mlsanityData to 14 Oct 2026

Motion Prediction Performance Analysis for Autonomous Driving Systems and the Effects of Tracking Noise

arXiv 2104.08368 ↗First posted 16 Apr 2021cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Autonomous driving consists of a multitude of interacting modules, where each module must contend with errors from the others. Typically, the motion prediction module depends upon a robust tracking system to capture each agent's past movement. In this work, we systematically explore the importance of the tracking module for the motion prediction task and ultimately conclude that the overall motion prediction performance is highly sensitive to the tracking module's imperfections. We explicitly compare models that use tracking information to models that do not across multiple scenarios and conditions. We find that the tracking information plays an essential role and improves motion prediction performance in noise-free conditions. However, in the presence of tracking noise, it can potentially affect the overall performance if not studied thoroughly. We thus argue practitioners should be mindful of noise when developing and testing motion/tracking modules, or that they should consider tracking free alternatives.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 42 references that are in the map. First posted on arXiv 16 Apr 2021.

Builds on

32 of 42 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  5. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 690
  6. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 530
  7. 2019MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Predictioncited by 420
  8. 2019A Survey of Autonomous Driving: Common Practices and Emerging Technologiescited by 379
  9. 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 325
  10. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  11. 2018Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networkscited by 289
  12. 2019Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relationscited by 247
20 more
  1. 2020One Thousand and One Hours: Self-driving Motion Prediction Datasetcited by 240
  2. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 229
  3. 2020Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Netcited by 228
  4. 2020Transformer Networks for Trajectory Forecastingcited by 181
  5. 2019PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settingscited by 179
  6. 2021IntentNet: Learning to Predict Intention from Raw Sensor Datacited by 158
  7. 2020Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representationscited by 153
  8. 2020PnPNet: End-to-End Perception and Prediction with Tracking in the Loopcited by 144
  9. 2019Multi-Agent Tensor Fusion for Contextual Trajectory Predictioncited by 131
  10. 2018Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Drivingcited by 90
  11. 2019Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidthcited by 89
  12. 2018TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactionscited by 82
  13. 2020Probabilistic 3D Multi-Object Tracking for Autonomous Drivingcited by 64
  14. 2015Learning Visual Predictive Models of Physics for Playing Billiardscited by 58
  15. 2020Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Datacited by 58
  16. 2021DEFT: Detection Embeddings for Trackingcited by 56
  17. 2020MultiXNet: Multiclass Multistage Multimodal Motion Predictioncited by 31
  18. 2019Looking Ahead: Anticipating Pedestrians Crossing with Future Frames Predictioncited by 25
  19. 2020Deep Learning for Vision-based Prediction: A Surveycited by 19
  20. 2019Predicting Motion of Vulnerable Road Users using High-Definition Maps and Efficient ConvNetscited by 16

Built on by

Not cited yet.