Haoxiao Wang
Papers
2
Total Citations
26
H-Index
2
About
Haoxiao Wang is a roboticist whose work sits at the intersection of computer vision and manipulation, tackling one of the field’s most persistent challenges: enabling robots to reliably grasp objects of arbitrary shape, material, and texture. Wang’s key contribution is the development of **RGBGrasp**, a novel framework that leverages Neural Radiance Fields (NeRF) to reconstruct 3D object geometry from standard RGB images captured during a robot arm’s natural movement. This approach elegantly sidesteps the traditional reliance on expensive, specialized point-cloud cameras or massive RGB datasets, making robust grasping more accessible and cost-effective. The flagship 2024 paper on this method has already garnered 24 citations, signaling strong interest from the community. By fusing multi-view image capture with implicit neural representations, Wang has provided a practical pathway for robots to understand and interact with their environment using only a simple camera. This work not only advances the state of the art in dexterous manipulation but also opens the door for more adaptive, vision-driven robotic systems in unstructured settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2