Zobrazeno 1 - 10
of 190
pro vyhledávání: '"XU, Ruinian"'
Task-oriented grasping (TOG), which refers to synthesizing grasps on an object that are configurationally compatible with the downstream manipulation task, is the first milestone towards tool manipulation. Analogous to the activation of two brain reg
Externí odkaz:
http://arxiv.org/abs/2404.10399
Deep neural networks are susceptible to generating overconfident yet erroneous predictions when presented with data beyond known concepts. This challenge underscores the importance of detecting out-of-distribution (OOD) samples in the open world. In
Externí odkaz:
http://arxiv.org/abs/2303.07543
Home-assistant robots have been a long-standing research topic, and one of the biggest challenges is searching for required objects in housing environments. Previous object-goal navigation requires the robot to search for a target object category in
Externí odkaz:
http://arxiv.org/abs/2303.06228
We propose a new 6-DoF grasp pose synthesis approach from 2D/2.5D input based on keypoints. Keypoint-based grasp detector from image input has demonstrated promising results in the previous study, where the additional visual information provided by c
Externí odkaz:
http://arxiv.org/abs/2303.05617
Great success has been achieved in the 6-DoF grasp learning from the point cloud input, yet the computational cost due to the point set orderlessness remains a concern. Alternatively, we explore the grasp generation from the RGB-D input in this paper
Externí odkaz:
http://arxiv.org/abs/2209.08752
Publikováno v:
In Catalysis Today 1 December 2024 442
Autor:
Guo, Yu, Zhang, Xinhe, Dai, Chengna, Liu, Ning, Xu, Ruinian, Wang, Ning, Chen, Biaohua, Hu, Yufeng, Zhou, Teng, Lei, Zhigang, Yu, Gangqiang
Publikováno v:
In Chemical Engineering Science 5 February 2025 302 Part A
This paper investigates robot manipulation based on human instruction with ambiguous requests. The intent is to compensate for imperfect natural language via visual observations. Early symbolic methods, based on manually defined symbols, built modula
Externí odkaz:
http://arxiv.org/abs/2202.12912
Shape informs how an object should be grasped, both in terms of where and how. As such, this paper describes a segmentation-based architecture for decomposing objects sensed with a depth camera into multiple primitive shapes, along with a post-proces
Externí odkaz:
http://arxiv.org/abs/2201.00956
Publikováno v:
In Catalysis Today 15 June 2024 436