no code implementations • 2 Oct 2022 • Yijun Cao, Xianshi Zhang, Fuya Luo, Chuan Lin, YongJie Li
To improve the PointGoal navigation accuracy without GPS signal, we use visual odometry (VO) and propose a novel action integration module (AIM) trained in unsupervised manner.
no code implementations • 22 Nov 2021 • Yijun Cao, Xianshi Zhang, Fuya Luo, Peng Peng, YongJie Li
The experiments show that the proposed system not only achieves comparable performance with other state-of-the-art self-supervised learning-based methods on the KITTI dataset, but also significantly improves the generalization capability compared with geometry-based, learning-based and hybrid VO systems on the noisy KITTI and the challenging outdoor (KAIST) scenes.
1 code implementation • 29 Apr 2021 • Fuya Luo, Yunhan Li, Guang Zeng, Peng Peng, Gang Wang, YongJie Li
Furthermore, a new metric is devised to evaluate the geometric consistency in the translation process.