# Long-term Prediction of Vehicle Behavior using Short-term Uncertainty-aware Trajectories and High-definition Maps

arXiv: https://arxiv.org/abs/2003.06143 · HTML: https://mlsanity.com/paper/2003.06143/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Mar 2020.

## Built on by (most cited first, 5 of 5)

- [Behavioral Intention Prediction in Driving Scenes: A Survey](https://mlsanity.com/paper/2211.00385/) (2022)
- [Navigating Uncertainty: The Role of Short-Term Trajectory Prediction in Autonomous Vehicle Safety](https://mlsanity.com/paper/2307.05288/) (2023)
- [Optimizing Ego Vehicle Trajectory Prediction: The Graph Enhancement Approach](https://mlsanity.com/paper/2312.13104/) (2023)
- [F1tenth Autonomous Racing With Offline Reinforcement Learning Methods](https://mlsanity.com/paper/2408.04198/) (2024)
- [Digital-Twin Losses for Lane-Compliant Trajectory Prediction at Urban Intersections](https://mlsanity.com/paper/2603.05546/) (2026)

## Abstract (arXiv)

Motion prediction of surrounding vehicles is one of the most important tasks handled by a self-driving vehicle, and represents a critical step in the autonomous system necessary to ensure safety for all the involved traffic actors. Recently a number of researchers from both academic and industrial communities have focused on this important problem, proposing ideas ranging from engineered, rule-based methods to learned approaches, shown to perform well at different prediction horizons. In particular, while for longer-term trajectories the engineered methods outperform the competing approaches, the learned methods have proven to be the best choice at short-term horizons. In this work we describe how to overcome the discrepancy between these two research directions, and propose a method that combines the disparate approaches under a single unifying framework. The resulting algorithm fuses learned, uncertainty-aware trajectories with lane-based paths in a principled manner, resulting in improved prediction accuracy at both shorter- and longer-term horizons. Experiments on real-world, large-scale data strongly suggest benefits of the proposed unified method, which outperformed the existing state-of-the-art. Moreover, following offline evaluation the proposed method was successfully tested onboard a self-driving vehicle.