 1–7, 2020

    2020

  77. [77]

    Driving behavior modeling using naturalistic human driving data with inverse reinforcement learning.IEEE Transactions on Intelligent Transportation Systems, 23(8):10239–10251, 2021

    Zhiyu Huang, Jingda Wu, and Chen Lv. Driving behavior modeling using naturalistic human driving data with inverse reinforcement learning.IEEE Transactions on Intelligent Transportation Systems, 23(8):10239–10251, 2021

    2021

  78. [78]

    Decision making for autonomous driving via augmented adversarial inverse reinforcement learning

    Pin Wang, Dapeng Liu, Jiayu Chen, Hanhan Li, and Ching-Yao Chan. Decision making for autonomous driving via augmented adversarial inverse reinforcement learning. In2021 IEEE International Conference on Robotics and Automation (ICRA), pages 1036–1042. IEEE, 2021

    2021

  79. [79]

    Modeling driver behavior using adversarial inverse reinforcement learning

    Moritz Sackmann, Henrik Bey, Ulrich Hofmann, and Jörn Thielecke. Modeling driver behavior using adversarial inverse reinforcement learning. In2022 IEEE Intelligent Vehicles Symposium (IV), pages 1683–1690. IEEE, 2022

    2022

  80. [80]

    Transfuser: Imitation with transformer- based sensor fusion for autonomous driving.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023

    Kashyap Chitta, Aditya Prakash, Bernhard Jaeger, Zehao Yu, Katrin Renz, and Andreas Geiger. Transfuser: Imitation with transformer- based sensor fusion for autonomous driving.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023

    2023

Showing first 80 references.