Importance is in your attention: agent importance prediction for autonomous driving
This addresses the need for prioritizing agent interactions in autonomous driving, but it is incremental as it builds on existing attention-based models.
The paper tackled the problem of identifying which surrounding agents are most important for an autonomous vehicle's planned trajectory by using attention information from existing trajectory prediction models, and it demonstrated effectiveness in ranking agents by impact on the ego vehicle's plan on the nuPlans dataset.
Trajectory prediction is an important task in autonomous driving. State-of-the-art trajectory prediction models often use attention mechanisms to model the interaction between agents. In this paper, we show that the attention information from such models can also be used to measure the importance of each agent with respect to the ego vehicle's future planned trajectory. Our experiment results on the nuPlans dataset show that our method can effectively find and rank surrounding agents by their impact on the ego's plan.