Learning Interaction-aware Motion Prediction Model for Decision-making in Autonomous Driving

TL;DR

This paper introduces an interaction-aware motion prediction model for autonomous driving that predicts other agents' reactions based on the ego vehicle's planned actions, improving decision-making accuracy and efficiency.

Contribution

The paper presents a novel Transformer-based model that incorporates the ego vehicle's plan into predicting other agents' trajectories, along with an online learning framework for training.

Findings

Interaction-aware model outperforms non-interaction models.

Online learning improves prediction accuracy.

Decision-making surpasses reinforcement learning in efficiency and performance.

Abstract

Predicting the behaviors of other road users is crucial to safe and intelligent decision-making for autonomous vehicles (AVs). However, most motion prediction models ignore the influence of the AV's actions and the planning module has to treat other agents as unalterable moving obstacles. To address this problem, this paper proposes an interaction-aware motion prediction model that is able to predict other agents' future trajectories according to the ego agent's future plan, i.e., their reactions to the ego's actions. Specifically, we employ Transformers to effectively encode the driving scene and incorporate the AV's plan in decoding the predicted trajectories. To train the model to accurately predict the reactions of other agents, we develop an online learning framework, where the ego agent explores the environment and collects other agents' reactions to itself. We validate the decision-making and learning framework in three highly interactive simulated driving scenarios. The results reveal that our decision-making method significantly outperforms the reinforcement learning methods in terms of data efficiency and performance. We also find that using the interaction-aware model can bring better performance than the non-interaction-aware model and the exploration process helps improve the success rate in testing.