mlsanityData to 7 Oct 2026

Anomaly Detection in Multi-Agent Trajectories for Automated Driving

arXiv 2110.07922 ↗First posted 15 Oct 2021cs.RO cs.LG cs.MAcited by 15

Not on the map. Why?

Abstract (arXiv)

Human drivers can recognise fast abnormal driving situations to avoid accidents. Similar to humans, automated vehicles are supposed to perform anomaly detection. In this work, we propose the spatio-temporal graph auto-encoder for learning normal driving behaviours. Our innovation is the ability to jointly learn multiple trajectories of a dynamic number of agents. To perform anomaly detection, we first estimate a density function of the learned trajectory feature representation and then detect anomalies in low-density regions. Due to the lack of multi-agent trajectory datasets for anomaly detection in automated driving, we introduce our dataset using a driving simulator for normal and abnormal manoeuvres. Our evaluations show that our approach learns the relation between different agents and delivers promising results compared to the related works. The code, simulation and the dataset are publicly available on https://github.com/againerju/maad_highway.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 27 of its 51 references that are in the map. First posted on arXiv 15 Oct 2021.

Builds on

27 of 51 references.

References · 27

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  4. 2016OpenAI Gymcited by 1,684
  5. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  6. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  7. 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 504
  8. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  9. 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 324
  10. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  11. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 296
  12. 2017A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencodercited by 209
15 more
  1. 2019Addressing Failure Prediction by Learning Model Confidencecited by 183
  2. 2019Multiple Futures Predictioncited by 178
  3. 2020Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigmcited by 115
  4. 2019Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videoscited by 103
  5. 2019What the Constant Velocity Model Can Teach Us About Pedestrian Motion Predictioncited by 78
  6. 2020Few-shot Scene-adaptive Anomaly Detectioncited by 62
  7. 2018The EuroCity Persons Dataset: A Novel Benchmark for Object Detectioncited by 56
  8. 2018Sequence-to-Sequence Prediction of Vehicle Trajectory via LSTM Encoder-Decoder Architecturecited by 55
  9. 2020Traffic Control Gesture Recognition for Autonomous Vehiclescited by 24
  10. 2021Deep Latent Competition: Learning to Race Using Visual Control Policies in Latent Spacecited by 20
  11. 2018Robustness to Out-of-Distribution Inputs via Task-Aware Generative Uncertaintycited by 14
  12. 2019Perceptual Attention-based Predictive Controlcited by 11
  13. 2020Multi-Modal Anomaly Detection for Unstructured and Uncertain Environmentscited by 11
  14. 2019DeepLocalization: Landmark-based Self-Localization with Deep Neural Networkscited by 9
  15. 2021Dual-Modality Vehicle Anomaly Detection via Bilateral Trajectory Tracingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 3; 2024: 5; 2025: 2; 2026: 2.

15 papers.

Sort:

By area:

  1. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 66
  2. 2022Task-Relevant Failure Detection for Trajectory Predictors in Autonomous Vehiclescited by 11
  3. 2026Trajectory Guard -- A Lightweight, Sequence-Aware Model for Real-Time Anomaly Detection in Agentic AIcited by 10
  4. 2023Learning Representation for Anomaly Detection of Vehicle Trajectoriescited by 6
  5. 2024Multi-Agent Trajectory Prediction with Difficulty-Guided Feature Enhancement Networkcited by 6
  6. 2025AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Frameworkcited by 5
  7. 2022Conquering Ghosts: Relation Learning for Information Reliability Representation and End-to-End Robust Navigationcited by 3
  8. 2023Detecting Socially Abnormal Highway Driving Behaviors via Recurrent Graph Attention Networkscited by 3
  9. 2024Building Real-time Awareness of Out-of-distribution in Trajectory Prediction for Autonomous Vehiclescited by 3
  10. 2025Multi-Agent Reinforcement Learning in Intelligent Transportation Systems: A Comprehensive Surveycited by 2
  11. 2024Hybrid Video Anomaly Detection for Anomalous Scenarios in Autonomous Drivingcited by 1
  12. 2024ROAD-Waymo: A Large-Scale Action Awareness Dataset for Autonomous Drivingcited by 1
3 more
  1. 2022Asynchronous, Option-Based Multi-Agent Policy Gradient: A Conditional Reasoning Approachcited by 0
  2. 2023Infrastructure-based End-to-End Learning and Prevention of Driver Failurecited by 0
  3. 2026Forecasting the Past: Gradient-Based Distribution Shift Detection in Trajectory Predictioncited by 0