Toward Trustworthy Decision-Making for Autonomous Vehicles:A Robust Reinforcement Learning Approach with Safety Guarantees

While autonomous vehicles are vital components of intelligent transportation systems,ensuring the trustworthiness of decision-making remains a substantial challenge in realizing autonomous driving.Therefore,we present a novel robust reinforcement learning approach with safety guarantees to attain trustworthy decision-making for autonomous vehicles.The proposed technique ensures decision trustworthiness in terms of policy robustness and collision safety.Specifically,an adversary model is learned online to simulate the worst-case uncertainty by approximating the optimal adversarial perturbations on the observed states and environmental dynamics.In addition,an adversarial robust actor-critic algorithm is developed to enable the agent to learn robust policies against perturbations in observations and dynamics.Moreover,we devise a safety mask to guarantee the collision safety of the autonomous driving agent during both the training and testing processes using an interpretable knowledge model known as the Responsibility-Sensitive Safety Model.Finally,the proposed approach is evaluated through both simulations and experiments.These results indicate that the autonomous driving agent can make trustworthy decisions and drastically reduce the number of collisions through robust safety policies.

UAV maneuvering decision-making algorithm based on deep reinforcement learning under the guidance of expert experience

Autonomous umanned aerial vehicle(UAV) manipulation is necessary for the defense department to execute tactical missions given by commanders in the future unmanned battlefield. A large amount of research has been devoted to improving the autonomous decision-making ability of UAV in an interactive environment, where finding the optimal maneuvering decisionmaking policy became one of the key issues for enabling the intelligence of UAV. In this paper, we propose a maneuvering decision-making algorithm for autonomous air-delivery based on deep reinforcement learning under the guidance of expert experience. Specifically, we refine the guidance towards area and guidance towards specific point tasks for the air-delivery process based on the traditional air-to-surface fire control methods.Moreover, we construct the UAV maneuvering decision-making model based on Markov decision processes(MDPs). Specifically, we present a reward shaping method for the guidance towards area and guidance towards specific point tasks using potential-based function and expert-guided advice. The proposed algorithm could accelerate the convergence of the maneuvering decision-making policy and increase the stability of the policy in terms of the output during the later stage of training process. The effectiveness of the proposed maneuvering decision-making policy is illustrated by the curves of training parameters and extensive experimental results for testing the trained policy.

Autonomous air combat decision-making of UAV based on parallel self-play reinforcement learning

Aiming at addressing the problem of manoeuvring decision-making in UAV air combat,this study establishes a one-to-one air combat model,defines missile attack areas,and uses the non-deterministic policy Soft-Actor-Critic(SAC)algorithm in deep reinforcement learning to construct a decision model to realize the manoeuvring process.At the same time,the complexity of the proposed algorithm is calculated,and the stability of the closed-loop system of air combat decision-making controlled by neural network is analysed by the Lyapunov function.This study defines the UAV air combat process as a gaming process and proposes a Parallel Self-Play training SAC algorithm(PSP-SAC)to improve the generalisation performance of UAV control decisions.Simulation results have shown that the proposed algorithm can realize sample sharing and policy sharing in multiple combat environments and can significantly improve the generalisation ability of the model compared to independent training.

Communication-Efficient Decision-Making of Digital Twin Assisted Internet of Vehicles: A Hierarchical Multi-Agent Reinforcement Learning Approach

The connected autonomous vehicle is considered an effective way to improve transport safety and efficiency.To overcome the limited sensing and computing capabilities of individual vehicles,we design a digital twin assisted decision-making framework for Internet of Vehicles,by leveraging the integration of communication,sensing and computing.In this framework,the digital twin entities residing on edge can effectively communicate and cooperate with each other to plan sub-targets for their respective vehicles,while the vehicles only need to achieve the sub-targets by generating a sequence of atomic actions.Furthermore,we propose a hierarchical multiagent reinforcement learning approach to implement the framework,which can be trained in an end-to-end way.In the proposed approach,the communication interval of digital twin entities could adapt to timevarying environment.Extensive experiments on driving decision-making have been performed in traffic junction scenarios of different difficulties.The experimental results show that the proposed approach can largely improve collaboration efficiency while reducing communication overhead.

Evolutionary Decision-Making and Planning for Autonomous Driving Based on Safe and Rational Exploration and Exploitation

Decision-making and motion planning are extremely important in autonomous driving to ensure safe driving in a real-world environment.This study proposes an online evolutionary decision-making and motion planning framework for autonomous driving based on a hybrid data-and model-driven method.First,a data-driven decision-making module based on deep reinforcement learning(DRL)is developed to pursue a rational driving performance as much as possible.Then,model predictive control(MPC)is employed to execute both longitudinal and lateral motion planning tasks.Multiple constraints are defined according to the vehicle’s physical limit to meet the driving task requirements.Finally,two principles of safety and rationality for the self-evolution of autonomous driving are proposed.A motion envelope is established and embedded into a rational exploration and exploitation scheme,which filters out unreasonable experiences by masking unsafe actions so as to collect high-quality training data for the DRL agent.Experiments with a high-fidelity vehicle model and MATLAB/Simulink co-simulation environment are conducted,and the results show that the proposed online-evolution framework is able to generate safer,more rational,and more efficient driving action in a real-world environment.

