Tianyuan Yuan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Tianyuan Yuan has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
Hang Zhao
IIIS and MARS Lab, Tsinghua University, Beijing, China
1 shared publication- Hao Zhao
Tsinghua University, Beijing, China
1 shared publication - Huan-Ang Gao
Tsinghua University
1 shared publication - Pengfei Li
AiR, Tsinghua University, Beijing, China
1 shared publication - Yongliang Shi
Qiyuan Lab, Beijing, China
1 shared publication - Zhenxin Zhu
School of Automation Science and Electrical Engineering, Beihang University, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 21 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (10) , 8539-8546
P-MapNet: Far-Seeing Map Generator Enhanced by Both SDMap and HDMap Priors
Autonomous vehicles are gradually entering city roads today, with the help of high-definition maps (HDMaps). However, the reliance on HDMaps prevents autonomous vehicles from stepping into regions without this expensive digital infrastructure. This fact drives many researchers to study online HDMap generation algorithms, but the performance of these algorithms at far regions is still unsatisfying. We present P-MapNet, in which the letter P highlights the fact that we focus on incorporating map priors to improve model performance. Specifically, we exploit priors in both standard-definition map (SDMap) and HDMap. On one hand, we extract weakly aligned SDMap from OpenStreetMap and encode it as an additional conditioning branch. Despite the misalignment challenge, our attention-based architecture adaptively attends to relevant SDMap skeletons and significantly improves performance. On the other hand, we exploit a masked autoencoder to capture the prior distribution of HDMap, which can serve as a refinement module to mitigate occlusions and artifacts. We benchmark on the nuScenes and Argoverse2 datasets.
- 21 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (10) , 8539-8546
Open AccessP-MapNet: Far-Seeing Map Generator Enhanced by Both SDMap and HDMap Priors
Autonomous vehicles are gradually entering city roads today, with the help of high-definition maps (HDMaps). However, the reliance on HDMaps prevents autonomous vehicles from stepping into regions without this expensive digital infrastructure. This fact drives many researchers to study online HDMap generation algorithms, but the performance of these algorithms at far regions is still unsatisfying. We present P-MapNet, in which the letter P highlights the fact that we focus on incorporating map priors to improve model performance. Specifically, we exploit priors in both standard-definition map (SDMap) and HDMap. On one hand, we extract weakly aligned SDMap from OpenStreetMap and encode it as an additional conditioning branch. Despite the misalignment challenge, our attention-based architecture adaptively attends to relevant SDMap skeletons and significantly improves performance. On the other hand, we exploit a masked autoencoder to capture the prior distribution of HDMap, which can serve as a refinement module to mitigate occlusions and artifacts. We benchmark on the nuScenes and Argoverse2 datasets.