Decision‐making in unmanned combat aerial vehicles (UCAVs) presents a multifaceted challenge because of the complexity and dynamics of the flight environment, which leads to hurdles in training convergence, low decision validity, and the dimensionality catastrophe for decision‐making neural networks. A novel framework is proposed to address breaking down the complicated decision issues, which combines the strengths of graph convolutional networks in relation extraction with the ability of hierarchical reinforcement learning. To solve the problem of decision validity under high‐dimensional inputs, the joint framework is applied to the Maneuver Intent's decision, and a maneuver library‐based state space design method is suggested. The joint framework executes adaptable strategies and flight maneuvers to address the issue of training non‐convergence or task failure due to difficult‐to‐obtain reward signals across various scenarios. Then, the recurrent curriculum training and cross‐entropy rewards are designed to train decisions on different sub‐strategies. The experimental evaluation demonstrated more flexibility and adaptability in decision‐making problems under complex tasks compared to rule‐based and reinforcement learning baseline methods. The method proposed in this article provides a novel approach to resolving intricate decision problems, and which has certain theoretical significance and reference value for engineering applications.
{"title":"Joint Situational Assessment‐Hierarchical Decision‐Making Framework for Maneuver Intent Decisions","authors":"Ruihai Chen, Hao Li, Guanwei Yan, Haojie Peng, Qian Zhang","doi":"10.1002/aisy.202300574","DOIUrl":"https://doi.org/10.1002/aisy.202300574","url":null,"abstract":"Decision‐making in unmanned combat aerial vehicles (UCAVs) presents a multifaceted challenge because of the complexity and dynamics of the flight environment, which leads to hurdles in training convergence, low decision validity, and the dimensionality catastrophe for decision‐making neural networks. A novel framework is proposed to address breaking down the complicated decision issues, which combines the strengths of graph convolutional networks in relation extraction with the ability of hierarchical reinforcement learning. To solve the problem of decision validity under high‐dimensional inputs, the joint framework is applied to the Maneuver Intent's decision, and a maneuver library‐based state space design method is suggested. The joint framework executes adaptable strategies and flight maneuvers to address the issue of training non‐convergence or task failure due to difficult‐to‐obtain reward signals across various scenarios. Then, the recurrent curriculum training and cross‐entropy rewards are designed to train decisions on different sub‐strategies. The experimental evaluation demonstrated more flexibility and adaptability in decision‐making problems under complex tasks compared to rule‐based and reinforcement learning baseline methods. The method proposed in this article provides a novel approach to resolving intricate decision problems, and which has certain theoretical significance and reference value for engineering applications.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"103 13","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140678886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Geonwoo Hwang, Jongseok Nam, Minki Kim, David Santiago Diaz Cortes, Ki-Uk Kyung
Human–robot collaboration (HRC) is effective to improve productivity in industrial fields, based on the robot's fast and precise work and the human's flexible skill. To facilitate the HRC system, the first priority is to ensure safety in the event of accidents, such as collisions between robots and humans. Therefore, a protective and collision-sensitive robot skin, named Gel-Skin is proposed to guarantee the safety in HRC. The Gel-Skin is composed of polyvinyl chloride (PVC) gel, which is a functional material with piezoresistive characteristics and impact absorption capability. In particular, the PVC gel has a distinctive piezoresistive property that the relation between mechanical pressure and electrical resistance is tunable depending on an applied voltage. When a voltage is applied to the PVC gel, the electrical charges are accumulated around the anode and it shows increased piezoresistive sensitivity. In this study, it is verified for the PVC gel to exhibit the 4.78 times higher sensitivity by simply applying a voltage. This novel physical phenomenon enables the Gel-Skin to detect the collision rapidly. Finally, the Gel-Skin is applicated to a real robot system and it is verified that the Gel-Skin can detect a collision and absorb impact to ensure safety.