UAV-Assisted Dynamic Avatar Task Migration for Vehicular Metaverse Services: A Multi-Agent Deep Reinforcement Learning Approach

Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metaverses. However, avatar tasks include a multitude of human-to-avatar and avatar-to-avatar interactive applications, e.g., augmented reality navigation,which consumes intensive computing resources. It is inefficient and impractical for vehicles to process avatar tasks locally. Fortunately, migrating avatar tasks to the nearest roadside units(RSU)or unmanned aerial vehicles(UAV) for execution is a promising solution to decrease computation overhead and reduce task processing latency, while the high mobility of vehicles brings challenges for vehicles to independently perform avatar migration decisions depending on current and future vehicle status. To address these challenges, in this paper, we propose a novel avatar task migration system based on multi-agent deep reinforcement learning(MADRL) to execute immersive vehicular avatar tasks dynamically. Specifically, we first formulate the problem of avatar task migration from vehicles to RSUs/UAVs as a partially observable Markov decision process that can be solved by MADRL algorithms. We then design the multi-agent proximal policy optimization(MAPPO) approach as the MADRL algorithm for the avatar task migration problem. To overcome slow convergence resulting from the curse of dimensionality and non-stationary issues caused by shared parameters in MAPPO, we further propose a transformer-based MAPPO approach via sequential decision-making models for the efficient representation of relationships among agents. Finally, to motivate terrestrial or non-terrestrial edge servers(e.g., RSUs or UAVs) to share computation resources and ensure traceability of the sharing records, we apply smart contracts and blockchain technologies to achieve secure sharing management. Numerical results demonstrate that the proposed approach outperforms the MAPPO approach by around 2% and effectively reduces approximately 20% of the latency of avatar task execution in UAV-assisted vehicular Metaverses.

Recent Progress in Reinforcement Learning and Adaptive Dynamic Programming for Advanced Control Applications

Reinforcement learning(RL) has roots in dynamic programming and it is called adaptive/approximate dynamic programming(ADP) within the control community. This paper reviews recent developments in ADP along with RL and its applications to various advanced control fields. First, the background of the development of ADP is described, emphasizing the significance of regulation and tracking control problems. Some effective offline and online algorithms for ADP/adaptive critic control are displayed, where the main results towards discrete-time systems and continuous-time systems are surveyed, respectively.Then, the research progress on adaptive critic control based on the event-triggered framework and under uncertain environment is discussed, respectively, where event-based design, robust stabilization, and game design are reviewed. Moreover, the extensions of ADP for addressing control problems under complex environment attract enormous attention. The ADP architecture is revisited under the perspective of data-driven and RL frameworks,showing how they promote ADP formulation significantly.Finally, several typical control applications with respect to RL and ADP are summarized, particularly in the fields of wastewater treatment processes and power systems, followed by some general prospects for future research. Overall, the comprehensive survey on ADP and RL for advanced control applications has d emonstrated its remarkable potential within the artificial intelligence era. In addition, it also plays a vital role in promoting environmental protection and industrial intelligence.

Orientation and Decision-Making for Soccer Based on Sports Analytics and AI:A Systematic Review

Due to ever-growing soccer data collection approaches and progressing artificial intelligence(AI) methods, soccer analysis, evaluation, and decision-making have received increasing interest from not only the professional sports analytics realm but also the academic AI research community. AI brings gamechanging approaches for soccer analytics where soccer has been a typical benchmark for AI research. The combination has been an emerging topic. In this paper, soccer match analytics are taken as a complete observation-orientation-decision-action(OODA) loop.In addition, as in AI frameworks such as that for reinforcement learning, interacting with a virtual environment enables an evolving model. Therefore, both soccer analytics in the real world and virtual domains are discussed. With the intersection of the OODA loop and the real-virtual domains, available soccer data, including event and tracking data, and diverse orientation and decisionmaking models for both real-world and virtual soccer matches are comprehensively reviewed. Finally, some promising directions in this interdisciplinary area are pointed out. It is claimed that paradigms for both professional sports analytics and AI research could be combined. Moreover, it is quite promising to bridge the gap between the real and virtual domains for soccer match analysis and decision-making.

