Zero-shot coordination(ZSC), a key challenge in multi-agent game theory, has become a hot topic in reinforcement learning (RL) research recently, especially in complex evolving games. It focuses on the generalization ability of agents, requiring them to coordinate well with collaborators from a diverse, potentially evolving, pool of partners that are not seen before without any fine-tuning. Population-based training, which approximates such an evolving partner pool, has been proven to provide good zero-shot coordination performance; nevertheless, existing methods are limited by computational resources, mainly focusing on optimizing diversity in small populations while neglecting the potential performance gains from scaling population size. To address this issue, this paper proposes the Scalable Population Training (ScaPT), an efficient RL training framework comprising two key components: a meta-agent that efficiently realizes a population by selectively sharing parameters across agents, and a mutual information regularizer that guarantees population diversity. To empirically validate the effectiveness of ScaPT, this paper evaluates it along with representational frameworks in Hanabi cooperative game and confirms its superiority.

Place recognition and localization using sonar images is a critical task in the underwater Internet of Things (IoT). In this paper, we propose a robust multi-sensor fusion method that fuses mechanical scanning imaging sonar (MSIS), an inertial measurement unit (IMU), and a Doppler velocity log (DVL). To address the sparse and noisy nature of MSIS data, we introduce dedicated feature descriptors based on echo intensity and structural clustering for stable registration. Moreover, we design a double-check loop closure detection scheme that combines complementary algorithms to effectively suppress false positives and reduce missed detections. Experimental evaluations on multiple real-world datasets and the HoloOcean platform demonstrate that the proposed method consistently achieves robust and accurate performance across diverse underwater environments.

he emergence of unauthorized unmanned aerial vehicles (UAVs) has raised widespread safety threats, making the blind signal recognition of unauthorized multiple UAVs (multi-UAV) critically important.he emergence of unauthorized unmanned aerial vehicles (UAVs) has raised widespread safety threats, making the blind signal recognition of unauthorized multiple UAVs (multi-UAV) critically important.T Meanwhile, the frequency hopping (FH) control signals with the start-end identical preamble (SIP) structure, have three major characteristics: non-stationarity, short dwell time, and scarcity of known labels. These characteristics pose significant challenges to the recognition of unauthorized SIP signals in spectrograms. In this paper, we propose a cross-domain segmenter self-learning classifier (CS-SC) scheme for SIP signals, which can segment each class of UAV in-phase/quadrature (I/Q) signals in multi-UAV environments, and detects the features of unauthorized and unknown SIP signal via self-learning. First, the CS scheme performs time-frequency analysis on received SIP signals, locates signals via an adaptive statistical feature detector on spectrograms, then combines with time-frequency segmentation to obtain I/Q representations of each class of signals. Second, we design a cyclic self-search algorithm in the SC scheme, and the SC scheme can learn discriminative features via the preamble structures, and reduces the interference from payload of unknown UAV signals. Then, these learned features are utilized in template matching for blind SIP signal recognition, which is more efficient than the related learning algorithms. Simulation results validate that, our CS-SC scheme achieves 40% higher clustering accuracy compared with the existing clustering algorithms, and improves the recognition accuracy about 40% than related deep learning algorithms in a wide signal-to-noise ratio (SNR) region.

Open set recognition (OSR) in radio frequency fingerprint (RFF) is critical for securing Internet of Things (IoT) systems, where previously unseen or malicious devices may attempt unauthorized access. A widely used approach treats all unknown devices as a single additional class and assumes that they will produce low confidence scores during inference. However, due to the inherently subtle and highly similar RFF features across devices, this assumption often fails, leading to high false acceptance rates. To address this challenge, we propose a novel framework, called Multiple Unknown Classes Generation (MUCG), which replaces the single-class modeling of unknowns with a more expressive structure that simulates multiple distinct unknown classes. MUCG employs a conditional generative adversarial network (cGAN) guided by ideal signal priors to produce diverse and realistic unknown samples. Furthermore, we introduce a soft label perturbation (SLP) strategy that blends label semantics using Feature-wise Linear Modulation (FiLM), encouraging the generator to embed richer feature variations. Experiments on three public IoT datasets demonstrate that MUCG consistently outperforms state-of-the-art (SOTA) methods in OSR tasks, achieving superior accuracy and robustness under varying signal conditions.

Finding the Nash equilibrium in large-scale zero-sum games has long been a challenging problem due to the vast and unknown policy space and the utility matrix. The Policy-Space Response Oracles (PSRO) framework, as a combination of conventional game analysis with deep reinforcement learning, iteratively constructs a restricted game by including a pure policy that is the best response to the equilibrium of the restricted game in the previous iteration. However, adding a pure policy at a time is inefficient, as there may be multiple policies that dominate the equilibrium of the current restricted game. In this regard, we propose Mixed Policy-Space Response Oracles (M-PSRO), which add a mixed policy rather than a pure policy to the current policy set. To obtain more effective mixed policy candidates, we adopt a parallelized training framework to promote policy diversity. Theoretical analysis shows that M-PSRO can converge to an approximate Nash equilibrium. We conduct extensive experiments across a wide range of complex games, and results show that the M-PSRO algorithm achieves state-of-the-art performance across all the games and can approach the Nash equilibrium more efficiently. Numerous ablation studies show that the improvement benefits from the usage of mixed policies in M-PSRO, which offer an even more flexible optimization space.

Automatic modulation recognition (AMR) is a crucial step in wireless communication systems, which identifies the modulation scheme from detected signals to provide key information for further processing. However, previous work has mainly focused on the identification of a single signal, overlooking the phenomenon of multiple signal superposition in practical channels and the signal detection procedures that must be conducted beforehand. Considering the susceptibility of radio frequency (RF) signals to noise interference and significant spectral variations, we propose a novel Hierarchical Feature Integration (HIFI)-YOLO framework for multi-signal joint detection and modulation recognition. Our HIFI-YOLO framework, with its unique design of hierarchical feature integration, effectively enhances the representation capability of features in different modules, thereby improving detection performance. We construct a large-scale AMR dataset specifically tailored for scenarios of the coexistence or overlapping of multiple signals transmitted through channels with realistic propagation conditions, consisting of diverse digital and analog modulation schemes. Extensive experiments on our dataset demonstrate the excellent performance of HIFI-YOLO in multi-signal detection and modulation recognition as a joint approach.