{"title":"Protective and Collision-Sensitive Gel-Skin: Visco-Elastomeric Polyvinyl Chloride Gel Rapidly Detects Robot Collision by Breaking Electrical Charge Accumulation Stability","authors":"Geonwoo Hwang, Jongseok Nam, Minki Kim, David Santiago Diaz Cortes, Ki-Uk Kyung","doi":"10.1002/aisy.202300583","DOIUrl":"https://doi.org/10.1002/aisy.202300583","url":null,"abstract":"Human–robot collaboration (HRC) is effective to improve productivity in industrial fields, based on the robot's fast and precise work and the human's flexible skill. To facilitate the HRC system, the first priority is to ensure safety in the event of accidents, such as collisions between robots and humans. Therefore, a protective and collision-sensitive robot skin, named Gel-Skin is proposed to guarantee the safety in HRC. The Gel-Skin is composed of polyvinyl chloride (PVC) gel, which is a functional material with piezoresistive characteristics and impact absorption capability. In particular, the PVC gel has a distinctive piezoresistive property that the relation between mechanical pressure and electrical resistance is tunable depending on an applied voltage. When a voltage is applied to the PVC gel, the electrical charges are accumulated around the anode and it shows increased piezoresistive sensitivity. In this study, it is verified for the PVC gel to exhibit the 4.78 times higher sensitivity by simply applying a voltage. This novel physical phenomenon enables the Gel-Skin to detect the collision rapidly. Finally, the Gel-Skin is applicated to a real robot system and it is verified that the Gel-Skin can detect a collision and absorb impact to ensure safety.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"20 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140569526","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jieun Park, Minho Kim, Jinhyung Park, Myungrae Hong, Sunghoon Im, Damin Choi, Eunyoung Kim, Dohyeon Gong, Seokhaeng Huh, Seung-Un Jo, ChangHwan Kim, Je-Sung Koh, Seungyong Han, Daeshik Kang
Rat whiskers are an exceptional sensing system, extracting information from their surrounding environment. Inspired by this concept, active whisker sensors measure various physical and geometric properties through contact with objects. However, previous research has focused on measuring the object geometry, often overlooking the potential for broader applications of the sensors. Herein, an active whisker sensor that enables simple measurement of the surface properties such as surface hardness and adhesiveness is reported. Composed of motor-, wire-, and crack-based mechanosensor, the active whisker sensor implements a tapping process inspired by the movement of a rat's whiskers to quickly evaluate the object surface. One area of potential application is the food industry. The active whisker sensors offer a new approach to measuring surface properties of viscoelastic and inelastic food that are difficult to measure with traditional bulky systems. Herein, it is validated that the tapping process can be used to measure the surface properties of a various foods. With the aid of machine learning algorithms, sensor can also recognize differences in the surface properties of bananas at different ripeness stages and classify them with 99% accuracy. In this report, the possibilities for applications of active whisker sensors, including food industry, robotics, and medical devices, are opened up.
{"title":"Active Whisker-Inspired Food Material Surface Property Measurement Using Deep-Learned Mechanosensor","authors":"Jieun Park, Minho Kim, Jinhyung Park, Myungrae Hong, Sunghoon Im, Damin Choi, Eunyoung Kim, Dohyeon Gong, Seokhaeng Huh, Seung-Un Jo, ChangHwan Kim, Je-Sung Koh, Seungyong Han, Daeshik Kang","doi":"10.1002/aisy.202300660","DOIUrl":"https://doi.org/10.1002/aisy.202300660","url":null,"abstract":"Rat whiskers are an exceptional sensing system, extracting information from their surrounding environment. Inspired by this concept, active whisker sensors measure various physical and geometric properties through contact with objects. However, previous research has focused on measuring the object geometry, often overlooking the potential for broader applications of the sensors. Herein, an active whisker sensor that enables simple measurement of the surface properties such as surface hardness and adhesiveness is reported. Composed of motor-, wire-, and crack-based mechanosensor, the active whisker sensor implements a tapping process inspired by the movement of a rat's whiskers to quickly evaluate the object surface. One area of potential application is the food industry. The active whisker sensors offer a new approach to measuring surface properties of viscoelastic and inelastic food that are difficult to measure with traditional bulky systems. Herein, it is validated that the tapping process can be used to measure the surface properties of a various foods. With the aid of machine learning algorithms, sensor can also recognize differences in the surface properties of bananas at different ripeness stages and classify them with 99% accuracy. In this report, the possibilities for applications of active whisker sensors, including food industry, robotics, and medical devices, are opened up.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"64 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139760053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ngoc Hung Phi, Huu Nguyen Bui, Seong-Yoen Moon, Jong‐Wook Lee
