mlsanityData to 7 Oct 2026

LOKI: Long Term and Key Intentions for Trajectory Prediction

arXiv 2108.08236 ↗First posted 18 Aug 2021cs.CV cs.AI cs.LGcited by 57

Not on the map. Why?

Abstract (arXiv)

Recent advances in trajectory prediction have shown that explicit reasoning about agents' intent is important to accurately forecast their motion. However, the current research activities are not directly applicable to intelligent and safety critical systems. This is mainly because very few public datasets are available, and they only consider pedestrian-specific intents for a short temporal horizon from a restricted egocentric view. To this end, we propose LOKI (LOng term and Key Intentions), a novel large-scale dataset that is designed to tackle joint trajectory and intention prediction for heterogeneous traffic agents (pedestrians and vehicles) in an autonomous driving setting. The LOKI dataset is created to discover several factors that may affect intention, including i) agent's own will, ii) social interactions, iii) environmental constraints, and iv) contextual information. We also propose a model that jointly performs trajectory and intention prediction, showing that recurrently reasoning about intention can assist with trajectory prediction. We show our method outperforms state-of-the-art trajectory prediction methods by upto 27% and also provide a baseline for frame-wise intention estimation.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). Builds on 30 of its 46 references that are in the map. First posted on arXiv 18 Aug 2021.

Builds on

30 of 46 references.

References · 30

  1. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  2. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  3. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  4. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  5. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 500
  6. 2020TNT: Target-driveN Trajectory Predictioncited by 345
  7. 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 324
  8. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  9. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 296
  10. 2020It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Predictioncited by 235
  11. 2019Human Motion Trajectory Prediction: A Surveycited by 231
  12. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 228
18 more
  1. 2019PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settingscited by 178
  2. 2020From Goals, Waypoints & Paths To Long Term Human Trajectory Forecastingcited by 166
  3. 2021IntentNet: Learning to Predict Intention from Raw Sensor Datacited by 158
  4. 2020Human Trajectory Forecasting in Crowds: A Deep Learning Perspectivecited by 128
  5. 2019Conditional Generative Neural System for Probabilistic Trajectory Predictioncited by 76
  6. 2020Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Planscited by 72
  7. 2020Spatiotemporal Relationship Reasoning for Pedestrian Intent Predictioncited by 71
  8. 2020TITAN: Future Forecast using Action Priorscited by 58
  9. 2017Future Person Localization in First-Person Videoscited by 57
  10. 2020Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position Estimationcited by 57
  11. 2020BiTraP: Bi-directional Pedestrian Trajectory Prediction with Multi-modal Goal Estimationcited by 47
  12. 2021RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecastingcited by 36
  13. 2020Shared Cross-Modal Trajectory Prediction for Autonomous Drivingcited by 31
  14. 2020Map-Adaptive Goal-Based Trajectory Predictioncited by 29
  15. 2019Social and Scene-Aware Trajectory Prediction in Crowded Spacescited by 19
  16. 2020Interaction-Based Trajectory Prediction Over a Hybrid Traffic Graphcited by 17
  17. 2021Physically Feasible Vehicle Trajectory Predictioncited by 8
  18. 2021Pedestrian Simulation: A Reviewcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 4; 2023: 20; 2024: 15; 2025: 10; 2026: 6.

57 papers.

Sort:

By area:

