检索结果-内蒙古大学图书馆

Development and initial experiments of an intelligent dual-arm mobile robot - Baymax-I

学校读者我要写书评

暂无评论

Development and initial experiments of an intelligent dual-a...

2021 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2021

作者： Liu, Wei Wang, Haitao Wang, Rui Wen, Dayong Lu, Tao Wang, Shuo Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China University of Chinese Academy of Sciences Beijing100049 China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai200031 China

ISBN: (纸本)9781665436786

This paper addresses the design and control of an intelligent dual-arm mobile robot named Baymax-I. The mechanism design of Baymax-I is based on modular concepts, which is mainly composed of three parts, including main body, dual-arms and a mobile chassis. The main body is designed as human-like structure, carrying multiple sensors. UR3 manipulators are adopted as two arms. Each manipulator has six degrees of freedom. A two-finger grip pawl is mounted on the end of each manipulator. A MIR mobile chassis drives the Baymax-I motion with high maneuverability. As for software systems, the robot is designed based on hierarchical structure. The bottom driving layer is used to perform specific movements. The middle layer is responsible for processing sensor data. The top layer is algorithm execution layer. In the end, three experiments including SLAM, pressing the elevator and opening the fridge are presented to verify the feasibility and effectiveness of the proposed system design and control methods of the Baymax-I robot. © 2021 IEEE.

关键词： Mobile robots

Indiscriminate ssDNA cleavage activity of CRISPR-cas12a induces no detectable off-target effects in mouse embryos

学校读者我要写书评

暂无评论

Protein & Cell 2021年第9期12卷 741-745页

作者： Yu Wei Yingsi Zhou Yajing Liu Wenqin Ying Ruiming Lv Qimeng Zhao Haibo Zhou Erwei Zuo Yidi Sun Hui Yang Changyang Zhou Institute of Neuroscienee State Key Laboratory of NeuroscieneeKey Laboratory of Primate NeurobiologyCenter for Excellence in Brain Science and Intelligenee TechnologyChinese Academy of SciencesShanghai 200031China University of Chinese Academy of Sciences Beijing 100049China Shanghai Center for Brain Science and Brairvlnspired Intelligence Technology Shanghai 201210China Center for Animal Genomics Agricultural Genome Institute at ShenzhenChinese Academy of Agricultural SciencesShenzhen 518124China

Dear Editor,Newly discovered characteristics like"collateral effect"or trans-cleavage in CRISPR-cas13 and CRISPR-cas12 systems have enabled their usage in nucleic acid detection(Gootenberg et al.2017,2018;Chen et al.2018).The collateral RNA cleavage of cas13a has been reported to be harmful for cell development(Wang et al.2019;Buchman et al.2020).As a representative gene editor of CRISPR-cas12 system,CRISPR-cas12a(Cpf1)holds great potential for therapeutic applications in the future(Zetsche et al.2015;Koo et al.2018;Campa et al.2019).

关键词： al. cleavage holds

PIC 4th Challenge: Semantic-Assisted Multi-Feature Encoding and Multi-Head Decoding for Dense Video Captioning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lu, Yifan Zhang, Ziqi Chen, Yuxin Yuan, Chunfeng Li, Bing Hu, Weiming National Laboratory of Pattern Recognition Casia Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences China Cas Center for Excellence in Brain Science and Intelligence Technology China

The task of Dense Video Captioning (DVC) aims to generate captions with timestamps for multiple events in one video. Semantic information plays an important role for both localization and description of DVC. We present a semantic-assisted dense video captioning model based on an encoding-decoding framework. In the encoding stage, we design a concept detector to extract semantic information, which is then fused with multi-modal visual features to sufficiently represent the input video. In the decoding stage, we design a classification head, paralleled with the localization and captioning heads, to provide semantic supervision. Our method achieves significant improvements on the YouMakeup dataset [14] under DVC evaluation metrics and achieves high performance in the Makeup Dense Video Captioning (MDVC) task of PIC 4th Challenge. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

Tuning Synaptic Connections instead of Weights by Genetic Algorithm in Spiking Policy Network