Nonreciprocity plays a fundamental role in governing direction‐dependent asymmetric wave propagation. Previous approaches to nonreciprocity involve ferrite‐based devices with bulky systems. Herein, the controlled synthesis of a space–time modulation (STM) metamaterial for enhanced nonreciprocity using machine learning (ML) is investigated. The design of STM metamaterial poses great challenges due to the nonlinear nature of time‐periodic Floquet harmonics, which are inefficiently handled in traditional methods such as numerical optimization. To deal with the challenge, an ML approach is proposed that learns from the accumulated training data using the guided objective function and generates high‐quality designs by leveraging the learned features. This approach first trains a residual neural network (ResNet) to learn the nonlinear relationships between the STM parameters and nonreciprocal responses. The trained ResNet achieves a high testing accuracy, with 96.7% of the 9000 instances having a mean square error less than 0.6 × 10−4. For the synthesis of STM metamaterial, a customized Wasserstein generative adversarial network (WGAN) is proposed, which leverages the discovered nonlinearity and synthesizes large‐scale datasets using small computational costs. The histogram obtained using 90 000 data samples shows that WGAN generates designs with an average normalized nonreciprocity of 0.83, four times higher than the measured data.
{"title":"Controlled Synthesis of Space–Time Modulated Metamaterial for Enhanced Nonreciprocity by Machine Learning","authors":"Ngoc Hung Phi, Huu Nguyen Bui, Seong-Yoen Moon, Jong‐Wook Lee","doi":"10.1002/aisy.202300565","DOIUrl":"https://doi.org/10.1002/aisy.202300565","url":null,"abstract":"Nonreciprocity plays a fundamental role in governing direction‐dependent asymmetric wave propagation. Previous approaches to nonreciprocity involve ferrite‐based devices with bulky systems. Herein, the controlled synthesis of a space–time modulation (STM) metamaterial for enhanced nonreciprocity using machine learning (ML) is investigated. The design of STM metamaterial poses great challenges due to the nonlinear nature of time‐periodic Floquet harmonics, which are inefficiently handled in traditional methods such as numerical optimization. To deal with the challenge, an ML approach is proposed that learns from the accumulated training data using the guided objective function and generates high‐quality designs by leveraging the learned features. This approach first trains a residual neural network (ResNet) to learn the nonlinear relationships between the STM parameters and nonreciprocal responses. The trained ResNet achieves a high testing accuracy, with 96.7% of the 9000 instances having a mean square error less than 0.6 × 10−4. For the synthesis of STM metamaterial, a customized Wasserstein generative adversarial network (WGAN) is proposed, which leverages the discovered nonlinearity and synthesizes large‐scale datasets using small computational costs. The histogram obtained using 90 000 data samples shows that WGAN generates designs with an average normalized nonreciprocity of 0.83, four times higher than the measured data.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"21 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139861213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jungmin Hamm, Seonghyeon Lim, Jiae Park, Jiwon Kang, Injun Lee, Yoongeun Lee, Jiseok Kang, Youngjun Jo, Jaejin Lee, Seoyeong Lee, M. C. Ratri, A. I. Brilian, Seungyeon Lee, Seokhwan Jeong, Kwanwoo Shin
Robotic arms are now commonplace in diverse settings and are poised to play a crucial role in automating laboratory tasks. However, biological experiments remain challenging for automation due to their dependence on human factors, such as researchers’ skills and experience. This article introduces robotic automation and remote control for both general and biological research tasks through a modularized platform comprising a robotic arm, auxiliary tools, and software. This platform facilitates fully automated or remote execution of key experiments in chemistry and biology, including liquid handling, mixing, cell seeding, culturing, and genetic manipulation. The robot interfaces seamlessly with standard laboratory equipment and operates remotely in real time through an online program. Integration of a vision system via robotic arm webcams ensures precise positioning and object localization, enhancing accuracy. This modularized robotic platform signifies a substantial advancement in lab automation, promising enhanced efficiency, reproducibility, and scientific progress compared to human‐led experiments.