  1. 2024A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlookcited by 65
  2. 2023Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Predictioncited by 47
  3. 2021View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrumscited by 44
  4. 2022Intention-Conditioned Long-Term Human Egocentric Action Forecastingcited by 35
  5. 2022Behavioral Intention Prediction in Driving Scenes: A Surveycited by 30
  6. 2025UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Drivingcited by 27
  7. 2024CMP: Cooperative Motion Prediction with Multi-Agent Communicationcited by 25
  8. 2023Learning Cooperative Trajectory Representations for Motion Forecastingcited by 21
  9. 2023Pedestrian Trajectory Prediction in Pedestrian-Vehicle Mixed Environments: A Systematic Reviewcited by 18
  10. 2024VisionTrap: Vision-Augmented Trajectory Prediction Guided by Textual Descriptionscited by 18
  11. 2021PSI: A Benchmark for Human Interpretation and Response in Traffic Interactionscited by 17
  12. 2023Unsupervised Sampling Promoting for Stochastic Human Trajectory Predictioncited by 17
38 more
  1. 2022Forecasting Human Trajectory from Scene Historycited by 14
  2. 2023Another Vertical View: A Hierarchical Network for Heterogeneous Trajectory Prediction via Spectrumscited by 14
  3. 2023Scene Informer: Anchor-based Occlusion Inference and Trajectory Prediction in Partially Observable Environmentscited by 14
  4. 2023Pedestrian Crossing Action Recognition and Trajectory Prediction with 3D Human Keypointscited by 12
  5. 2023A Novel Benchmarking Paradigm and a Scale- and Motion-Aware Model for Egocentric Pedestrian Trajectory Predictioncited by 12
  6. 2023RiskBench: A Scenario-based Benchmark for Risk Identificationcited by 12
  7. 2022Heterogeneous Trajectory Forecasting via Risk and Scene Graph Learningcited by 11
  8. 2023Interactive Autonomous Navigation with Internal State Inference and Interactivity Estimationcited by 10
  9. 2024MATRIX: Multi-Agent Trajectory Generation with Diverse Contextscited by 9
  10. 2023Vision-based Multi-future Trajectory Prediction: A Surveycited by 8
  11. 2023CRITERIA: a New Benchmarking Paradigm for Evaluating Trajectory Prediction Models for Autonomous Drivingcited by 8
  12. 2024SoNIC: Safe Social Navigation with Adaptive Conformal Inference and Constrained Reinforcement Learningcited by 8
  13. 2024Human Action Anticipation: A Surveycited by 8
  14. 2023EqDrive: Efficient Equivariant Motion Forecasting with Multi-Modality for Autonomous Drivingcited by 7
  15. 2025CoReVLA: A Dual-Stage End-to-End Autonomous Driving Framework for Long-Tail Scenarios via Collect-and-Refinecited by 7
  16. 2023Equivariant Map and Agent Geometry for Autonomous Driving Motion Predictioncited by 6
  17. 2023Distilling Knowledge for Short-to-Long Term Trajectory Predictioncited by 5
  18. 2025Towards Generalizable Safety in Crowd Navigation via Conformal Uncertainty Handlingcited by 5
  19. 2023Trajectory-Prediction with Vision: A Surveycited by 4
  20. 2023XVTP3D: Cross-view Trajectory Prediction Using Shared 3D Queries for Autonomous Drivingcited by 4
  21. 2023Temporal DINO: A Self-supervised Video Strategy to Enhance Action Predictioncited by 3
  22. 2024Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videoscited by 3
  23. 2025Large Foundation Models for Trajectory Prediction in Autonomous Driving: A Comprehensive Surveycited by 3
  24. 2025Action Anticipation at a Glimpse: To What Extent Can Multimodal Cues Replace Video?cited by 3
  25. 2023Polar Collision Grids: Effective Interaction Modelling for Pedestrian Trajectory Prediction in Shared Space Using Collision Checkscited by 2
  26. 2023Leveraging Driver Field-of-View for Multimodal Ego-Trajectory Predictioncited by 2
  27. 2024Neural Interaction Energy for Multi-Agent Trajectory Predictioncited by 2
  28. 2025ASTRA: A Scene-aware TRAnsformer-based model for trajectory predictioncited by 2
  29. 2025INTENT: Trajectory Prediction Framework with Intention-Guided Contrastive Clusteringcited by 2
  30. 2026Understanding Multimodal Complementarity for Single-Frame Action Anticipationcited by 2
  31. 2024PreGSU-A Generalized Traffic Scene Understanding Model for Autonomous Driving based on Pre-trained Graph Attention Networkcited by 1
  32. 2024TLD: A Vehicle Tail Light signal Dataset and Benchmarkcited by 1
  33. 2024TH"OR-MAGNI Act: Actions for Human Motion Modeling in Robot-Shared Industrial Spacescited by 1
  34. 2025Casper: Inferring Diverse Intents for Assistive Teleoperation with Vision Language Modelscited by 1
  35. 2026DD-MDN: Human Trajectory Forecasting with Diffusion-Based Dual Mixture Density Networks and Uncertainty Self-Calibrationcited by 1
  36. 2026Towards Driver Behavior Understanding: Weakly-Supervised Risk Perception in Driving Scenescited by 1
  37. 2026HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detectioncited by 1
  38. 2024Vehicle Behavior Prediction by Episodic-Memory Implanted NDTcited by 0

50 most cited of 57 All 57 (JSON)