Back to Search
Start Over
Trajectory Prediction for Autonomous Driving Using a Transformer Network
- Source :
- International Joint Conferences on Artificial Intelligence 2021 AI4AD
- Publication Year :
- 2024
-
Abstract
- Predicting the trajectories of surrounding agents is still considered one of the most challenging tasks for autonomous driving. In this paper, we introduce a multi-modal trajectory prediction framework based on the transformer network. The semantic maps of each agent are used as inputs to convolutional networks to automatically derive relevant contextual information. A novel auxiliary loss that penalizes unfeasible off-road predictions is also proposed in this study. Experiments on the Lyft l5kit dataset show that the proposed model achieves state-of-the-art performance, substantially improving the accuracy and feasibility of the prediction outcomes.
- Subjects :
- Computer Science - Robotics
Subjects
Details
- Database :
- arXiv
- Journal :
- International Joint Conferences on Artificial Intelligence 2021 AI4AD
- Publication Type :
- Report
- Accession number :
- edsarx.2402.16501
- Document Type :
- Working Paper