Haoxiang Ma

I'm a PhD student in Beihang University where I focus on 6-DoF Grasping and Robotic Manipulation.

Email  /  Scholar  /  Github

profile photo

Research

I'm interested in robotic learning, computer vision and embodied AI. Most of my research is about inferring the grasp poses from images and point-clouds.

Active Perception for Grasp Detection via Neural Graspness Field
Haoxiang Ma, Modi Shi, Boyang Gao, Di Huang
NeurIPS, 2024
paper

An active perception method for grasp detection by introducing the neural graspness field, which models the grasp distribution of a scene.

Generalizing 6-DoF Grasp Detection via Domain Prior Knowledge
Haoxiang Ma, Modi Shi, Boyang Gao, Di Huang
CVPR, 2024
code / paper / video

Generalizing 6-DoF grasp detection framework with domain prior knowledge of robotic grasping.

Sim-to-Real Grasp Detection with Global-to-Local RGB-D Adaptation
Haoxiang Ma, Ran Qin, Modi Shi, Boyang Gao, Di Huang
ICRA, 2024
code / paper

We present a global-to-local method to address hybrid domain gaps in RGB and depth data and insufficient multi-modal feature alignment.

Sim-to-Real Grasp Detection with Global-to-Local RGB-D Adaptation
Ran Qin, Haoxiang Ma, Boyang Gao, Di Huang
ICRA, 2023
code / paper

We build a depth guided learning framework, where both the RGB and depth images are fed and their features are combined to generate grasp proposals.

Generalizing 6-DoF Grasp Detection via Domain Prior Knowledge
Haoxiang Ma, Di Huang
CoRL, 2022
code / paper / video

Focus on the problem of feature learning in the presence of scale imbalance for 6-DoF grasp detection and propose a novel approach to especially address the difficulty in dealing with small-scale samples.

Boundary Guided Context Aggregation for Semantic Segmentation
Haoxiang Ma, Hongyu Yang, Di Huang
BMVC, 2021
code / paper

We exploit boundary as a significant guidance for context aggregation to promote the overall semantic understanding of an image.

Miscellanea

Academic Service

Reviewer of CVPR, CoRL, ICLR, NeurIPS, ICML, RA-L and etc.


Website template from Jon Barron.