LMFormer: Lane based Motion Prediction Transformer
Motion prediction plays an important role in autonomous driving. This study presents LMFormer, 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, LMFormer 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. For benchmarking, we evaluate LMFormer 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 LMFormer to train on multiple datasets and achieve better performance.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingBenchmarkingmotion predictionPredictionTrajectory PredictionSimilar Papers 제목 키워드 기반
ELMformer: Efficient Raw Image Restoration with a Locally Multiplicative Transformer
In order to get raw images of high quality for downstream Image Signal Process (ISP), in this paper we present an Efficient Locally Multiplicative Transformer called ELMformer for raw image restoration. ELMformer contain…
AttributeDeblurringDenoisingImage RestorationNILMFormer: Non-Intrusive Load Monitoring that Accounts for Non-Stationarity
Millions of smart meters have been deployed worldwide, collecting the total power consumed by individual households. Based on these data, electricity suppliers offer their clients energy monitoring solutions to provide f…
Non-Intrusive Load MonitoringMitigating Data Redundancy to Revitalize Transformer-based Long-Term Time Series Forecasting System
Long-term time-series forecasting (LTSF) is fundamental to various real-world applications, where Transformer-based models have become the dominant framework due to their ability to capture long-range dependencies. Howev…
Data AugmentationDecoderTime SeriesTime Series Analysis+1Temporal Triplane Transformers as Occupancy World Models
World models aim to learn or construct representations of the environment that enable the prediction of future scenes, thereby supporting intelligent motion planning. However, existing models often struggle to produce fi…
Autonomous DrivingMotion PlanningMotion-Plane-Adaptive Inter Prediction in 360-Degree Video Coding
Inter prediction is one of the key technologies enabling the high compression efficiency of modern video coding standards. 360-degree video needs to be mapped to the 2D image plane prior to coding in order to allow compr…
Prediction