Action Sequence Predictions of Vehicles in Urban Environments using Map and Social Context
This work addresses the need for accurate vehicle action prediction in autonomous driving, though it is incremental as it builds on existing datasets and methods.
The paper tackles the problem of predicting future action sequences for vehicles in urban driving by automatically converting trajectories to action sequences using HD maps, creating a dataset of 228,000 sequences from Argoverse, and proposing a neural network that integrates position, velocity, map, and social context, resulting in improved prediction performance with dataset size and outperforming comparison models.
This work studies the problem of predicting the sequence of future actions for surround vehicles in real-world driving scenarios. To this aim, we make three main contributions. The first contribution is an automatic method to convert the trajectories recorded in real-world driving scenarios to action sequences with the help of HD maps. The method enables automatic dataset creation for this task from large-scale driving data. Our second contribution lies in applying the method to the well-known traffic agent tracking and prediction dataset Argoverse, resulting in 228,000 action sequences. Additionally, 2,245 action sequences were manually annotated for testing. The third contribution is to propose a novel action sequence prediction method by integrating past positions and velocities of the traffic agents, map information and social context into a single end-to-end trainable neural network. Our experiments prove the merit of the data creation method and the value of the created dataset - prediction performance improves consistently with the size of the dataset and shows that our action prediction method outperforms comparing models.