mlsanityData to 7 Oct 2026

Likely, Light, and Accurate Context-Free Clusters-based Trajectory Prediction

arXiv 2307.14788 ↗First posted 27 Jul 2023cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Autonomous systems in the road transportation network require intelligent mechanisms that cope with uncertainty to foresee the future. In this paper, we propose a multi-stage probabilistic approach for trajectory forecasting: trajectory transformation to displacement space, clustering of displacement time series, trajectory proposals, and ranking proposals. We introduce a new deep feature clustering method, underlying self-conditioned GAN, which copes better with distribution shifts than traditional methods. Additionally, we propose novel distance-based ranking proposals to assign probabilities to the generated trajectories that are more efficient yet accurate than an auxiliary neural network. The overall system surpasses context-free deep generative models in human and road agents trajectory data while performing similarly to point estimators when comparing the most probable trajectory.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 43 references that are in the map. First posted on arXiv 27 Jul 2023.

Builds on

23 of 43 references.

References · 23

  1. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  2. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  3. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 296
  4. 2017Soft-DTW: a Differentiable Loss Function for Time-Seriescited by 265
  5. 2019CoverNet: Multimodal Behavior Prediction using Trajectory Setscited by 259
  6. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 228
  7. 2020Transformer Networks for Trajectory Forecastingcited by 180
  8. 2021Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solutioncited by 156
  9. 2020Human Trajectory Forecasting in Crowds: A Deep Learning Perspectivecited by 128
  10. 2021Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversalscited by 112
  11. 2019What the Constant Velocity Model Can Teach Us About Pedestrian Motion Predictioncited by 78
  12. 2020Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position Estimationcited by 57
11 more
  1. 2020Diverse Image Generation via Self-Conditioned GANscited by 54
  2. 2021Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesiscited by 46
  3. 2022Non-Probability Sampling Network for Stochastic Human Trajectory Predictioncited by 46
  4. 2019TH"OR: Human-Robot Navigation Data Collection and Accurate Motion Trajectories Datasetcited by 36
  5. 2020Reciprocal Learning Networks for Human Trajectory Predictioncited by 30
  6. 2021Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertaintycited by 19
  7. 2022CSCNet: Contextual Semantic Consistency Network for Trajectory Prediction in Crowded Spacescited by 18
  8. 2020Likelihood-Based Diverse Sampling for Trajectory Forecastingcited by 16
  9. 2022Safety-compliant Generative Adversarial Networks for Human Trajectory Forecastingcited by 12
  10. 2021Pose and Semantic Map Based Probabilistic Forecast of Vulnerable Road Users' Trajectoriescited by 6
  11. 2023Diverse Probabilistic Trajectory Forecasting with Admissibility Constraintscited by 3

Built on by

Not cited yet.