Radio frequency fingerprint identification (RFFI) leverages signal distortions caused by hardware impairments to identify transmitters, thereby enhancing IoT security. However, current radio frequency fingerprints (RFFs) modelings typically focus on partial hardware impairments, risking incomplete RFF extraction and limited RFF understanding. This study aims to refine the modeling of RFFs and guide the development of robust and accurate RFFI approaches based on this model. Specifically, we propose a comprehensive time-domain signal distortion model based on hardware impairments in wireless transmission circuit components, revealing that RFFs can be categorized into two types: 1) fine-grained RFF and 2) coarse-grained RFF. The former encompass localized distortions, such as mismatches, intersymbol interference, and nonlinear distortions; the latter relate to global features, including frequency spurs, phase noise, and crystal oscillator frequency offset. Subsequently, we analyze the impact of interference on the RFF model and propose necessary methods to mitigate the interference. Combining the comprehensive analysis of the RFF model and interference, we summarize three primary characteristics of RFFs: 1) multiscale; 2) fixedness; and 3) ubiquity. These characteristics indicate that convolutional neural networks (CNNs) from the visual domain cannot be directly transferred or simply adapted in terms of input data shape for application in RFFI. Therefore, we propose an enhanced CNN architecture with grouped convolutions and channel fusion modules for effective RFF extraction. To demonstrate the generalizability of our approach, we conduct extensive experiments using three public IoT signal datasets. Experimental results demonstrate that our method exhibits excellent identification performance and robustness against interference across various environments.

Communication in multi-agent reinforcement learning (MARL) has been proven to effectively promote cooperation among agents recently. Since communication in real-world scenarios is vulnerable to noises and adversarial attacks, it is crucial to develop robust communicative MARL technique. However, existing research in this domain has predominantly focused on passive defense strategies, where agents receive all messages equally, making it hard to balance performance and robustness. We propose an active defense strategy, where agents automatically reduce the impact of potentially harmful messages on the final decision. There are two challenges to implement this strategy, that are defining unreliable messages and adjusting the unreliable messages' impact on the final decision properly. To address them, we design an Active Defense Multi-Agent Communication framework (ADMAC), which estimates the reliability of received messages and adjusts their impact on the final decision accordingly with the help of a decomposable decision structure. The superiority of ADMAC over existing methods is validated by experiments in three communication-critical tasks under four types of attacks.

Tracking the kinetic state of a non-cooperative target in time-varying non-line-of-sight (NLOS) environment is a challenging problem in many applications. The distance estimation (DE) of a target in such tracking system, produced by local anchors, can be influenced by a positive bias caused by refraction and reflection in the physical channel within a NLOS environment. Specifically, in a DE-based positioning network, such as a Time Difference of Arrival (TDOA) localization system with several listening anchors blocked, the NLOS error can cause an overall deviation in positioning, which in turn affects the accuracy of trajectory estimations. In this paper, we develop a regression-based error transition model to associate the NLOS errors with the target states by its previous trajectory. Then, by employing a joint variational Bayesian (VB) approximation, we decouple this association iteratively through algorithm. Thereby facilitating an accurate estimation of the posterior distribution for target trajectories and the ranging error. Experiments involving an actual Unmanned Aerial Vehicle (UAV) and TDOA localization system validate the robustness and performance of our algorithm compared to existing approaches.

Radio Frequency Fingerprinting (RFF)-based identification methods have the potential to enhance the security of the Internet of Things (IoT). However, conventional fingerprinting techniques based on standard sample rates face limitations related to noise and device scale. The utilization of high sample rate receivers offers a promising solution to mitigate these constraints. Nonetheless, the challenge lies in extracting RFFs from the collected ultra-long signals. Image-based methods, which accumulate signals in the time domain, reduce the difficulty of extracting RFFs from long signals but overlook the fine-grained RFFs in the time domain. To solve this problem, this paper proposes RFF modeling for long signals, emphasizing the importance of obtaining short-term time-varying RFFs and time-invariant RFFs. Combining an analysis of the inductive biases of convolutional neural networks, we propose a backbone network named GResNet, which is capable to effectively extract these two types of RFFs. An information fusion module is added to improve identification performance. Extensive experiments are conducted with 100 LoRa devices, demonstrating that our method outperforms existing RFFI techniques based on standard sample rate or high sample rate signals. Furthermore, our approach maintains robust performance within a wide range of SNRs.

The rapid expansion of the Internet of Things (IoT) has heightened the necessity for device identity authentication to ensure security. Radio frequency fingerprint identification (RFFI) has emerged as a promising solution for this purpose, which leverage unique signal distortions caused by hardware impairments to authenticate device identities. However, most RFFI methods operate under a closed-set assumption and usually mistakenly identify unknown devices from the open set as known devices. In this paper, we propose a Synthetic Feature Constrain for open-set Recognition (SFCR) method to maintain classification performance on known devices and identify unknowns. Specifically, we modify the nonlinear characteristics of known devices based on the power amplifier nonlinearity model of radio frequency fingerprints (RFF) to synthesize signals for unknown devices. Furthermore, we propose a synthetic feature constraint to calibrate the position of synthetic devices in the feature space, such that they lie between the feature centers of the collective synthetic and originating known devices. As synthetic devices represent only a subset of the real unknown devices, we also introduce a calibration method for the prediction results. Experiments on a publicly available LoRa device dataset have validated the effectiveness of our approach. The code is released on github.com/wzyxwqx/SFCR.

Time-sparse frequency-hopping (FH) signals detection and sequences identification present a significant challenge in spectrum tracking of multiple targets. The non-continuous observations that arise from their temporal sparsity complicates identification efforts in low signal-to-noise ratio (SNR) environments. In this letter, a dynamic temporal perception probability hypothesis density (DTP-PHD) filter for spectrum tracking of multiple targets with potential periodicity was proposed by leveraging the periodicity alignment likelihood ratio (PALR). The PALR enables the estimation of the time transition function of targets' FH signals, which also facilitates the extraction of the spectrum track by identifying each target using a joint posterior intensity. Moreover, a closed-form solution of DTP-PHD was derived under linear Gaussian assumptions. The validity of the periodicity estimation was established by implementing a particle version of the proposed algorithm, which demonstrated robust tracking performance in noisy environments.

