This paper addresses motion forecasting in multi-agent environments, pivotal for ensuring safety of autonomous vehicles. Traditional and recent data-driven marginal trajectory prediction methods struggle to properly learn non-linear agent-to-agent interactions. We present SSL-Interactions that proposes pretext tasks to enhance interaction modeling for trajectory prediction. We introduce four interaction-aware pretext tasks to encapsulate various aspects of agent interactions: range gap prediction, closest distance prediction, direction of movement prediction, and type of interaction prediction. We further propose an approach to curate interaction-heavy scenarios from datasets. This curated data has two advantages: it provides a stronger learning signal to the interaction model, and facilitates generation of pseudo-labels for interaction-centric pretext tasks. We also propose three new metrics specifically designed to evaluate predictions in interactive scenes. Our empirical evaluations indicate SSL-Interactions outperforms state-of-the-art motion forecasting methods quantitatively with up to 8% improvement, and qualitatively, for interaction-heavy scenarios.
SSL-Interactions: Pretext Tasks for Interactive Trajectory Prediction
2024 IEEE Intelligent Vehicles Symposium (IV) ; 1450-1457
2024-06-02
2313906 byte
Conference paper
Electronic Resource
English
Quality circles - waymark or pretext
Automotive engineering | 1987
|Adjacent vehicle interactive trajectory prediction method
European Patent Office | 2023
|INTERACTIVE OBJECT TRAJECTORY PREDICTION SYSTEMS AND METHODS
European Patent Office | 2024
|Learning Interactive Knowledge Graph for Trajectory Prediction
British Library Conference Proceedings | 2022
|Learning Interactive Knowledge Graph for Trajectory Prediction
Springer Verlag | 2022
|