mlsanityData to 7 Oct 2026

Benchmark for Models Predicting Human Behavior in Gap Acceptance Scenarios

arXiv 2211.05455 ↗First posted 10 Nov 2022cs.RO cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Autonomous vehicles currently suffer from a time-inefficient driving style caused by uncertainty about human behavior in traffic interactions. Accurate and reliable prediction models enabling more efficient trajectory planning could make autonomous vehicles more assertive in such interactions. However, the evaluation of such models is commonly oversimplistic, ignoring the asymmetric importance of prediction errors and the heterogeneity of the datasets used for testing. We examine the potential of recasting interactions between vehicles as gap acceptance scenarios and evaluating models in this structured environment. To that end, we develop a framework aiming to facilitate the evaluation of any model, by any metric, and in any scenario. We then apply this framework to state-of-the-art prediction models, which all show themselves to be unreliable in the most safety-critical situations.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 28 of its 65 references that are in the map. First posted on arXiv 10 Nov 2022.

Builds on

28 of 65 references.

References · 28

  1. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 327
  2. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 296
  3. 2018The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systemscited by 276
  4. 2019Human Motion Trajectory Prediction: A Surveycited by 231
  5. 2020The Next Decade in AI: Four Steps Towards Robust Artificial Intelligencecited by 194
  6. 2020Transformer Networks for Trajectory Forecastingcited by 180
  7. 2020VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Changecited by 101
  8. 2021LookOut: Diverse Multi-Future Prediction and Planning for Self-Drivingcited by 96
  9. 2022On Adversarial Robustness of Trajectory Prediction for Autonomous Vehiclescited by 89
  10. 2022Human Trajectory Prediction via Neural Social Physicscited by 66
  11. 2021Predicting Pedestrian Crossing Intention with Feature Fusion and Spatio-Temporal Attentioncited by 48
  12. 2022AdvDO: Realistic Adversarial Attacks for Trajectory Predictioncited by 48
16 more
  1. 2021Interpretable Social Anchors for Human Trajectory Forecasting in Crowdscited by 44
  2. 2019Graph Neural Networks for Modelling Traffic Participant Interactioncited by 42
  3. 2021Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use casescited by 39
  4. 2019Deep Learning-based Vehicle Behaviour Prediction For Autonomous Driving Applications: A Reviewcited by 31
  5. 2020Pedestrian Models for Autonomous Driving Part II: High-Level Models of Human Behaviorcited by 23
  6. 2021Injecting Planning-Awareness into Prediction and Detection Evaluationcited by 21
  7. 2021Causal-based Time Series Domain Generalization for Vehicle Intention Predictioncited by 17
  8. 2021HYPER: Learned Hybrid Trajectory Prediction via Factored Inference and Adaptive Samplingcited by 12
  9. 2021Using Graph-Theoretic Machine Learning to Predict Human Driver Behaviorcited by 12
  10. 2022Task-Relevant Failure Detection for Trajectory Predictors in Autonomous Vehiclescited by 11
  11. 2021On complementing end-to-end human behavior predictors with planningcited by 10
  12. 2021Early Lane Change Prediction for Automated Driving Systems Using Multi-Task Attention-based Convolutional Neural Networkscited by 10
  13. 2022Leveraging Smooth Attention Prior for Multi-Agent Trajectory Predictioncited by 9
  14. 2021Comparing merging behaviors observed in naturalistic data with behaviors generated by a machine learned modelcited by 3
  15. 2022Predicting highway lane-changing maneuvers: A benchmark analysis of machine and ensemble learning algorithmscited by 3
  16. 2022Beyond RMSE: Do machine-learned models of road user interaction produce human-like behavior?cited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 0; 2025: 2; 2026: 1.

5 papers.

  1. 2023Using Models Based on Cognitive Theory to Predict Human Behavior in Traffic: A Case Studycited by 5
  2. 2025Realistic Adversarial Attacks for Robustness Evaluation of Trajectory Prediction Models via Future State Perturbationcited by 3
  3. 2025STEP: Structured Training and Evaluation Platform for benchmarking trajectory prediction modelscited by 2
  4. 2023Smooth-Trajectron++: Augmenting the Trajectron++ behaviour prediction model with smooth attentioncited by 1
  5. 2026Evaluating randomized smoothing as a defense against adversarial attacks in trajectory predictioncited by 1