Automatic modulation recognition (AMR) has received widespread attention as a crucial aspect of non-cooperative communication. Despite this, large carrier frequency offsets (CFOs) and sample rate offsets (SROs) caused by inaccurate parameter estimation at the receiver are harmful to the recognition accuracy, which is still to be addressed. In this letter, we focus on intelligent modulation recognition tasks under such offsets. A novel transformer-based method named TransGroupNet is designed that can extract deep features of signals from the instantaneous amplitude, phase, and frequency (APF) domain. In addition, lightweight group convolution layers are added ahead of the transformer blocks for better feature preprocessing. Simulations demonstrate that the proposed TransGroupNet achieves better recognition accuracy under large offsets compared with the previous state-of-the-art methods, even though these methods adopt correction modules (CM) to address such offsets.

With the fast development of multi-agent reinforcement learning, communication among agents has become a new research hotspot for its significant role in promoting the cooperation of automated devices. However, in real-world scenarios, agents such as unmanned vehicles and robots are likely to suffer from communication resource constraints, making designing efficient communication protocols essential. In this paper, we propose to quantize messages and reduce discrete entropy to achieve effective multi-agent communication under bandwidth limits. Achieving this goal requires solving two challenges: The first one is that the gradients of discrete entropy remain zero except for several discontinuous points wherein the gradients are undefined, making it hard to reduce discrete entropy via gradient-based training. To overcome it, we design Surrogate Entropy Minimization (SEM) scheme and confirm its effectiveness theoretically. The second challenge is maximizing cooperation performance under a given bandwidth limit. We model it as a constrained optimization problem and design Soft Barrier Method (SBM). Our proposed scheme is evaluated alongside four other methods in six environment settings and five different bandwidth limits, and demonstrates outstanding performance. Specifically, it manages to reduce bandwidth consumption by up to 90% with little or no loss of cooperation performance.

Multi-agent reinforcement learning (MARL) has achieved great progress in cooperative tasks in recent years. However, in the local reward scheme, where only local rewards for each agent are given without global rewards shared by all the agents, traditional MARL algorithms lack sufficient consideration of agents’ mutual influence. In cooperative tasks, agents’ mutual influence is especially important since agents are supposed to coordinate to achieve better performance. In this paper, we propose a novel algorithm Mutual-Help-based MARL (MH-MARL) to instruct agents to help each other in order to promote cooperation. MH-MARL utilizes an expected action module to generate expected other agents’ actions for each particular agent. Then, the expected actions are delivered to other agents for selective imitation during training. Experimental results show that MH-MARL improves the performance of MARL both in success rate and cumulative reward.

Communication in multi-agent reinforcement learning has been drawing attention recently for its significant role in cooperation. However, multi-agent systems may suffer from limitations on communication resources and thus need efficient communication techniques in real-world scenarios. According to the Shannon-Hartley theorem, messages to be transmitted reliably in worse channels require lower entropy. Therefore, we aim to reduce message entropy in multi-agent communication. A fundamental challenge is that the gradients of entropy are either 0 or ∞, disabling gradient-based methods. To handle it, we propose a pseudo gradient descent scheme, which reduces entropy by adjusting the distributions of messages wisely. We conduct experiments on two base communication frameworks with six environment settings and find that our scheme can reduce message entropy by up to 90% with nearly no loss of cooperation performance.

Control algorithms of a multiagent system (MAS) have been applied to many Internet of Things devices, such as unmanned aerial vehicles and autonomous underwater vehicles. Flocking control is a crucial problem in MAS to enhance the safety and cooperativity of agents, which requires the agents to maintain the flock when navigating to a target position and avoiding collisions. In comparison with the traditional algorithms, methods based on multiagent reinforcement learning (MARL) can solve the problem of flocking control more flexibly and adapt to more complex environments. However, the MARL-based methods demand a huge number of interactions between agents and the environment, resulting in the problem of sample inefficiency. In this article, we propose nonexpert policy-aided MARL (NPA-MARL) to improve sample efficiency, which utilizes a fundamental MARL algorithm and a prior policy whose performance can be nonexpert. Before online MARL training, NPA-MARL generates demonstrations by the nonexpert policy to pretrain agents, while preventing overfitting demonstrations. During online training, NPA-MARL instructs agents to imitate the nonexpert policy if the nonexpert policy is better in agents’ recognition. We leverage NPA-MARL to solve the problem of flocking control. Experimental results show that NPA-MARL improves sample efficiency and policy performance in flocking control. Besides, NPA-MARL has the scalability of more agents and the flexibility of choice of the nonexpert policy and a fundamental MARL algorithm.

Edge computing has been envisioned as a key enabler to provide computation-intensive and delay-sensitive services in the future Internet of Things systems. By offloading the computational tasks to the edge server, both the service latency and energy consumption can be reduced. Since devices may request various types of computing services, caching appropriate services in the edge server to immediately provide computing resources can improve the quality of service. Nevertheless, it brings new challenges to jointly optimize the resource allocation, where the timeliness of caching and offloading operations are different. In this article, we first formulate the collaborative service caching and computation offloading as a dual-timescale resource allocation problem to minimize the costs of latency and energy consumption. Under this framework, a novel scheme based on hierarchical deep reinforcement learning is proposed to output collaborative caching and computing actions. Specifically, the proposed approach contains the service caching policy and the device computing policy with hierarchical action–value functions, which allows a flexible configuration of caching timescales. The simulation results demonstrate that the proposed policy outperforms the existing schemes on convergence performance and various parameters.

