Quantifying Uncertainty in Motion Prediction with Variational Bayesian Mixture
This addresses safety and robustness in autonomous vehicles by improving trajectory prediction with uncertainty quantification, though it appears incremental as it builds on existing methods.
The paper tackles the problem of predicting future trajectories for moving objects in autonomous vehicles by proposing a generative model that quantifies uncertainty and distinguishes out-of-distribution data, achieving competitive performance with metrics such as 0.446 meters minimum Final Displacement Error and 5.35% Miss Rate on the INTERACTION dataset.
Safety and robustness are crucial factors in developing trustworthy autonomous vehicles. One essential aspect of addressing these factors is to equip vehicles with the capability to predict future trajectories for all moving objects in the surroundings and quantify prediction uncertainties. In this paper, we propose the Sequential Neural Variational Agent (SeNeVA), a generative model that describes the distribution of future trajectories for a single moving object. Our approach can distinguish Out-of-Distribution data while quantifying uncertainty and achieving competitive performance compared to state-of-the-art methods on the Argoverse 2 and INTERACTION datasets. Specifically, a 0.446 meters minimum Final Displacement Error, a 0.203 meters minimum Average Displacement Error, and a 5.35% Miss Rate are achieved on the INTERACTION test set. Extensive qualitative and quantitative analysis is also provided to evaluate the proposed model. Our open-source code is available at https://github.com/PurdueDigitalTwin/seneva.