Lane Attention: Predicting Vehicles' Moving Trajectories by Learning Their Attention over Lanes
This work addresses trajectory prediction for autonomous driving, which is crucial for safety and efficiency, by introducing a novel non-Euclidean approach that is incremental in its method but offers strong specific gains.
The paper tackles predicting vehicle trajectories by modeling driver intention through attention mechanisms and LSTM networks, treating lanes as non-Euclidean structures with a spatio-temporal graph and Graph Neural Networks. It outperforms state-of-the-art models in several metrics, with practicability and interpretability analysis showing potential for large-scale deployment in autonomous driving systems.
Accurately forecasting the future movements of surrounding vehicles is essential for safe and efficient operations of autonomous driving cars. This task is difficult because a vehicle's moving trajectory is greatly determined by its driver's intention, which is often hard to estimate. By leveraging attention mechanisms along with long short-term memory (LSTM) networks, this work learns the relation between a driver's intention and the vehicle's changing positions relative to road infrastructures, and uses it to guide the prediction. Different from other state-of-the-art solutions, our work treats the on-road lanes as non-Euclidean structures, unfolds the vehicle's moving history to form a spatio-temporal graph, and uses methods from Graph Neural Networks to solve the problem. Not only is our approach a pioneering attempt in using non-Euclidean methods to process static environmental features around a predicted object, our model also outperforms other state-of-the-art models in several metrics. The practicability and interpretability analysis of the model shows great potential for large-scale deployment in various autonomous driving systems in addition to our own.