Vehicular edge computing (VEC) is an effective method to increase the computing capability of vehicles, where vehicles share their idle computing resources with each other. However, due to the high mobility of vehicles, it is challenging to design an optimal task allocation policy that adapts to the dynamic vehicular environment. Further, vehicular computation offloading often occurs between unfamiliar vehicles, how to motivate vehicles to share their computing resources while guaranteeing the reliability of resource allocation in task offloading is one main challenge. In this paper, we propose a blockchain-enabled VEC framework to ensure the reliability and efficiency of vehicle-to-vehicle (V2V) task offloading. Specifically, we develop a deep reinforcement learning (DRL)-based computation offloading scheme for the smart contract of blockchain, where task vehicles can offload part of computation-intensive tasks to neighboring vehicles. To ensure the security and reliability in task offloading, we evaluate the reliability of vehicles in resource allocation by blockchain. Moreover, we propose an enhanced consensus algorithm based on practical Byzantine fault tolerance (PBFT), and design a consensus nodes selection algorithm to improve the efficiency of consensus and motivate base stations to improve reliability in task allocation. Simulation results validate the effectiveness of our proposed scheme for blockchain-enabled VEC.

Multi-agent systems are being widely deployed to various tasks due to excellent collaboration gains. These tasks usually contain localization and control stages, in which the information coupling mechanism is still unclear thus many system resources are wasted. In this paper, we integrally analyze the performance bound of 3D formation accuracy with localization uncertainty so as to reduce consumption. We start from the equivalence class distance to analyze the 3D relative formation distance and obtain its closed-form upper bound and lower bound. Then we establish an integrated localization and control framework for the 3D formation and analyze how observation and control errors affect the formation accuracy. We propose integrated feedback resource allocation algorithms including agents scheduling and power allocation. Simulation results show the significant performance gain and resource cost reduction brought by the integrated framework.

Autonomous exploration and mapping of unknown terrains employing single or multiple robots is an essential task in mobile robotics and has therefore been widely investigated. Nevertheless, given the lack of unified data sets, metrics, and platforms to evaluate the exploration approaches, we develop an autonomous robot exploration benchmark en-titled Explore-Bench. The benchmark involves various explo-ration scenarios and presents two types of quantitative metrics to evaluate exploration efficiency and multi-robot cooperation. Explore-Bench is extremely useful as, recently, deep rein-forcement learning (DRL) has been widely used for robot exploration tasks and achieved promising results. However, training DRL-based approaches requires large data sets, and additionally, current benchmarks rely on realistic simulators with a slow simulation speed, which is not appropriate for training exploration strategies. Hence, to support efficient DRL training and comprehensive evaluation, the suggested Explore-Bench designs a 3-level platform with a unified data flow and 12 × speed-up that includes a grid-based simulator for fast evaluation and efficient training, a realistic Gazebo simulator, and a remotely accessible robot testbed for high-accuracy tests in physical environments. The practicality of the proposed benchmark is highlighted with the application of one DRL-based and three frontier-based exploration approaches. Fur-thermore, we analyze the performance differences and provide some insights about the selection and design of exploration methods. Our benchmark is available at https://github.com/efc-robot/Explore-Bench.

Multi-agent formation as well as obstacle avoid-ance is one of the most actively studied topics in the field of multi-agent systems. Although some classic controllers like model predictive control (MPC) and fuzzy control achieve a certain measure of success, most of them require precise global information which is not accessible in harsh environments. On the other hand, some reinforcement learning (RL) based approaches adopt the leader-follower structure to organize different agents' behaviors, which sacrifices the collaboration between agents thus suffering from bottlenecks in maneuver-ability and robustness. In this paper, we propose a distributed formation and obstacle avoidance method based on multi-agent reinforcement learning (MARL). Agents in our system only utilize local and relative information to make decisions and control themselves distributively, and will reorganize themselves into a new topology quickly in case that any of them is dis-connected. Our method achieves better performance regarding formation error, formation convergence rate and on-par success rate of obstacle avoidance compared with baselines (both classic control methods and another RL-based method). The feasibility of our method is verified by both simulation and hardware implementation with Ackermann-steering vehicles.

Flocking control is a challenging problem, where multiple agents, such as drones or vehicles, need to reach a target position while maintaining the flock and avoiding collisions with obstacles and collisions among agents in the environment. Multi-agent reinforcement learning has achieved promising performance in flocking control. However, methods based on traditional reinforcement learning require a considerable number of interactions between agents and the environment. This paper proposes a sub-optimal policy aided multiagent reinforcement learning algorithm (SPA-MARL) to boost sample efficiency. SPA-MARL directly leverages a prior policy that can be manually designed or solved with a non-learning method to aid agents in learning, where the performance of the policy can be sub-optimal. SPA-MARL recognizes the difference in performance between the sub-optimal policy and itself, and then imitates the sub-optimal policy if the suboptimal policy is better. We leverage SPA-MARL to solve the flocking control problem. A traditional control method based on artificial potential fields is used to generate a sub-optimal policy. Experiments demonstrate that SPA-MARL can speed up the training process and outperform both the MARL baseline and the used sub-optimal policy.

Flocking control is a significant problem in multi-agent systems such as multi-agent unmanned aerial vehicles and multi-agent autonomous underwater vehicles, which enhances the cooperativity and safety of agents. In contrast to traditional methods, multi-agent reinforcement learning (MARL) solves the problem of flocking control more flexibly. However, methods based on MARL suffer from sample inefficiency, since they require a huge number of experiences to be collected from interactions between agents and the environment. We propose a novel method Pretraining with Demonstrations for MARL (PwD-MARL), which can utilize non-expert demonstrations collected in advance with traditional methods to pretrain agents. During the process of pretraining, agents learn policies from demonstrations by MARL and behavior cloning simultaneously, and are prevented from overfitting demonstrations. By pretraining with non-expert demonstrations, PwD-MARL improves sample efficiency in the process of online MARL with a warm start. Experiments show that PwD-MARL improves sample efficiency and policy performance in the problem of flocking control, even with bad or few demonstrations.

The rapid evolution of vehicles leads to future vehicular technologies which improve transportation systems. One prominent technology is platooning networks where a vehicle, called platoon head, leads to a group of vehicles. Platoons not only improve the vehicle driving experience and safety but also reduce traffic congestion. Despite all these benefits, the authentication of vehicles for platoon networks is a critical problem in order to share and get access control to other vehicles. Moreover, due to the platoon networks’ complexity and high dynamic formation, it requires an efficient and robust authentication mechanism between vehicles. In this paper, we propose a blockchain-based authentication protocol for platoons using the concept of the platoon as a service. Our approach not only proposes an efficient protocol that reduces the computation and communication for the authentication but also improves the security with the use of a distributed authentication (Auth-I) data ledger across the network and a token-based platoon authentication (Auth-II), which is suitable for practical implementations in areas with different traffic density.

