Zobrazeno 1 - 10
of 850
pro vyhledávání: '"Wang Hongcheng"'
MO-DDN: A Coarse-to-Fine Attribute-based Exploration Agent for Multi-object Demand-driven Navigation
The process of satisfying daily demands is a fundamental aspect of humans' daily lives. With the advancement of embodied AI, robots are increasingly capable of satisfying human demands. Demand-driven navigation (DDN) is a task in which an agent must
Externí odkaz:
http://arxiv.org/abs/2410.03488
Autor:
Grosz, Steven, Zhao, Rui, Ranjan, Rajeev, Wang, Hongcheng, Aggarwal, Manoj, Medioni, Gerard, Jain, Anil
This paper improves upon existing data pruning methods for image classification by introducing a novel pruning metric and pruning procedure based on importance sampling. The proposed pruning metric explicitly accounts for data separability, data inte
Externí odkaz:
http://arxiv.org/abs/2409.13915
Enabling robots to navigate following diverse language instructions in unexplored environments is an attractive goal for human-robot interaction. However, this goal is challenging because different navigation tasks require different strategies. The s
Externí odkaz:
http://arxiv.org/abs/2406.04882
Autor:
Wang, Fei, Lu, Kannan, Zhan, Huijuan, Ma, Lu, Wu, Feng, Sun, Hantao, Deng, Hao, Bai, Yang, Bao, Feng, Chang, Xu, Gao, Ran, Gao, Xun, Gong, Guicheng, Hu, Lijuan, Hu, Ruizi, Ji, Honghong, Ma, Xizheng, Mao, Liyong, Song, Zhijun, Tang, Chengchun, Wang, Hongcheng, Wang, Tenghui, Wang, Ziang, Xia, Tian, Xu, Hongxin, Zhan, Ze, Zhang, Gengyan, Zhou, Tao, Zhu, Mengyu, Zhu, Qingbin, Zhu, Shasha, Zhu, Xing, Shi, Yaoyun, Zhao, Hui-Hai, Deng, Chunqing
Fluxonium qubits are recognized for their high coherence times and high operation fidelities, attributed to their unique design incorporating over 100 Josephson junctions per superconducting loop. However, this complexity poses significant fabricatio
Externí odkaz:
http://arxiv.org/abs/2405.05481
In cross-domain retrieval, a model is required to identify images from the same semantic category across two visual domains. For instance, given a sketch of an object, a model needs to retrieve a real image of it from an online store's catalog. A sta
Externí odkaz:
http://arxiv.org/abs/2401.00420
The task of Visual Object Navigation (VON) involves an agent's ability to locate a particular object within a given scene. In order to successfully accomplish the VON task, two essential conditions must be fulfilled:1) the user must know the name of
Externí odkaz:
http://arxiv.org/abs/2309.08138
Autor:
Ma, Xizheng, Zhang, Gengyan, Wu, Feng, Bao, Feng, Chang, Xu, Chen, Jianjun, Deng, Hao, Gao, Ran, Gao, Xun, Hu, Lijuan, Ji, Honghong, Ku, Hsiang-Sheng, Lu, Kannan, Ma, Lu, Mao, Liyong, Song, Zhijun, Sun, Hantao, Tang, Chengchun, Wang, Fei, Wang, Hongcheng, Wang, Tenghui, Xia, Tian, Ying, Make, Zhan, Huijuan, Zhou, Tao, Zhu, Mengyu, Zhu, Qingbin, Shi, Yaoyun, Zhao, Hui-Hai, Deng, Chunqing
The fluxonium qubits have emerged as a promising platform for gate-based quantum information processing. However, their extraordinary protection against charge fluctuations comes at a cost: when coupled capacitively, the qubit-qubit interactions are
Externí odkaz:
http://arxiv.org/abs/2308.16040
Despite recent advances in video-based action recognition and robust spatio-temporal modeling, most of the proposed approaches rely on the abundance of computational resources to afford running huge and computation-intensive convolutional or transfor
Externí odkaz:
http://arxiv.org/abs/2305.07812
Autor:
Wang, Hongcheng, Wang, Yuxuan, Zhong, Fangwei, Wu, Mingdong, Zhang, Jianwei, Wang, Yizhou, Dong, Hao
Publikováno v:
The IEEE Robotics and Automation Letters 2023
Visual-audio navigation (VAN) is attracting more and more attention from the robotic community due to its broad applications, \emph{e.g.}, household robots and rescue robots. In this task, an embodied agent must search for and navigate to the sound s
Externí odkaz:
http://arxiv.org/abs/2304.10773
Autor:
Yuan, Haoqi, Zhang, Chi, Wang, Hongcheng, Xie, Feiyang, Cai, Penglin, Dong, Hao, Lu, Zongqing
We study building multi-task agents in open-world environments. Without human demonstrations, learning to accomplish long-horizon tasks in a large open-world environment with reinforcement learning (RL) is extremely inefficient. To tackle this challe
Externí odkaz:
http://arxiv.org/abs/2303.16563