Diverse Probabilistic Trajectory Forecasting with Admissibility Constraints

TL;DR

This paper introduces a novel structured prediction method for diverse trajectory forecasting in autonomous driving, combining a pretrained generative model with a determinantal point process and quality constraints to improve diversity and accuracy.

Contribution

It proposes a new approach that integrates DPP-based diversity, knowledge-based quality constraints, and a gating mechanism to enhance trajectory prediction diversity and realism.

Findings

Significant improvement in trajectory diversity on nuScenes dataset

Enhanced trajectory quality with the proposed method

Better coverage of possible agent motions in predictions

Abstract

Predicting multiple trajectories for road users is important for automated driving systems: ego-vehicle motion planning indeed requires a clear view of the possible motions of the surrounding agents. However, the generative models used for multiple-trajectory forecasting suffer from a lack of diversity in their proposals. To avoid this form of collapse, we propose a novel method for structured prediction of diverse trajectories. To this end, we complement an underlying pretrained generative model with a diversity component, based on a determinantal point process (DPP). We balance and structure this diversity with the inclusion of knowledge-based quality constraints, independent from the underlying generative model. We combine these two novel components with a gating operation, ensuring that the predictions are both diverse and within the drivable area. We demonstrate on the nuScenes driving dataset the relevance of our compound approach, which yields significant improvements in the diversity and the quality of the generated trajectories.