Sparse fast Fourier transform (SFFT) achieves spectrum sensing with sublinear computational and sample complexity, which has raised widely attention in the signal processing community recently. However, SFFT ignores the structure characteristics of spectrum. In this paper, we optimize the SFFT algorithm for band-limited spectrum sensing. The optimized permutation theory is given and proven first. Then, based on the optimized permutation theory, the optimized sparse Fourier transform for band-limited signal (OB-SFT) is designed. OB-SFT is a universal algorithm with deterministic parameters, and the computational and sample complexity are less than SFFT. Finally, numerical simulations verify the effectiveness and advantages of OB-SFT.

Precise range information is essential for high-precision network localization, where clock drifts will severely degrade the ranging accuracy. Two-way ranging methods are commonly adopted to mitigate those effects in localization networks but requiring a large amount of signal transmission to measure the distance between all pairs of nodes. This paper establishes a network localization framework, which fully mitigates clock drifts using only a minimum number of signal transmissions. The enabler is the proposed signal-multiplexing network ranging (SM-NR) method that minimizes communication overhead via signal multiplexing and eliminates clock drifts by exploiting the interconnections of timestamps. The proposed localization framework also allows some nodes to work in silent mode, of which the positions can be precisely determined without extra ranging signal transmissions. Simulation results show that the proposed algorithm can achieve high-precision localization in the presence of clock drifts with minimum signal overhead.

Coverage control is an essential problem in wireless camera sensor networks (WCSNs), and how to realize cooperative dynamic coverage control in WCSNs with anisotropic perception receives wide concern. In this paper, first we design a coverage metric integrating both the perception quality and the cover rate, in which the dynamic accumulation of coverage performance over time is also considered. To characterize the perception and the motion traits of the WCSNs, an anisotropic sensing model and the unicycle kinematic model are adopted. Then we propose a two-level cooperative dynamic coverage con-trol scheme for the WCSNs, which incorporates both the time-domain cooperation among time instants and the spatial-domain cooperation among agents. Compared with the traditional area-oriented methods, our scheme achieves target-oriented coverage based on the density function within the region. Numerical results verify the performance of our scheme in terms of the total and the perception cover rates.

Mobile multi-agent detection has enabled compre-hensive applications for intelligent sensing networks including Internet of Vehicles, Internet of Things and unmanned aerial vehicle formation. Regardless of the significant advantages of broad coverage and great flexibility, the implementation and popularization of sensing technologies are also limited by the inherent issues of position uncertainty, status update delay and sampling frequency. In this paper, we propose a detection performance evaluation scheme for distributed multi-agent detection in the presence of delayed update of agent positions. By deriving the spatial-temporal detection utility function across the network, we determine the influence mechanism of various non-ideal factors. Moreover, the universal lower bound of detection performance and the upper bounds for two scheduling policies are presented via asymptotic analysis on infinite time horizon. Numerical results further validate the superiority of delay-aware scheduling in mobile detection networks.

With the fast evolution of vehicle networks, Connected and Autonomous Vehicles (CAVs) are mobile devices that are not only used for transportation but also form part of other promising technologies such as the internet of vehicles and cyber-physical systems. Despite the benefits of CAVs, exposing in-vehicle networks to external devices can lead to different privacy and security challenges. Due to scalability, efficiency, and dynamic communication requirements, the security between in-vehicle networks with external devices cannot fully rely on the vehicle's external third parties. In this paper, we propose a semi-decentralized fine-grained security framework based on Ciphertex-Policy Attribute-Based Encryption (CP-ABE) to secure the communication of in-vehicle network's Electronic Control Units (ECUs) with vehicle's external connected device. Our approach's fine-grained access control is based on the attributes of external devices connected to different subsystems inside the vehicle. Each subsystem inside the vehicle has full control of the access policy during the vehicle's operation. Therefore, our proposed approach has a flexible and dynamic key management suitable for future CAVs. Finally, the experiment of our framework validates its feasibility for implementation.

Vehicular fog computing (VFC) has been expected as a promising paradigm that can improve the computational capability of vehicles, where vehicles can share their idle computing resource among each other. Considering the limited computational capability of a single vehicle and the short vehicle-to-vehicle (V2V) link duration, binary task offloading may suffer from the long execution time and the V2V link interruption, which may not be appropriate for some computation-intensive tasks. V2V partial computation offloading is expected to be a promising solution where tasks are divided into several parts and executed in multiple neighboring vehicles. However, due to the high-dynamic vehicular environment, it is challenging to design a scheme that can determine the service vehicles and the computing resource allocation both in local on-board CPU and in service vehicles for offloading tasks. To deal with these problems above, this paper develops a novel V2V partial computation offloading scheme and evaluates the service availability of neighboring vehicles in terms of their idle computing resource and the vehicle mobility. Moreover, the V2V partial offloading problem is formulated as a sequential decision making problem and solved by our proposed algorithm based on deep reinforcement learning (DRL). Finally, simulation results validate the effectiveness of our proposed mechanism.

Accurate location information is essential for many emerging applications of the Internet of Things. Compared with absolute positions, relative positions of nodes are often more relevant in tasks such as formation control and autonomous driving. In this article, we propose a relative localization scheme for terminals aided by unmanned aerial vehicles. We first derive the performance limit of the relative position error as the constrained Cramér-Rao lower bound (CRLB), and proved that the equivalent Fisher information of a subnetwork retains all the information for its relative localization. We then develop a distributed localization algorithm based on local geometry transforming for the proposed scheme with low computation complexity. Moreover, an iterative descent algorithm is designed for joint power and spectrum allocation for relative localization. Numerical results show that the proposed localization algorithm significantly outperforms existing algorithms and the optimal allocation scheme can reduce the relative CRLB by about 50% compared with the uniform allocation scheme.

