Multi-modal Trajectory Prediction for Autonomous Driving with Semantic Map and Dynamic Graph Attention Network
This work addresses trajectory prediction for autonomous vehicles to improve road safety, representing an incremental advance in handling multi-class movements and social interactions.
The paper tackles the problem of predicting multi-modal trajectories for multiple types of agents in autonomous driving by proposing a dynamic graph attention network that incorporates semantic maps and social interactions, achieving state-of-the-art performance on proprietary and public datasets.
Predicting future trajectories of surrounding obstacles is a crucial task for autonomous driving cars to achieve a high degree of road safety. There are several challenges in trajectory prediction in real-world traffic scenarios, including obeying traffic rules, dealing with social interactions, handling traffic of multi-class movement, and predicting multi-modal trajectories with probability. Inspired by people's natural habit of navigating traffic with attention to their goals and surroundings, this paper presents a unique dynamic graph attention network to solve all those challenges. The network is designed to model the dynamic social interactions among agents and conform to traffic rules with a semantic map. By extending the anchor-based method to multiple types of agents, the proposed method can predict multi-modal trajectories with probabilities for multi-class movements using a single model. We validate our approach on the proprietary autonomous driving dataset for the logistic delivery scenario and two publicly available datasets. The results show that our method outperforms state-of-the-art techniques and demonstrates the potential for trajectory prediction in real-world traffic.