Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Xu, Juzhan"'
Autor:
Shen, Xujie, Peng, Haocheng, Yang, Zesong, Xu, Juzhan, Bao, Hujun, Hu, Ruizhen, Cui, Zhaopeng
Motion Planning (MP) is a critical challenge in robotics, especially pertinent with the burgeoning interest in embodied artificial intelligence. Traditional MP methods often struggle with high-dimensional complexities. Recently neural motion planners
Externí odkaz:
http://arxiv.org/abs/2410.12805
In this paper, we introduce a novel method called FRI-Net for 2D floorplan reconstruction from 3D point cloud. Existing methods typically rely on corner regression or box regression, which lack consideration for the global shapes of rooms. To address
Externí odkaz:
http://arxiv.org/abs/2407.10687
We present a novel learning framework to solve the transport-and-packing (TAP) problem in 3D. It constitutes a full solution pipeline from partial observations of input objects via RGBD sensing and recognition to final box placement, via robotic moti
Externí odkaz:
http://arxiv.org/abs/2311.09233
We introduce NIFT, Neural Interaction Field and Template, a descriptive and robust interaction representation of object manipulations to facilitate imitation learning. Given a few object manipulation demos, NIFT guides the generation of the interacti
Externí odkaz:
http://arxiv.org/abs/2210.10992
We approach the problem of high-DOF reaching-and-grasping via learning joint planning of grasp and motion with deep reinforcement learning. To resolve the sample efficiency issue in learning the high-dimensional and complex control of dexterous grasp
Externí odkaz:
http://arxiv.org/abs/2204.13998
Publikováno v:
IEEE Transactions on Visualization and Computer Graphics 2021
We present a neural optimization model trained with reinforcement learning to solve the coordinate ordering problem for sets of star glyphs. Given a set of star glyphs associated to multiple class labels, we propose to use shape context descriptors t
Externí odkaz:
http://arxiv.org/abs/2103.02380
Publikováno v:
ACM Transactions on Graphics 2020
We introduce the transport-and-pack(TAP) problem, a frequently encountered instance of real-world packing, and develop a neural optimization solution based on reinforcement learning. Given an initial spatial configuration of boxes, we seek an efficie
Externí odkaz:
http://arxiv.org/abs/2009.01469
Publikováno v:
ACM Transactions on Graphics 37(4). August 2018
To carry out autonomous 3D scanning and online reconstruction of unknown indoor scenes, one has to find a balance between global exploration of the entire scene and local scanning of the objects within it. In this work, we propose a novel approach, w
Externí odkaz:
http://arxiv.org/abs/1805.07794
Autor:
Chen, Luanmin1 (AUTHOR), Xu, Juzhan1 (AUTHOR), Wang, Chuan1 (AUTHOR), Huang, Haibin2 (AUTHOR), Huang, Hui1 (AUTHOR), Hu, Ruizhen1 (AUTHOR) ruizhen.hu@gmail.com
Publikováno v:
Computer Graphics Forum. Oct2021, Vol. 40 Issue 7, p265-275. 11p. 4 Color Photographs, 2 Diagrams, 9 Charts.
