In this paper, we propose a novel Deep Reinforcement Learning (DRL) algorithm which can navigate non-holonomic robots with continuous control in an unknown dynamic environment with moving obstacles. We call the approach MK-A3C (Memory and Knowledge-based Asynchronous Advantage Actor-Critic) for short. As its first component, MK-A3C builds a GRU-based memory neural network to enhance the robot’s capability for temporal reasoning. Robots without it tend to suffer from a lack of rationality in face of incomplete and noisy estimations for complex environments. Additionally, robots with certain memory ability endowed by MK-A3C can avoid local minima traps by estimating the environmental model. Secondly, MK-A3C combines the domain knowledge-based reward function and the transfer learning-based training task architecture, which can solve the non-convergence policies problems caused by sparse reward. These improvements of MK-A3C can efficiently navigate robots in unknown dynamic environments, and satisfy kinetic constraints while handling moving objects. Simulation experiments show that compared with existing methods, MK-A3C can realize successful robotic navigation in unknown and challenging environments by outputting continuous acceleration commands.

Since the submarine has become the major threat to maritime security, there is an urgent need to find a more efficient method of anti-submarine warfare (ASW). The digital twin theory is one of the most outstanding information technologies, and has been quite popular in recent years. The most influential change produced by digital twin is the ability to enable real-time dynamic interactions between the simulation world and the real world. Digital twin can be regarded as a paradigm by means of which selected online measurements are dynamically assimilated into the simulation world, with the running simulation model guiding the real world adaptively in reverse. By combining digital twin theory and random finite sets (RFSs) closely, a new framework of sensor control in ASW is proposed. Two key algorithms are proposed for supporting the digital twin-based framework. First, the RFS-based data-assimilation algorithm is proposed for online assimilating the sequence of real-time measurements with detection uncertainty, data association uncertainty, noise, and clutters. Second, the computation of the reward function by using the results of the proposed data-assimilation algorithm is introduced to find the optimal control action. The results of three groups of experiments successfully verify the feasibility and effectiveness of the proposed approach.

In modern training, entertainment and education applications, behavior trees (BTs) have already become a fantastic alternative to finite state machines (FSMs) in modeling and controlling autonomous agents. However, it is expensive and inefficient to create BTs for various task scenarios manually. Thus, the genetic programming (GP) approach has been devised to evolve BTs automatically but only received limited success. The standard GP approaches to evolve BTs fail to scale up and to provide good solutions, while GP approaches with domain-specific constraints can accelerate learning but need significant knowledge engineering effort. In this paper, we propose a modified approach, named evolving BTs with hybrid constraints (EBT-HC), to improve the evolution of BTs for autonomous agents. We first propose a novel idea of dynamic constraint based on frequent sub-trees mining, which can accelerate evolution by protecting preponderant behavior sub-trees from undesired crossover. Then we introduce the existing ‘static’ structural constraint into our dynamic constraint to form the evolving BTs with hybrid constraints. The static structure can constrain expected BT form to reduce the size of the search space, thus the hybrid constraints would lead more efficient learning and find better solutions without the loss of the domain-independence. Preliminary experiments, carried out on the Pac-Man game environment, show that the hybrid EBT-HC outperforms other approaches in facilitating the BT design by achieving better behavior performance within fewer generations. Moreover, the generated behavior models by EBT-HC are human readable and easy to be fine-tuned by domain experts.

Wireless rechargeable sensor networks (WRSNs) are promising in maintaining sustainable large-area monitoring tasks. Mobile chargers (MCs) are commonly used in WRSNs to replenish energy to nodes due to its flexibility and easy maintenance. Most existing works on WRSNs focus on designing offline or model-based online charging methods, which need the exact system information to conduct the optimization. However, in practical WRSNs, the exact system information such as the nodes' locations and energy consumption rates may not be easily accessible to the optimizer due to their unpredictability and high dynamics. Thus, in this work, we jointly optimize the MC's trajectory design and charging scheduling in a general and practical WRSN with inaccessibility to the exact system information, such that the charging utility of the MC is maximized. To address this problem, we introduce the model-free reinforcement learning (RL) technique, which enables the MC to learn to jointly optimize its moving trajectory and charging scheduling by interacting with the environment and tracking feedback signals from nodes and obstacles in real time. Specifically, we develop a soft actor-critic based mobile security policy intervened algorithm (SAC-MSPI) based on a novel safe RL framework, which maximizes the MC's charging utility while maintaining the safe movement (not hitting obstacles) for the MC during the entire charging period. Extensive evaluation results show that the proposed SAC-MSPI algorithm outperforms existing main RL solutions and traditional algorithms with respect to the charging utility maximization as well as the collision avoidance.

To address the communication burden issues associated with Federated Learning (FL), Decentralized Federated Learning (DFL) discards the central server and establishes a decentralized communication network, where each client communicates only with neighboring clients. However, existing DFL methods still suffer from two major challenges: local inconsistency and local heterogeneous overfitting, which existing DFL methods have not fundamentally addressed. To tackle these issues, we propose novel DFL algorithms, DFedADMM and its enhanced version DFedADMM-SAM, to improve the performance for DFL. The DFedADMM algorithm employs primal-dual optimization (ADMM) by utilizing dual variables to control the model inconsistency raised from the decentralized heterogeneous data distributions. The DFedADMM-SAM algorithm further improves on DFedADMM by employing a Sharpness-Aware Minimization (SAM) optimizer, which uses gradient perturbations to generate locally flat models and searches for models with uniformly low loss values to mitigate local heterogeneous overfitting. Theoretically, we derive convergence rates of $\mathcal {O}(\frac{1}{\sqrt{KT}}+\frac{1}{KT(1-\psi )^{2}})$ and $ \mathcal {O}(\frac{1}{\sqrt{KT}}+\frac{1}{KT(1-\psi )^{2}}+ \frac{1}{T^{3/2}K^{1/2}})$ in the non-convex setting for DFedADMM and DFedADMM-SAM, respectively, where $1 - \psi$ represents the spectral gap of the gossip matrix. Empirically, extensive experiments on MNIST, CIFAR10, and CIFAR100 datasets demonstrate that our algorithms exhibit superior performance in terms of generalization, convergence speed, and communication overhead compared to existing state-of-the-art (SOTA) optimizers in DFL.

Since an individual approach can hardly navigate robots through complex environments, we present a novel two-level hierarchical framework called JPS-IA3C (Jump Point Search improved Asynchronous Advantage Actor-Critic) in this paper for robot navigation in dynamic environments through continuous controlling signals. Its global planner JPS+ (P) is a variant of JPS (Jump Point Search), which efficiently computes an abstract path of neighboring jump points. These nodes, which are seen as subgoals, completely rid Deep Reinforcement Learning (DRL)-based controllers of notorious local minima. To satisfy the kinetic constraints and be adaptive to changing environments, we propose an improved A3C (IA3C) algorithm to learn the control policies of the robots’ local motion. Moreover, the combination of modified curriculum learning and reward shaping helps IA3C build a novel reward function framework to avoid learning inefficiency because of sparse reward. We additionally strengthen the robots’ temporal reasoning of the environments by a memory-based network. These improvements make the IA3C controller converge faster and become more adaptive to incomplete, noisy information caused by partial observability. Simulated experiments show that compared with existing methods, this JPS-IA3C hierarchy successfully outputs continuous commands to accomplish large-range navigation tasks at shorter paths and less time through reasonable subgoal selection and rational motions.