← Search

Yizhe Wu

4 accepted papers

2024

DreamUp3D: Object-Centric Generative Models for Single-View 3D Scene Understanding and Real-to-Sim Transfer

RA-L 2024

3D scene understanding for robotic applications exhibits a unique set of requirements including real-time inference, object-centric latent representation learning, accurate 6D pose estimation and 3D reconstruction of objects. Current methods for scene understanding typically rely on a combination of

Cited by 2SourceScholar
2021

APEX: Unsupervised, Object-Centric Scene Segmentation and Tracking for Robot Manipulation

IROS 2021poster

Recent advances in unsupervised learning for object detection, segmentation, and tracking hold significant promise for applications in robotics. A common approach is to frame these tasks as inference in probabilistic latent-variable models. In this paper, however, we show that the current state-of-t…

Cited by 23SourceScholar
2021

Introspective Visuomotor Control: Exploiting Uncertainty in Deep Visuomotor Control for Failure Recovery

ICRA 2021poster

End-to-end visuomotor control is emerging as a compelling solution for robot manipulation tasks. However, imitation learning-based visuomotor control approaches tend to suffer from a common limitation, lacking the ability to recover from an out-of-distribution state caused by compounding errors. In…

Cited by 4SourceScholar