Towards Consistent and Explainable Motion Prediction using Heterogeneous Graph Attention
This work addresses the need for reliable and interpretable motion prediction in autonomous driving, though it appears incremental as it builds on existing methods with specific improvements.
The paper tackles the problem of predicted trajectories straying from actual lanes in autonomous driving motion prediction by introducing a refinement module that projects trajectories back onto the map, leading to more consistent predictions, and a novel scene encoder using a heterogeneous graph attention network for explainability.
In autonomous driving, accurately interpreting the movements of other road users and leveraging this knowledge to forecast future trajectories is crucial. This is typically achieved through the integration of map data and tracked trajectories of various agents. Numerous methodologies combine this information into a singular embedding for each agent, which is then utilized to predict future behavior. However, these approaches have a notable drawback in that they may lose exact location information during the encoding process. The encoding still includes general map information. However, the generation of valid and consistent trajectories is not guaranteed. This can cause the predicted trajectories to stray from the actual lanes. This paper introduces a new refinement module designed to project the predicted trajectories back onto the actual map, rectifying these discrepancies and leading towards more consistent predictions. This versatile module can be readily incorporated into a wide range of architectures. Additionally, we propose a novel scene encoder that handles all relations between agents and their environment in a single unified heterogeneous graph attention network. By analyzing the attention values on the different edges in this graph, we can gain unique insights into the neural network's inner workings leading towards a more explainable prediction.