The WayHome: Long-term Motion Prediction on Dynamically Scaled
This addresses the problem of accurate long-term motion prediction for autonomous vehicles, offering incremental improvements over existing methods.
The paper tackles motion prediction for autonomous vehicles by developing a neural network-based approach that predicts heatmaps for traffic participants and uses a novel sampling algorithm to extract future positions, improving state-of-the-art miss rate performance for 3-second predictions and being competitive up to 8 seconds on the Waymo motion challenge.
One of the key challenges for autonomous vehicles is the ability to accurately predict the motion of other objects in the surrounding environment, such as pedestrians or other vehicles. In this contribution, a novel motion forecasting approach for autonomous vehicles is developed, inspired by the work of Gilles et al. [1]. We predict multiple heatmaps with a neuralnetwork-based model for every traffic participant in the vicinity of the autonomous vehicle; with one heatmap per timestep. The heatmaps are used as input to a novel sampling algorithm that extracts coordinates corresponding to the most likely future positions. We experiment with different encoders and decoders, as well as a comparison of two loss functions. Additionally, a new grid-scaling technique is introduced, showing further improved performance. Overall, our approach improves stateof-the-art miss rate performance for the function-relevant prediction interval of 3 seconds while being competitive in longer prediction intervals (up to eight seconds). The evaluation is done on the public 2022 Waymo motion challenge.