{"title":"A Modular Robotic Platform for Biological Research: Cell Culture Automation and Remote Experimentation","authors":"Jungmin Hamm, Seonghyeon Lim, Jiae Park, Jiwon Kang, Injun Lee, Yoongeun Lee, Jiseok Kang, Youngjun Jo, Jaejin Lee, Seoyeong Lee, M. C. Ratri, A. I. Brilian, Seungyeon Lee, Seokhwan Jeong, Kwanwoo Shin","doi":"10.1002/aisy.202300566","DOIUrl":"https://doi.org/10.1002/aisy.202300566","url":null,"abstract":"Robotic arms are now commonplace in diverse settings and are poised to play a crucial role in automating laboratory tasks. However, biological experiments remain challenging for automation due to their dependence on human factors, such as researchers’ skills and experience. This article introduces robotic automation and remote control for both general and biological research tasks through a modularized platform comprising a robotic arm, auxiliary tools, and software. This platform facilitates fully automated or remote execution of key experiments in chemistry and biology, including liquid handling, mixing, cell seeding, culturing, and genetic manipulation. The robot interfaces seamlessly with standard laboratory equipment and operates remotely in real time through an online program. Integration of a vision system via robotic arm webcams ensures precise positioning and object localization, enhancing accuracy. This modularized robotic platform signifies a substantial advancement in lab automation, promising enhanced efficiency, reproducibility, and scientific progress compared to human‐led experiments.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"16 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139814864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Brittan T. Wilcox, John Joyce, Michael D. Bartlett
Biological organisms are extraordinary in their ability to change physical form to perform different functions. Mimicking these capabilities in engineered systems has the potential to create multifunctional robots that adapt form and function on-demand for search and rescue, environmental monitoring, and transportation. Organisms are able to navigate such unstructured environments with the ability to rapidly change shape, move swiftly in multiple locomotion modes, and do this efficiently and reversibly without external power sources, feats which are difficult for robots. Herein, a bio-inspired latch-mediated, spring-actuated (LaMSA) morphing mechanism is harnessed to near-instantaneously and reversibly reconfigure a multifunctional robot to achieve driving and flying configurations. This shape change coupled with a combined propeller/wheel leverages the same motors and electronics for both flying and driving, providing efficiency of morphing and locomotion for completely untethered operation. The adaptive robotic vehicle can move through confined spaces and rough terrain which are difficult to pass by driving or flying alone, and expands the potential range through power savings in the driving mode. This work provides a powerful scheme for LaMSA in robots, in which controlled, small-scale LaMSA systems can be integrated as individual components to robots of all sizes to enable new functionalities and enhance performance.