As a promising technology to improve the computation experience for mobile devices, mobile edge computing (MEC) is becoming an emerging paradigm to meet the tremendous increasing computation demands. In this paper, a mobile edge computing system consisting of multiple mobile devices with energy harvesting and an edge server is considered. Specifically, multiple devices decide the offloading ratio and local computation capacity, which are both in continuous values. Each device equips a task load queue and energy harvesting, which increases the system dynamics and leads to the time-dependence of the optimal offloading decision. In order to minimize the sum cost of the execution time and energy consumption in the long-term, we develop a continuous control based deep reinforcement learning algorithm for computation offloading. Utilizing the actor-critic learning approach, we propose a centralized learning policy for each device. By incorporating the states of other devices with centralized learning, the proposed method learns to coordinate among all devices. Simulation results validate the effectiveness of our proposed algorithm, which demonstrates superior generalization ability and achieves a better performance compared with discrete decision based deep reinforcement learning methods.

Large-scale antenna arrays offer considerable opportunities for high-accuracy network localization. However, such systems face severe resource challenges both from communication and computation, due to high-dimensional array signal processing. To reduce resource consumption, in this paper, we propose a lossless array signal dimension reduction scheme for multipath scenarios. The lossless scheme is determined by deriving and exploring the performance bound of localization systems in multipath environments. The effects of system parameters on the lossless scheme are also presented. Our results reveal that instead of directly processing high-dimensional array signals to seek high-accuracy localization, a comparable performance with significantly lower resource consumptions can be achieved by projecting signals into the low-dimensional subspace.

The isoline tracking of this work is concerned with the control design for a sensing robot to track a given isoline of an unknown 2-D scalar filed. To this end, we propose a coordinate-free controller with a simple PI-like form using only the concentration feedback for a Dubins robot, which is particularly useful in GPS-denied environments. The key idea lies in the novel design of a sliding surface based error term in the standard PI controller. Interestingly, we also prove that the tracking error can be reduced by increasing the proportion gain, and be eliminated for circular fields with a non-zero integral gain. The effectiveness of our controller is validated via simulations by using a fixed-wing UAV on the real dataset of the concentration distribution of PM2.5 in an area of China.

Despite the benefits of electric and autonomous vehicles, current in-vehicle networks lack a robust and feasible security framework that considers the authentication, confidentiality, and integrity for the communication of Electronic Control Units (ECUs). Although a centralized key management mechanism offers an efficient solution, the security fully relies on this centralized unit, which leads to a single point of failure problem. In this paper, we present a semi-centralized key management framework to secure in-vehicle networks. It provides a decentralized and dynamic key distribution during the vehicle's operation and considers different aspects such as ECU's broadcast communication, ECU manufacturing process and ECU authentication without the use of certificates from external third parties. Finally, the implementation and the simulation of our framework validate the feasibility and practical use of our approach.

For the next generation of communication systems, low latency is an urging requirement to satisfy the increasing computation requires. In response, mobile edge computing (MEC) with energy harvesting (EH) is a promising technology to achieve sustained improvement of the computation experience. However, the frequently varied harvested energy, coupled with variable computing tasks and changing computation capacity of servers, results in the high dynamics of the computation offloading problem. In order to get satisfactory computation quality for such a high dynamic offloading problem, devices should learn to make multiple continuous and discrete actions when optimizing the system performance, such as latency, energy efficiency, etc. In this paper, we propose a continuous-discrete hybrid decision based deep reinforcement learning algorithm for dynamic computation offloading. Specifically, the actor outputs continuous actions (offloading ratio and local computation capacity) corresponding to every server. On the other hand, the critic outputs the discrete action (server selection) while also evaluates the performance of the actor for neural network updating. Simulation results validate the effectiveness of our proposed algorithm, which demonstrates superior generalization ability and achieves better performance compared with the discrete decision based deep reinforcement learning methods.

Vehicular computation offloading is a promising paradigm that improves the computing capability of vehicles to support autonomous driving and various on-board infotainment services. Comparing with accessing the remote cloud, distributed vehicle-to-vehicle (V2V) computation offloading is more efficient and suitable for delay-sensitive tasks by taking advantage of vehicular idle computing resources. Due to the high dynamic vehicular environment and the variation of available vehicular computing resources, it is a great challenge to design an effective task offloading mechanism to efficiently utilize vehicular computing resources. In this paper, we investigate the computation task allocation among vehicles, and propose a distributed V2V computation offloading framework, in which wireless channel states and variation of idle computing resources are both considered. Specially, we formulate the task allocation problem as a sequential decision making problem, which can be solved by using deep reinforcement learning. Considering that vehicles with idle computing resources may not share their computing resources voluntarily, we thus propose a dynamic pricing scheme that motivates vehicles to contribute their computing resources according to the price they receive. The performance of designed task allocation mechanism is validated by simulation results which reveal the effectiveness of our mechanism compared to the other algorithms.

Unmanned aerial vehicles (UAVs) have the potential in delivering Internet-of-Things (IoT) services from a great height, creating an airborne domain of the IoT. In this article, we address the problem of autonomous UAV navigation in large-scale complex environments by formulating it as a Markov decision process with sparse rewards and propose an algorithm named deep reinforcement learning (RL) with nonexpert helpers (LwH). In contrast to prior RL-based methods that put huge efforts into reward shaping, we adopt the sparse reward scheme, i.e., a UAV will be rewarded if and only if it completes navigation tasks. Using the sparse reward scheme ensures that the solution is not biased toward potentially suboptimal directions. However, having no intermediate rewards hinders the agent from efficient learning since informative states are rarely encountered. To handle the challenge, we assume that a prior policy (nonexpert helper) that might be of poor performance is available to the learning agent. The prior policy plays the role of guiding the agent in exploring the state space by reshaping the behavior policy used for environmental interaction. It also assists the agent in achieving goals by setting dynamic learning objectives with increasing difficulty. To evaluate our proposed method, we construct a simulator for UAV navigation in large-scale complex environments and compare our algorithm with several baselines. Experimental results demonstrate that LwH significantly outperforms the state-of-the-art algorithms handling sparse rewards and yields impressive navigation policies comparable to those learned in the environment with dense rewards.

