# Deep Kinematic Models for Kinematically Feasible Vehicle Trajectory Predictions

arXiv: https://arxiv.org/abs/1908.00219 · HTML: https://mlsanity.com/paper/1908.00219/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2019.

## Built on by (most cited first, 7 of 7)

- [On Exposing the Challenging Long Tail in Future Prediction of Traffic Actors](https://mlsanity.com/paper/2103.12474/) (2021)
- [Injecting Knowledge in Data-driven Vehicle Trajectory Predictors](https://mlsanity.com/paper/2103.04854/) (2021)
- [Self-Supervised Action-Space Prediction for Automated Driving](https://mlsanity.com/paper/2109.10024/) (2021)
- [Increasing the Efficiency of Policy Learning for Autonomous Vehicles by Multi-Task Representation Learning](https://mlsanity.com/paper/2103.14718/) (2021)
- [Analyzing and Enhancing Closed-loop Stability in Reactive Simulation](https://mlsanity.com/paper/2208.04559/) (2022)
- [Fast nonlinear risk assessment for autonomous vehicles using learned conditional probabilistic models of agent futures](https://mlsanity.com/paper/2109.09975/) (2021)
- [Polynomial Trajectory Predictions for Improved Learning Performance](https://mlsanity.com/paper/2101.12616/) (2021)

## Abstract (arXiv)

Self-driving vehicles (SDVs) hold great potential for improving traffic safety and are poised to positively affect the quality of life of millions of people. To unlock this potential one of the critical aspects of the autonomous technology is understanding and predicting future movement of vehicles surrounding the SDV. This work presents a deep-learning-based method for kinematically feasible motion prediction of such traffic actors. Previous work did not explicitly encode vehicle kinematics and instead relied on the models to learn the constraints directly from the data, potentially resulting in kinematically infeasible, suboptimal trajectory predictions. To address this issue we propose a method that seamlessly combines ideas from the AI with physically grounded vehicle motion models. In this way we employ best of the both worlds, coupling powerful learning models with strong feasibility guarantees for their outputs. The proposed approach is general, being applicable to any type of learning method. Extensive experiments using deep convnets on real-world data strongly indicate its benefits, outperforming the existing state-of-the-art.