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Duzhen Zhang, Tielin Jia, Shuncheng Wang, Qingyu Xu, Bo School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Beijing100190 China Center for Excellence in Brain Science and Intelligence Technology CAS Shanghai200031 China

Learning from interaction is the primary way that biological agents acquire knowledge about their environment and themselves. Modern deep reinforcement learning (DRL) explores a computational approach to learning from interaction and has made significant progress in solving various tasks. However, despite its power, DRL still falls short of biological agents in terms of energy efficiency. Although the underlying mechanisms are not fully understood, we believe that the integration of spiking communication between neurons and biologically-plausible synaptic plasticity plays a prominent role in achieving greater energy efficiency. Following this biological intuition, we optimized a spiking policy network (SPN) using a genetic algorithm as an energy-efficient alternative to DRL. Our SPN mimics the sensorimotor neuron pathway of insects and communicates through event-based spikes. Inspired by biological research showing that the brain forms memories by creating new synaptic connections and rewiring these connections based on new experiences, we tuned the synaptic connections instead of weights in the SPN to solve given tasks. Experimental results on several robotic control tasks demonstrate that our method can achieve the same level of performance as mainstream DRL methods while exhibiting significantly higher energy efficiency. Copyright © 2022, The Authors. All rights reserved.

关键词： Neurons

Multiscale Dynamic Graph Representation for Biometric Recognition with Occlusions

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ren, Min Wang, Yunlong Zhu, Yuhao Zhang, Kunbo Sun, Zhenan The School of Artificial Intelligence Beijing Normal University Beijing100875 China The Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China The Postgraduate Department China Academy of Railway Sciences Beijing100081 China CAS Center for Excellence in Brain Science and Intelligence Technology School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100190 China

Occlusion is a common problem with biometric recognition in the wild. The generalization ability of CNNs greatly decreases due to the adverse effects of various occlusions. To this end, we propose a novel unified framework integrating the merits of both CNNs and graph models to overcome occlusion problems in biometric recognition, called multiscale dynamic graph representation (MS-DGR). More specifically, a group of deep features reflected on certain subregions is recrafted into a feature graph (FG). Each node inside the FG is deemed to characterize a specific local region of the input sample, and the edges imply the co-occurrence of non-occluded regions. By analyzing the similarities of the node representations and measuring the topological structures stored in the adjacent matrix, the proposed framework leverages dynamic graph matching to judiciously discard the nodes corresponding to the occluded parts. The multiscale strategy is further incorporated to attain more diverse nodes representing regions of various sizes. Furthermore, the proposed framework exhibits a more illustrative and reasonable inference by showing the paired nodes. Extensive experiments demonstrate the superiority of the proposed framework, which boosts the accuracy in both natural and occlusion-simulated cases by a large margin compared with that of baseline methods. The source code is available here, or you can visit this website: https://***/RenMin1991/Dyamic-Graph-Representation Copyright © 2023, The Authors. All rights reserved.

关键词： Biometrics

Pairwise interactions in gene expression determine a hierarchical transcriptional profile in the human brain

学校读者我要写书评

暂无评论

science Bulletin 2021年第14期66卷 1437-1447,M0004页

作者： Jiaojiao Hua Zhengyi Yang Tianzi Jiang Shan Yu Brainnetome Center and National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China CAS Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of SciencesBeijing 100190China School of Future Technology University of Chinese Academy of SciencesBeijing 100049China

The orchestrated expression of thousands of genes gives rise to the complexity of the human ***,the structures governing these myriad gene-gene interactions remain *** analyzing transcription data from more than 2000 sites in six human brains,we found that pairwise interactions between genes,without considering any higher-order interactions,are sufficient to predict the transcriptional pattern of the genome for individual brain regions and the transcriptional profile of the entire brain consisting of more than 200 *** findings suggest a quadratic complexity of transcriptional patterns in the human brain,which is much simpler than *** addition,using a pairwise interaction model,we revealed that the strength of gene-gene interactions in the human brain gives rise to the nearly maximal number of transcriptional clusters,which may account for the functional and structural richness of the brain.

