Physics Constrained Motion Prediction with Uncertainty Quantification

Renukanandan Tumu, Lars Lindemann, Truong Nghiem, Rahul Mangharam

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Predicting the motion of dynamic agents is a critical task for guaranteeing the safety of autonomous systems. A particular challenge is that motion prediction algorithms should obey dynamics constraints and quantify prediction uncertainty as a measure of confidence. We present a physics-constrained approach for motion prediction which uses a surrogate dynamical model to ensure that predicted trajectories are dynamically feasible. We propose a two-step integration consisting of intent and trajectory prediction subject to dynamics constraints. We also construct prediction regions that quantify uncertainty and are tailored for autonomous driving by using conformal prediction, a popular statistical tool. Physics Constrained Motion Prediction achieves a 41% better ADE, 56% better FDE, and 19% better IoU over a baseline in experiments using an autonomous racing dataset.

Original languageEnglish (US)
Title of host publicationIV 2023 - IEEE Intelligent Vehicles Symposium, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350346916
StatePublished - 2023
Event34th IEEE Intelligent Vehicles Symposium, IV 2023 - Anchorage, United States
Duration: Jun 4 2023Jun 7 2023

Publication series

NameIEEE Intelligent Vehicles Symposium, Proceedings


Conference34th IEEE Intelligent Vehicles Symposium, IV 2023
Country/TerritoryUnited States


  • autonomous-driving
  • conformal-prediction
  • machine-learning
  • motion-prediction
  • physics-constrained

ASJC Scopus subject areas

  • Computer Science Applications
  • Automotive Engineering
  • Modeling and Simulation


Dive into the research topics of 'Physics Constrained Motion Prediction with Uncertainty Quantification'. Together they form a unique fingerprint.

Cite this