Mobile-edge computing (MEC) with energy harvesting (EH) is becoming an emerging paradigm to improve the computation experience for the Internet-of-Things (IoT) devices. For a multidevice multiserver MEC system, the frequently varied harvested energy, along with changeable computation task loads and time-varying computation capacities of servers, increase the system's dynamic. Therefore, each device should learn to make coordinated actions, such as the offloading ratio, local computation capacity, and server selection, to achieve a satisfactory computation quality. Thus, the MEC system with EH devices is highly dynamic and face two challenges: 1) continuous- discrete hybrid action spaces and 2) coordination among devices. To deal with such problem, we propose two deep reinforcement learning (DRL)-based algorithms: 1) hybrid-decision-based actor-critic learning (Hybrid-AC) and 2) multidevice hybrid-AC (MD-Hybrid-AC) for dynamic computation offloading. HybridAC solves the hybrid action space with an improvement of actor-critic architecture, where the actor outputs continuous actions (offloading ratio and local computation capacity) corresponding to every server, and the critic evaluates the continuous actions and outputs the discrete action of server selection. MDHybrid-AC adopts the framework of centralized training with decentralized execution. It learns coordinated decisions by constructing a centralized critic to output server selections, which considers the continuous action policies of all devices. Simulation results show that the proposed algorithms achieve a good balance between consumed time and energy, and have a significant performance improvement compared with baseline offloading policies.

Cooperative detection in multi-agent networks has raised increasing concern for a variety of collaborative applications. Thorough research has been developed assuming exact knowledge about the space or space-time signature vector embedded at the received signal in fixed networks, but most of them fail to apply to a mobile scenario with inaccurate agent positions. In this paper, we propose a direct generalized likelihood ratio test (DGLRT) not only taking the position uncertainty of agents into consideration, but also obtaining the optimal steering vector by directly estimating target and agent positions instead of implementing testing under each possible intermediate parameter combination of range and angle-of-arrival (AOA). Furthermore, we conduct performance analysis on the proposed DGLRT and introduce the notation of effective signal-to-noise ratio (SNR) to measure its detection capability, from which the detection performance loss induced by position uncertainty is revealed. Comparison to the conventional detector demonstrates the superior detection performance of the DGLRT based on direct estimation of target and agent positions.

In this paper, we apply the idea of deep learning to radar waveform recognition. Since the frequency variation with time is the most essential distinction among radar signals with different modulation types, we transform one-dimensional radar signals into time-frequency images (TFIs) using time-frequency analysis and design a convolutional neural network to recognize the frequency variation patterns exhibited in TFIs. Furthermore, we analyze the statistical characteristics of the noise in TFIs and introduce a naive approach to reduce its influence on the frequency variation patterns. Simulation results demonstrate the impressive recognition rate under very low SNR conditions and the strong generalization ability of our proposed recognition method.

Traffic density estimation with vehicular ad hoc networks (VANETs) can facilitate many applications. Traditional density estimation is achieved by counting the number of vehicles occupied in a certain area with inductive loop detectors and cameras, which is applied over limited coverage and brings high cost. In this paper, we propose to fuse vehicle spacing information and and compute average spacing in a specific area during a short period of time for density estimation. The robustness of the proposed scheme against Byzantine attack is then analyzed. Finally, we carry our experiments with U.S. Highway 101 data and the results show that the average spacing estimation is consistent with the real value.

The recently announced Super Wi-Fi Network proposal in United States is aiming to enable Internet access in a nation-wide area. As traditional cable-connected power supply system becomes impractical or costly for a wide range wireless network, new infrastructure deployment for Super Wi-Fi is required. The fast developing Energy Harvesting (EH) techniques receive global attentions for their potential of solving the above power supply problem. It is a critical issue, from the user's perspective, how to make efficient network selection and access strategies. Unlike traditional wireless networks, the battery charge state and tendency in EH based networks have to be taken into account when making network selection and access, which has not been well investigated. In this paper, we propose a practical and efficient framework for multiple base stations access strategy in an EH powered Super Wi-Fi network. We consider the access strategy from the user's perspective, who exploits downlink transmission opportunities from one base station. To formulate the problem, we used Partially Observable Markov Decision Process (POMDP) to model users' observations on the base stations' battery situation and decisions on the base station selection and access. Simulation results show that our methods are efficacious and significantly outperform the traditional widely used CSMA method.

Collaborative spectrum sensing is an effective method to improve detection rates in cognitive radio networks. However, it is vulnerable to spectrum sensing data falsification (SSDF) attacks when malicious secondary users (SUs) report fraudulent sensing data. In order to improve the robustness, numerous attack prevention schemes have been proposed to identify malicious SUs. Nevertheless, most of them neglect to incentivize SUs to send truthful reports. An incentive method based on peer-prediction is proposed to identify malicious suspects, punish attackers, and incentivize SUs to send truthful reports simultaneously for decision fusion. Moreover, continuous peer-prediction derived from the binary case is introduced, which is capable of preventing attacks in the continuous domain. Theoretical analysis and simulation results demonstrate that honest SUs are rewarded for accurate and truthful sensing results, while malicious SUs incur penalty for making falsified sensing reports. A significant improvement of detection rates is obtained by the proposed scheme when there are no more than half of malicious SUs conducting SSDF attacks.

In space-based networks, the data relay satellites can assist low-earth-orbit satellites in relaying data to other satellites or the ground station and improve the real time system throughput. To take full advantage of transmission resource of the cooperative relays, this paper proposes a multiple access and resource allocation strategy, in which relays can receive and transmit simultaneously according to channel characteristics of space-based systems. Based on the queueing theoretic formulation, the stability of the proposed protocol is analyzed and the maximum stable throughput region is derived, which would provide the appropriate guidance for the design of the system optimal control. Simulation results exhibit multiple factors that affect the stable throughput and verify the theoretical analysis.

Privacy issues arising in the process of collecting, publishing and mining individuals' personal data have attracted much attention in recent years. In this paper, we consider a scenario where a data collector collects data from data providers and then publish the data to a data user. To protect data providers' privacy, the data collector performs anonymization on the data. Anonymization usually causes a decline of data utility on which the data user's profit depends, meanwhile, data providers' would provide more data if anonymity is strongly guaranteed. How to make a trade-off between privacy protection and data utility is an important question for data collector. In this paper we model the interactions among data providers/collector/user as a game, and propose a general approach to find the Nash equilibriums of the game. To elaborate the analysis, we also present a specific game formulation which takes k-anonymity as the anonymization method. Simulation results show that the game theoretical analysis can help the data collector to deal with the privacy-utility trade-off.

