LMFormer: Lane based Motion Prediction Transformer

Motion prediction plays an important role in autonomous driving. This study presents LMF ormer, a lane-aware transformer network for trajectory prediction tasks. In contrast to previous studies, our work provides a simple mechanism to dynamically prioritize the lanes and shows that such a mechanism introduces explainability into the learning behavior of the network. Additionally, LMF ormer uses the lane connection information at intersections, lane merges, and lane splits, in order to learn long-range dependency in lane structure. Moreover, we also address the issue of refining the predicted trajectories and propose an efficient method for iterative refinement through stacked transformer layers. F or benchmarking, we evaluate LMF ormer on the nuScenes dataset and demonstrate that it achieves SOTA performance across multiple metrics. Furthermore, the Deep Scenario dataset is used to not only illustrate cross-dataset network performance but also the unification capabilities of LMF ormer to train on multiple datasets and achieve better performance.