{"title":"Rapid and Reversible Morphing to Enable Multifunctionality in Robots","authors":"Brittan T. Wilcox, John Joyce, Michael D. Bartlett","doi":"10.1002/aisy.202300694","DOIUrl":"https://doi.org/10.1002/aisy.202300694","url":null,"abstract":"Biological organisms are extraordinary in their ability to change physical form to perform different functions. Mimicking these capabilities in engineered systems has the potential to create multifunctional robots that adapt form and function on-demand for search and rescue, environmental monitoring, and transportation. Organisms are able to navigate such unstructured environments with the ability to rapidly change shape, move swiftly in multiple locomotion modes, and do this efficiently and reversibly without external power sources, feats which are difficult for robots. Herein, a bio-inspired latch-mediated, spring-actuated (LaMSA) morphing mechanism is harnessed to near-instantaneously and reversibly reconfigure a multifunctional robot to achieve driving and flying configurations. This shape change coupled with a combined propeller/wheel leverages the same motors and electronics for both flying and driving, providing efficiency of morphing and locomotion for completely untethered operation. The adaptive robotic vehicle can move through confined spaces and rough terrain which are difficult to pass by driving or flying alone, and expands the potential range through power savings in the driving mode. This work provides a powerful scheme for LaMSA in robots, in which controlled, small-scale LaMSA systems can be integrated as individual components to robots of all sizes to enable new functionalities and enhance performance.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"26 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139558178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mobile robots have revolutionized the public and private sectors for transportation, exploration, and search and rescue. Efficient energy consumption and robust environmental interaction needed for complex tasks can be achieved in aerial–terrestrial robots by combining advantages of each locomotion mode. This review surveys over two decades of development in multimodal robots that move on the ground and in air. Multimodality can be achieved by leveraging three main design approaches: adding morphological features, adapting forms for locomotion transitions, and integrating multiple vehicle platforms. Each classification is thoroughly examined and synthesized, encompassing both qualitative and quantitative aspects. The authors delved into the intricacies of these approaches and explored the challenges and opportunities that lie ahead in pursuit of the next generation of mobile robots. This review aims to advance future deployment of multimodal robots in the real world for challenging operations in dangerous, unstructured, contact-prone, cluttered and subterranean environments.
{"title":"Multimodal Locomotion: Next Generation Aerial–Terrestrial Mobile Robotics","authors":"Jane Pauline Ramirez, Salua Hamaza","doi":"10.1002/aisy.202300327","DOIUrl":"https://doi.org/10.1002/aisy.202300327","url":null,"abstract":"Mobile robots have revolutionized the public and private sectors for transportation, exploration, and search and rescue. Efficient energy consumption and robust environmental interaction needed for complex tasks can be achieved in aerial–terrestrial robots by combining advantages of each locomotion mode. This review surveys over two decades of development in multimodal robots that move on the ground and in air. Multimodality can be achieved by leveraging three main design approaches: adding morphological features, adapting forms for locomotion transitions, and integrating multiple vehicle platforms. Each classification is thoroughly examined and synthesized, encompassing both qualitative and quantitative aspects. The authors delved into the intricacies of these approaches and explored the challenges and opportunities that lie ahead in pursuit of the next generation of mobile robots. This review aims to advance future deployment of multimodal robots in the real world for challenging operations in dangerous, unstructured, contact-prone, cluttered and subterranean environments.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"26 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138563839","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hybrid aerial–aquatic robots can operate in both air and water and cross between these two. They can be applied to amphibious observation, maritime search and rescue, and cross‐domain environmental monitoring. Herein, an aerial–aquatic hitchhiking robot is proposed that can fly, swim, and rapidly cross the air–water boundaries (0.16 s) and autonomously attach to surfaces in both air and water. Inspired by the mechanoreceptors of the remora ( Echeneis naucrates ) disc, the robot's hitchhiking device is equipped with two flexible bioinspired tactile sensors (FBTS) based on a triboelectric nanogenerator for tactile sensing of attachment status. Based on tactile sensing, the robot can perform reattachment after leakage or adhesion failure, enabling it to achieve long‐term adhesion on complex surfaces. The rotor‐based aerial–aquatic robot, which has two thrust vectoring units for underwater locomotion, can maneuver to pitch, yaw, and roll 360° and control precision motion position. The field tests show that the robot can continuously cross the air–water boundary, attach to the rough stone surface, and record video in both air and underwater. This study may shed light on future autonomous robots capable of intelligent navigation, adhesion, and operation in complex aerial–aquatic environments.
{"title":"An Aerial–Aquatic Hitchhiking Robot with Remora‐Inspired Tactile Sensors and Thrust Vectoring Units","authors":"Lei Li, Wenbo Liu, Bocheng Tian, Peiyu Hu, Wenzhuo Gao, Yuchen Liu, Fuqiang Yang, Youning Duo, Hongru Cai, Yiyuan Zhang, Zhouhao Zhang, Zimo Li, Li Wen","doi":"10.1002/aisy.202300381","DOIUrl":"https://doi.org/10.1002/aisy.202300381","url":null,"abstract":"Hybrid aerial–aquatic robots can operate in both air and water and cross between these two. They can be applied to amphibious observation, maritime search and rescue, and cross‐domain environmental monitoring. Herein, an aerial–aquatic hitchhiking robot is proposed that can fly, swim, and rapidly cross the air–water boundaries (0.16 s) and autonomously attach to surfaces in both air and water. Inspired by the mechanoreceptors of the remora ( Echeneis naucrates ) disc, the robot's hitchhiking device is equipped with two flexible bioinspired tactile sensors (FBTS) based on a triboelectric nanogenerator for tactile sensing of attachment status. Based on tactile sensing, the robot can perform reattachment after leakage or adhesion failure, enabling it to achieve long‐term adhesion on complex surfaces. The rotor‐based aerial–aquatic robot, which has two thrust vectoring units for underwater locomotion, can maneuver to pitch, yaw, and roll 360° and control precision motion position. The field tests show that the robot can continuously cross the air–water boundary, attach to the rough stone surface, and record video in both air and underwater. This study may shed light on future autonomous robots capable of intelligent navigation, adhesion, and operation in complex aerial–aquatic environments.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"157 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136314090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The advent of the intelligent society leads to the exponential growth of information, imposing urgent requirements in a time‐ and energy‐efficient way to process information where data are generated. This issue can be addressed by the neuromorphic paradigm of computing inspired by biological sensory systems that build up the association between external stimuli and the response of an organism in real‐time; in the paradigm, a neuromorphic system is integrated with sensors to form an artificial sensory system. Herein, a neuromorphic sensory system with integrated capabilities of gas sensing, data storage, and processing is demonstrated. Leaky integrate‐and‐fire (LIF) neurons, the basic computing units in the system, are realized with volatile memristive device Pt/Ag/TaOx/Pt; sensory neurons, i.e., the LIF neurons connected with an array of gas sensors, detect gases and convert the chemical information of gases into neural spikes; synapses based on nonvolatile memristive device Pt/Ta/TaOx/Pt transmit the signals from sensory neurons to relay neurons according to synaptic weights, which are trained by the supervised spike‐rate dependent plasticity; relay neurons then process the signals from the synapses and classify gases. The approach of this work can also be applied to emulate other biological perceptions through the integration with different sensors.
{"title":"A Bio‐Inspired Neuromorphic Sensory System","authors":"Tong Wang, Xiao-Xue Wang, Juan Wen, Zhenya Shao, He-Ming Huang, Xin Guo","doi":"10.1002/aisy.202200047","DOIUrl":"https://doi.org/10.1002/aisy.202200047","url":null,"abstract":"The advent of the intelligent society leads to the exponential growth of information, imposing urgent requirements in a time‐ and energy‐efficient way to process information where data are generated. This issue can be addressed by the neuromorphic paradigm of computing inspired by biological sensory systems that build up the association between external stimuli and the response of an organism in real‐time; in the paradigm, a neuromorphic system is integrated with sensors to form an artificial sensory system. Herein, a neuromorphic sensory system with integrated capabilities of gas sensing, data storage, and processing is demonstrated. Leaky integrate‐and‐fire (LIF) neurons, the basic computing units in the system, are realized with volatile memristive device Pt/Ag/TaOx/Pt; sensory neurons, i.e., the LIF neurons connected with an array of gas sensors, detect gases and convert the chemical information of gases into neural spikes; synapses based on nonvolatile memristive device Pt/Ta/TaOx/Pt transmit the signals from sensory neurons to relay neurons according to synaptic weights, which are trained by the supervised spike‐rate dependent plasticity; relay neurons then process the signals from the synapses and classify gases. The approach of this work can also be applied to emulate other biological perceptions through the integration with different sensors.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"120 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87779988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：