In this paper, a stepped‐frequency spaceborne/airborne bistatic synthetic aperture radar (SFSA‐BiSAR) configuration is proposed to show to improve the range resolution of BiSAR. First, the geometry and the signal model of SFSA‐BiSAR are formulated, and then an analytical bistatic point target reference spectrum (BPTRS) is derived. Second, based on the developed BPTRS, two imaging algorithms called combination‐before‐focusing algorithm (CBFA) and combination‐after‐focusing algorithm (CAFA) are proposed to obtain BiSAR images with improved range resolution. CBFA uses sub‐band combination to obtain synthetic BPTRS, and then uses a new bistatic frequency‐domain algorithm (BFDA) to obtain the improved BiSAR image, whereas CAFA first uses the BFDA to focus all the sub‐pulses, and then uses sub‐image combination to obtain the improved BiSAR image. Both of the two algorithms can focus the SFSA‐BiSAR signal well and comparison simulations are performed to verify the authors' conclusion. Computation loads are also calculated to compare the two algorithms and show that CAFA uses less floating‐point operations than CBFA. Besides, some important parameters of SFSA‐BiSAR are analysed both theoretically and numerically to provide a reference for system design.

In general detection problems, targets or sources may be present at an unknown direction. This letter proposes a detection scheme for the randomly present case based on the MIMO radar transmit beamspace (TB) technique. An average likelihood ratio (ALR) detector for randomly present target detection is formulated firstly. Then two TB design strategies for different present cases are proposed accordingly to get optimal detectors. Numerical results demonstrate that a significant gain in detection can be achieved by these designs comparing to the conventional methods. Finally, theoretical and numerical analyses illustrate the influence of the transceiver parameters on detection performance.

It is well known that avalanche effect errors in received noisy ciphertexts will cause severe error propagation in block-ciphered encryption systems, thus resulting in a large reduction in the achievable throughput. However, little is known about the statistical properties of the underlying error sequences in decrypted plaintexts in block-ciphered systems when channel errors are present. A rigorous study of the statistical properties of the errors in block-ciphered crypto-systems operating in cipher block chaining (CBC) mode is provided. The equivalent channel transition probability is obtained and then used to derive error statistics including both error weight probabilities and gap distributions. The validity of the theoretical analyses is confirmed by the excellent match with results obtained by simulated data encryption standard (DES)-based and advanced encryption standard (AES)-based crypto-systems operating in CBC mode. The error statistics will be valuable in the design and performance evaluation of communication protocols, as well as in error-control schemes for block-ciphered crypto-systems in the presence of erroneous ciphertexts, where errors are intentionally left to enhance security against passive eavesdroppers.

It has long been held that errors in received noisy ciphertexts should be eliminated using as many as possible powerful error correcting codes in order to reduce the avalanche effect on legitimate users' performance in block ciphered systems. However, the negative effect of erroneous ciphertexts on cryptanalysis by an eavesdropper has not been well understood, nor the possible measurable trade-off between security enhancement and performance degradation under noisy ciphertexts. To address these questions, we have launched a case study in this paper using Data Encryption Standard (DES)-based block ciphers operating in cipher feedback (CFB) mode to show quantitatively the pros and cons of exploiting voluntarily or nonvoluntarily introduced binary errors in ciphertexts of block ciphered systems using our proposed comparison metrics. A serially concatenated scheme with both outer and inner encoder-encipher pairs is proposed which allows us to quantitatively reveal the sacrifice made by legitimate users in its postdecryption capacity, as well as the security improvement factor (SIF) which reflects the additionally required plaintext-ciphertext pairs for eavesdropper's known plaintext attack, in the presence of noise in ciphertexts. Simulation results demonstrate the accuracy of derived approximations of the postdecryption performance for the legitimate receiver.

In this paper, we study the effect of channel errors on the performance of linear cryptanalysis against block ciphered system. We study DES block cipher working in cipher feedback mode (CFB) as a special case. In our model, eavesdropper launches linear attack by querying an oracle which provides her with corrupted ciphertexts over a binary symmetric channel (BSC). A new verification strategy in linear attack has been designed and numerically optimized to allow Eve to mount a successful attack in noisy environments. However, we show that even by utilizing this optimized strategy, there is still possibility of misdetection in Eve's cryptanalysis, which directly depends on the channel degradation level. Numerical results show that the proposed attack strategy lets Eve maintain a high performance even for relatively high noise levels. On the other hand, they suggest that due to Eve's possible failures in her attack, tunable cross over probability of the channel can bring about the lowest performance for Eve as well as a higher security.

This paper considers the problem of end-to-end security enhancement by resorting to deliberate noise injected in ciphertexts. The main goal is to generate a degraded wiretap channel in the application layer over which Wyner-type secrecy encoding is invoked to deliver additional secure information. More specifically, we study secrecy enhancement of the Data Encryption Standard (DES) block cipher working in cipher feedback model (CFB) when adjustable noise is introduced into the encrypted data in an application layer. A verification strategy in the exhaustive search step of the linear attack is designed to allow Eve to mount a successful attack in the noisy environment. Thus, a controllable wiretap channel is created over multiple frames by taking advantage of errors in Eve's cryptanalysis, whose secrecy capacity is found for the case of known channel states at receivers. As a result, additional secure information can be delivered by performing Wyner type secrecy encoding over superframes ahead of encryption. These secrecy bits could be taken as symmetric keys for upcoming frames. Numerical results indicate that a sufficiently large secrecy rate can be achieved by selective noise addition.

The benefits of Amplify-and-Forward (AF) and Decode-and-Forward (DF) cooperative relay for secure communication are investigated within Wyner's wiretap channel. We characterize the secrecy rate when source, destination, relay and eavesdropper all use single antenna and the channel conditions are fix. Both AF and DF cooperative strategies are proved theoretically to be able to facilitate secure communication. Detailed analysis of AF and DF scheme reveals a trade off between secrecy area and request secrecy rate. In addition, secrecy constraints in cooperative secure communication are discussed and are used to explain the differences in AF and DF scheme. Overall, our work establishes the utility of cooperation and compares each advantage of AF and DF scheme in facilitating secure communication over wireless channel.