关键词： Gene-gene interaction Co-expression Structural network Functional network Higher-order interactions

ABUTTING GRATING ILLUSION: COGNITIVE CHALLENGE TO NEURAL NETWORK MODELS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Fan, Jinyu Zeng, Yi Research Center for Brain-Inspired Intelligence Institute of Automation Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China

Even the state-of-the-art deep learning models lack fundamental abilities compared to humans. Multiple comparison paradigms have been proposed to explore the distinctions between humans and deep learning. While most comparisons rely on corruptions inspired by mathematical transformations, very few have bases on human cognitive phenomena. In this study, we propose a novel corruption method based on the abutting grating illusion, which is a visual phenomenon widely discovered in both human and a wide range of animal species. The corruption method destroys the gradient-defined boundaries and generates the perception of illusory contours using line gratings abutting each other. We applied the method on MNIST, high resolution MNIST, and silhouette object images. Various deep learning models are tested on the corruption, including models trained from scratch and 109 models pretrained with ImageNet or various data augmentation techniques. Our results show that abutting grating corruption is challenging even for state-of-the-art deep learning models because most models are randomly guessing. We also discovered that the DeepAugment technique can greatly improve robustness against abutting grating illusion. Visualisation of early layers indicates that better performing models exhibit stronger end-stopping property, which is consistent with neuroscience discoveries. To validate the corruption method, 24 human subjects are involved to classify samples of corrupted datasets. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

Mars exploration on the move

学校读者我要写书评

暂无评论

National science Review 2020年第9期7卷 1413-1413页

作者： Mu-ming Poo CAS Center for Excellence in Brain Science and Intelligence Technology

While the world is still struggling to overcome the COVID-19 pandemic, a new round of Mars exploration proceeded as planned, catching the July–August 2020 window of Earth–Mars close proximity that occurs once every 26 months. The excitement began with United Arab Emirates’ launch of the Hope orbiter on 19 July, followed by China’s launch of the Tianwen 1(天问一号) explorer on 23 July, and NASA’s launch of the Perseverance rover on 30 July.

关键词：

Ultra-Conformal Tongue Electrode Array for Taste Perception Decoding 22

学校读者我要写书评

暂无评论

Ultra-Conformal Tongue Electrode Array for Taste Perception ...

22nd International Conference on Solid-State Sensors, Actuators and Microsystems, Transducers 2023

作者： Wang, Xiner Bai, Guo Chen, Zhaohan Liang, Jizhi Xie, Qianyang Li, Meng Wei, Xiaoling Sun, Liuyang Zhou, Zhitao Tao, Tiger H. 2020 X-Lab Shanghai Institute Of Microsystem And Information Technology Chinese Academy Of Sciences Shanghai China State Key Laboratory Of Transducer Technology Shanghai Institute Of Microsystem And Information Technology Chinese Academy Of Sciences Shanghai China School Of Graduate Study University Of Chinese Academy Of Sciences Beijing China Shanghai Ninth People's Hospital Shanghai JiaoTong University School Of Medicine Shanghai China College Of Life Sciences Shanghai Normal University Shanghai China Center Of Materials Science And Optoelectronics Engineering University Of Chinese Academy Of Sciences Beijing China Center For Excellence In Brain Science And Intelligence Technology Chinese Academy Of Sciences Shanghai China Jiangxi Nanchang China Guangdong Institute Of Intelligence Science And Technology Zhuhai Guangdong Hengqin China Tianqiao And Chrissy Chen Institute For Translational Research Shanghai China

ISBN: (纸本)9784886864352

We report a flexible, ultra-conformal tongue electrode array for taste perception decoding. We have designed and fabricated the ultra-conformal tongue electrode array, which can acquire high-quality tongue electrophysiological signals. Utilizing the electrode array on human tongues, specific electrical signals were observed to be evoked by taste stimulation. By recording whole-tongue electrical signals and electroencephalography (EEG) signals under different taste stimuli simultaneously, this system links the role of the tongue and brain in the process of tasting, which promises great potential in solving scientific puzzles regarding taste-driven sensory and assisting taste reconstruction in the future. © 2023 IEEJ.

关键词： Electrical signals detecting Taste perception decoding Tongue electrode array Ultra-conformal contact