Remote Human Operator
Remote human operation involves controlling systems or robots from a distance, aiming to extend human capabilities and reach into inaccessible or hazardous environments. Current research emphasizes improving the efficiency and safety of remote control through advanced interfaces (e.g., virtual reality, haptic feedback), refined control algorithms (e.g., admittance control, reinforcement learning), and efficient data compression techniques (e.g., deep generative models) to handle the large data streams involved. This field is crucial for diverse applications, including surgery, construction, deep-sea exploration, and the increasingly important area of remote assistance for autonomous vehicles, improving both safety and efficiency in these domains.
Papers
Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models
Seungeun Oh, Jinhyuk Kim, Jihong Park, Seung-Woo Ko, Tony Q. S. Quek, Seong-Lyun Kim
SemStereo: Semantic-Constrained Stereo Matching Network for Remote Sensing
Chen Chen, Liangjin Zhao, Yuanchun He, Yingxuan Long, Kaiqiang Chen, Zhirui Wang, Yanfeng Hu, Xian Sun
RemoteTrimmer: Adaptive Structural Pruning for Remote Sensing Image Classification
Guanwenjie Zou, Liang Yao, Fan Liu, Chuanyi Zhang, Xin Li, Ning Chen, Shengxiang Xu, Jun Zhou
From Pixels to Prose: Advancing Multi-Modal Language Models for Remote Sensing
Xintian Sun, Benji Peng, Charles Zhang, Fei Jin, Qian Niu, Junyu Liu, Keyu Chen, Ming Li, Pohsun Feng, Ziqian Bi, Ming Liu, Yichao Zhang
DDFAV: Remote Sensing Large Vision Language Models Dataset and Evaluation Benchmark
Haodong Li, Haicheng Qu, Xiaofeng Zhang