تقرير
RedMotion: Motion Prediction via Redundancy Reduction
العنوان: | RedMotion: Motion Prediction via Redundancy Reduction |
---|---|
المؤلفون: | Wagner, Royden, Tas, Omer Sahin, Klemp, Marvin, Fernandez, Carlos, Stiller, Christoph |
سنة النشر: | 2023 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition, Computer Science - Robotics |
الوصف: | We introduce RedMotion, a transformer model for motion prediction in self-driving vehicles that learns environment representations via redundancy reduction. Our first type of redundancy reduction is induced by an internal transformer decoder and reduces a variable-sized set of local road environment tokens, representing road graphs and agent data, to a fixed-sized global embedding. The second type of redundancy reduction is obtained by self-supervised learning and applies the redundancy reduction principle to embeddings generated from augmented views of road environments. Our experiments reveal that our representation learning approach outperforms PreTraM, Traj-MAE, and GraphDINO in a semi-supervised setting. Moreover, RedMotion achieves competitive results compared to HPTR or MTR++ in the Waymo Motion Prediction Challenge. Our open-source implementation is available at: https://github.com/kit-mrt/future-motion Comment: 17 pages, 8 figures; v2: focus on transformer model; v3: TMLR camera-ready |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2306.10840 |
رقم الأكسشن: | edsarx.2306.10840 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |