In this paper,we present a Deep Neural Network(DNN)based framework that employs Radio Frequency(RF)hologram tensors to locate multiple Ultra-High Frequency(UHF)passive Radio-Frequency Identification(RFID)tags.The RF h...In this paper,we present a Deep Neural Network(DNN)based framework that employs Radio Frequency(RF)hologram tensors to locate multiple Ultra-High Frequency(UHF)passive Radio-Frequency Identification(RFID)tags.The RF hologram tensor exhibits a strong relationship between observation and spatial location,helping to improve the robustness to dynamic environments and equipment.Since RFID data is often marred by noise,we implement two types of deep neural network architectures to clean up the RF hologram tensor.Leveraging the spatial relationship between tags,the deep networks effectively mitigate fake peaks in the hologram tensors resulting from multipath propagation and phase wrapping.In contrast to fingerprinting-based localization systems that use deep networks as classifiers,our deep networks in the proposed framework treat the localization task as a regression problem preserving the ambiguity between fingerprints.We also present an intuitive peak finding algorithm to obtain estimated locations using the sanitized hologram tensors.The proposed framework is implemented using commodity RFID devices,and its superior performance is validated through extensive experiments.展开更多
在室内停车场中应用基于RFID的LANDMARC算法进行车辆定位时,由于室内停车场的复杂结构以及多径效应的影响,车辆定位精度不能通过增加参考标签数目或均匀规则的部署参考标签等方式来提升。提出了一种基于虚拟RFID标签的室内定位算法(loca...在室内停车场中应用基于RFID的LANDMARC算法进行车辆定位时,由于室内停车场的复杂结构以及多径效应的影响,车辆定位精度不能通过增加参考标签数目或均匀规则的部署参考标签等方式来提升。提出了一种基于虚拟RFID标签的室内定位算法(location algorithm based on virtual tag,LAVT)。该算法通过近邻标签确定车辆的近邻区域,计算出近邻区域的外心并插入虚拟参考标签;通过虚拟参考标签替换原近邻标签、缩小近邻区域面积,使新近邻标签更临近待定位车辆,从而更精确地计算出车辆的位置。仿真实验表明:LAVT算法在室内停车场环境中将车辆定位精度提升了19.03%。LAVT算法应用于室内停车场环境中的车辆定位具有更好的适用性,能满足室内停车场车辆定位的基本需求。展开更多
In this paper,we present an RFID based human and Unmanned Aerial Vehicle(UAV)Interaction system,termed RFHUI,to provide an intuitive and easy-to-operate method to navigate a UAV in an indoor environment.It relies on t...In this paper,we present an RFID based human and Unmanned Aerial Vehicle(UAV)Interaction system,termed RFHUI,to provide an intuitive and easy-to-operate method to navigate a UAV in an indoor environment.It relies on the passive Radio-Frequency IDentification(RFID)technology to precisely track the pose of a handheld controller,and then transfer the pose information to navigate the UAV.A prototype of the handheld controller is created by attaching three or more Ultra High Frequency(UHF)RFID tags to a board.A Commercial Off-The-Shelf(COTS)RFID reader with multiple antennas is deployed to collect the observations of the tags.First,the precise positions of all the tags can be obtained by our proposed method,which leverages a Bayesian filter and Channel State Information(CSI)phase measurements collected from the RFID reader.Second,we introduce a Singular Value Decomposition(SVD)based approach to obtain a 6-DoF(Degrees of Freedom)pose of the controller from estimated positions of the tags.Furthermore,the pose of the controller can be precisely tracked in a real-time manner,while the user moves the controller.Finally,control commands will be generated from the controller's pose and sent to the UAV for navigation.The performance of the RFHUI is evaluated by several experiments.The results show that it provides precise poses with 0.045m mean error in position and 2.5∘mean error in orientation for the controller,and enables the controller to precisely and intuitively navigate the UAV in an indoor environment.展开更多
Adaptive power control is a critical challenge in dense radio frequency identification(RFID)environments,where uncontrolled power levels can lead to excessive interference,energy inefficiency,and reduced system perfor...Adaptive power control is a critical challenge in dense radio frequency identification(RFID)environments,where uncontrolled power levels can lead to excessive interference,energy inefficiency,and reduced system performance.This paper presents a robust and scalable adaptive power control framework that dynamically adjusts transmit power levels to optimize energy efficiency,minimize interference,and enhance system throughput.The proposed framework leverages an optimization-driven approach based on real-time environmental feedback,ensuring compliance with regulatory constraints while maintaining optimal performance.A multi-objective optimization strategy is employed to balance several key metrics,including throughput,energy consumption,and fairness,with a Pareto front analysis demonstrating superior trade-offs compared to fixed power strategies.The effectiveness of the proposed approach is validated through extensive simulations and real-world experiments using universal software radio peripheral(USRP)devices in dense RFID deployments.The results show that our framework achieves a 34%reduction in cumulative interference,a 15%improvement in energy efficiency,and a 20%increase in throughput compared to baseline fixed power methods.Furthermore,it converges rapidly,even in dynamic and high-density networks.These improvements make it highly scalable and adaptable to varying reader densities,ensuring reliable performance in large-scale RFID applications such as supply chain management and industrial automation.展开更多
实时操作系统(Real-Time Operating System,RTOS)被广泛应用于窄带物联网(Narrow Band Internet of Things,NB-IoT)设备之中。这类设备对体积、能耗与稳定性有着严格的限制。NB-IoT设备多采用宏内核的RTOS,能得到较好的运行性能,但要求...实时操作系统(Real-Time Operating System,RTOS)被广泛应用于窄带物联网(Narrow Band Internet of Things,NB-IoT)设备之中。这类设备对体积、能耗与稳定性有着严格的限制。NB-IoT设备多采用宏内核的RTOS,能得到较好的运行性能,但要求更多的硬件资源,并且内核中出现的问题很可能会导致整个系统崩溃。该文对传统RTOS进行改进,设计开发了无内存管理单元(Memory Management Unit,MMU)的微内核实时操作系统(nM-MKRTOS)。该系统针对NB-IoT中资源较少的设备,利用微内核的优势,其通过动态加载与链接(Dynamic Loading and Dynamic Linking,DL 2)技术实现内存复用和快速启动,并采用模块化开发的方式提高系统稳定性。在实际测试中,nM-MKRTOS通过内存复用技术将内存利用率提高了56.25%;在系统的启动测试中,通过在DL 2技术中引入权重加载,系统的核心功能在三个任务子集上的启动时间分别减少57.59%、52.55%与47.59%。该系统能够广泛应用于智慧农业、智慧校园等场合,能够降低系统成本,提高系统稳定性。展开更多
In recent years,reinforcement learning(RL)has shown high potential for robotic applications.However,RL heavily relies on the reward function,and the agent merely follows the policy to maximize rewards but lacks reason...In recent years,reinforcement learning(RL)has shown high potential for robotic applications.However,RL heavily relies on the reward function,and the agent merely follows the policy to maximize rewards but lacks reasoning ability.As a result,RL may not be suitable for long-horizon robotic tasks.In this paper,we propose a novel learning framework,called multiple state spaces reasoning reinforcement learning(SRRL),to endow the agent with the primary reasoning capability.First,we abstract the implicit and latent links between multiple state spaces.Then,we embed historical observations through a long short-term memory(LSTM)network to preserve long-term memories and dependencies.The proposed SRRL’s ability of abstraction and long-term memory enables agents to execute long-horizon robotic searching and planning tasks more quickly and reasonably by exploiting the correlation between radio frequency identification(RFID)sensing properties and the environment occupation map.We experimentally validate the efficacy of SRRL in a visual game-based simulation environment.Our methodology outperforms three state-of-the-art baseline schemes by significant margins.展开更多
基金supported in part by the U.S.National Science Foundation(NSF)under Grants ECCS-2245608 and ECCS-2245607。
文摘In this paper,we present a Deep Neural Network(DNN)based framework that employs Radio Frequency(RF)hologram tensors to locate multiple Ultra-High Frequency(UHF)passive Radio-Frequency Identification(RFID)tags.The RF hologram tensor exhibits a strong relationship between observation and spatial location,helping to improve the robustness to dynamic environments and equipment.Since RFID data is often marred by noise,we implement two types of deep neural network architectures to clean up the RF hologram tensor.Leveraging the spatial relationship between tags,the deep networks effectively mitigate fake peaks in the hologram tensors resulting from multipath propagation and phase wrapping.In contrast to fingerprinting-based localization systems that use deep networks as classifiers,our deep networks in the proposed framework treat the localization task as a regression problem preserving the ambiguity between fingerprints.We also present an intuitive peak finding algorithm to obtain estimated locations using the sanitized hologram tensors.The proposed framework is implemented using commodity RFID devices,and its superior performance is validated through extensive experiments.
文摘在室内停车场中应用基于RFID的LANDMARC算法进行车辆定位时,由于室内停车场的复杂结构以及多径效应的影响,车辆定位精度不能通过增加参考标签数目或均匀规则的部署参考标签等方式来提升。提出了一种基于虚拟RFID标签的室内定位算法(location algorithm based on virtual tag,LAVT)。该算法通过近邻标签确定车辆的近邻区域,计算出近邻区域的外心并插入虚拟参考标签;通过虚拟参考标签替换原近邻标签、缩小近邻区域面积,使新近邻标签更临近待定位车辆,从而更精确地计算出车辆的位置。仿真实验表明:LAVT算法在室内停车场环境中将车辆定位精度提升了19.03%。LAVT算法应用于室内停车场环境中的车辆定位具有更好的适用性,能满足室内停车场车辆定位的基本需求。
文摘In this paper,we present an RFID based human and Unmanned Aerial Vehicle(UAV)Interaction system,termed RFHUI,to provide an intuitive and easy-to-operate method to navigate a UAV in an indoor environment.It relies on the passive Radio-Frequency IDentification(RFID)technology to precisely track the pose of a handheld controller,and then transfer the pose information to navigate the UAV.A prototype of the handheld controller is created by attaching three or more Ultra High Frequency(UHF)RFID tags to a board.A Commercial Off-The-Shelf(COTS)RFID reader with multiple antennas is deployed to collect the observations of the tags.First,the precise positions of all the tags can be obtained by our proposed method,which leverages a Bayesian filter and Channel State Information(CSI)phase measurements collected from the RFID reader.Second,we introduce a Singular Value Decomposition(SVD)based approach to obtain a 6-DoF(Degrees of Freedom)pose of the controller from estimated positions of the tags.Furthermore,the pose of the controller can be precisely tracked in a real-time manner,while the user moves the controller.Finally,control commands will be generated from the controller's pose and sent to the UAV for navigation.The performance of the RFHUI is evaluated by several experiments.The results show that it provides precise poses with 0.045m mean error in position and 2.5∘mean error in orientation for the controller,and enables the controller to precisely and intuitively navigate the UAV in an indoor environment.
基金supported in part by the United States National Science Foundation under Grants CCSS-2245607 and CCSS-2245608the Wireless Engineering Research and Education Center and RFID Lab at Auburn University.
文摘Adaptive power control is a critical challenge in dense radio frequency identification(RFID)environments,where uncontrolled power levels can lead to excessive interference,energy inefficiency,and reduced system performance.This paper presents a robust and scalable adaptive power control framework that dynamically adjusts transmit power levels to optimize energy efficiency,minimize interference,and enhance system throughput.The proposed framework leverages an optimization-driven approach based on real-time environmental feedback,ensuring compliance with regulatory constraints while maintaining optimal performance.A multi-objective optimization strategy is employed to balance several key metrics,including throughput,energy consumption,and fairness,with a Pareto front analysis demonstrating superior trade-offs compared to fixed power strategies.The effectiveness of the proposed approach is validated through extensive simulations and real-world experiments using universal software radio peripheral(USRP)devices in dense RFID deployments.The results show that our framework achieves a 34%reduction in cumulative interference,a 15%improvement in energy efficiency,and a 20%increase in throughput compared to baseline fixed power methods.Furthermore,it converges rapidly,even in dynamic and high-density networks.These improvements make it highly scalable and adaptable to varying reader densities,ensuring reliable performance in large-scale RFID applications such as supply chain management and industrial automation.
文摘实时操作系统(Real-Time Operating System,RTOS)被广泛应用于窄带物联网(Narrow Band Internet of Things,NB-IoT)设备之中。这类设备对体积、能耗与稳定性有着严格的限制。NB-IoT设备多采用宏内核的RTOS,能得到较好的运行性能,但要求更多的硬件资源,并且内核中出现的问题很可能会导致整个系统崩溃。该文对传统RTOS进行改进,设计开发了无内存管理单元(Memory Management Unit,MMU)的微内核实时操作系统(nM-MKRTOS)。该系统针对NB-IoT中资源较少的设备,利用微内核的优势,其通过动态加载与链接(Dynamic Loading and Dynamic Linking,DL 2)技术实现内存复用和快速启动,并采用模块化开发的方式提高系统稳定性。在实际测试中,nM-MKRTOS通过内存复用技术将内存利用率提高了56.25%;在系统的启动测试中,通过在DL 2技术中引入权重加载,系统的核心功能在三个任务子集上的启动时间分别减少57.59%、52.55%与47.59%。该系统能够广泛应用于智慧农业、智慧校园等场合,能够降低系统成本,提高系统稳定性。
基金supported in part by the NSF under Grants ECCS-1923163 and CNS-2107190through the RFID Lab and the Wireless Engineering Research and Education Center at Auburn University,Auburn,AL,USA.
文摘In recent years,reinforcement learning(RL)has shown high potential for robotic applications.However,RL heavily relies on the reward function,and the agent merely follows the policy to maximize rewards but lacks reasoning ability.As a result,RL may not be suitable for long-horizon robotic tasks.In this paper,we propose a novel learning framework,called multiple state spaces reasoning reinforcement learning(SRRL),to endow the agent with the primary reasoning capability.First,we abstract the implicit and latent links between multiple state spaces.Then,we embed historical observations through a long short-term memory(LSTM)network to preserve long-term memories and dependencies.The proposed SRRL’s ability of abstraction and long-term memory enables agents to execute long-horizon robotic searching and planning tasks more quickly and reasonably by exploiting the correlation between radio frequency identification(RFID)sensing properties and the environment occupation map.We experimentally validate the efficacy of SRRL in a visual game-based simulation environment.Our methodology outperforms three state-of-the-art baseline schemes by significant margins.