Ethical Decision-Making Framework Based on Incremental ILP Considering Conflicts

Humans are experiencing the inclusion of artificial agents in their lives,such as unmanned vehicles,service robots,voice assistants,and intelligent medical care.If the artificial agents cannot align with social values or make ethical decisions,they may not meet the expectations of humans.Traditionally,an ethical decision-making framework is constructed by rule-based or statistical approaches.In this paper,we propose an ethical decision-making framework based on incremental ILP(Inductive Logic Programming),which can overcome the brittleness of rule-based approaches and little interpretability of statistical approaches.As the current incremental ILP makes it difficult to solve conflicts,we propose a novel ethical decision-making framework considering conflicts in this paper,which adopts our proposed incremental ILP system.The framework consists of two processes:the learning process and the deduction process.The first process records bottom clauses with their score functions and learns rules guided by the entailment and the score function.The second process obtains an ethical decision based on the rules.In an ethical scenario about chatbots for teenagers’mental health,we verify that our framework can learn ethical rules and make ethical decisions.Besides,we extract incremental ILP from the framework and compare it with the state-of-the-art ILP systems based on ASP(Answer Set Programming)focusing on conflict resolution.The results of comparisons show that our proposed system can generate better-quality rules than most other systems.

Distributed Graph Database Load Balancing Method Based on Deep Reinforcement Learning

This paper focuses on the scheduling problem of workflow tasks that exhibit interdependencies.Unlike indepen-dent batch tasks,workflows typically consist of multiple subtasks with intrinsic correlations and dependencies.It necessitates the distribution of various computational tasks to appropriate computing node resources in accor-dance with task dependencies to ensure the smooth completion of the entire workflow.Workflow scheduling must consider an array of factors,including task dependencies,availability of computational resources,and the schedulability of tasks.Therefore,this paper delves into the distributed graph database workflow task scheduling problem and proposes a workflow scheduling methodology based on deep reinforcement learning(DRL).The method optimizes the maximum completion time(makespan)and response time of workflow tasks,aiming to enhance the responsiveness of workflow tasks while ensuring the minimization of the makespan.The experimental results indicate that the Q-learning Deep Reinforcement Learning(Q-DRL)algorithm markedly diminishes the makespan and refines the average response time within distributed graph database environments.In quantifying makespan,Q-DRL achieves mean reductions of 12.4%and 11.9%over established First-fit and Random scheduling strategies,respectively.Additionally,Q-DRL surpasses the performance of both DRL-Cloud and Improved Deep Q-learning Network(IDQN)algorithms,with improvements standing at 4.4%and 2.6%,respectively.With reference to average response time,the Q-DRL approach exhibits a significantly enhanced performance in the scheduling of workflow tasks,decreasing the average by 2.27%and 4.71%when compared to IDQN and DRL-Cloud,respectively.The Q-DRL algorithm also demonstrates a notable increase in the efficiency of system resource utilization,reducing the average idle rate by 5.02%and 9.30%in comparison to IDQN and DRL-Cloud,respectively.These findings support the assertion that Q-DRL not only upholds a lower average idle rate but also effectively curtails the average response time,thereby substantially improving processing efficiency and optimizing resource utilization within distributed graph database systems.

Stroke Risk Assessment Decision-Making Using a Machine Learning Model:Logistic-AdaBoost

Stroke is a chronic cerebrovascular disease that carries a high risk.Stroke risk assessment is of great significance in preventing,reversing and reducing the spread and the health hazards caused by stroke.Aiming to objectively predict and identify strokes,this paper proposes a new stroke risk assessment decision-making model named Logistic-AdaBoost(Logistic-AB)based on machine learning.First,the categorical boosting(CatBoost)method is used to perform feature selection for all features of stroke,and 8 main features are selected to form a new index evaluation system to predict the risk of stroke.Second,the borderline synthetic minority oversampling technique(SMOTE)algorithm is applied to transform the unbalanced stroke dataset into a balanced dataset.Finally,the stroke risk assessment decision-makingmodel Logistic-AB is constructed,and the overall prediction performance of this new model is evaluated by comparing it with ten other similar models.The comparison results show that the new model proposed in this paper performs better than the two single algorithms(logistic regression and AdaBoost)on the four indicators of recall,precision,F1 score,and accuracy,and the overall performance of the proposed model is better than that of common machine learning algorithms.The Logistic-AB model presented in this paper can more accurately predict patients’stroke risk.

QoS Routing Optimization Based on Deep Reinforcement Learning in SDN

To enhance the efficiency and expediency of issuing e-licenses within the power sector, we must confront thechallenge of managing the surging demand for data traffic. Within this realm, the network imposes stringentQuality of Service (QoS) requirements, revealing the inadequacies of traditional routing allocation mechanismsin accommodating such extensive data flows. In response to the imperative of handling a substantial influx of datarequests promptly and alleviating the constraints of existing technologies and network congestion, we present anarchitecture forQoS routing optimizationwith in SoftwareDefinedNetwork (SDN), leveraging deep reinforcementlearning. This innovative approach entails the separation of SDN control and transmission functionalities, centralizingcontrol over data forwardingwhile integrating deep reinforcement learning for informed routing decisions. Byfactoring in considerations such as delay, bandwidth, jitter rate, and packet loss rate, we design a reward function toguide theDeepDeterministic PolicyGradient (DDPG) algorithmin learning the optimal routing strategy to furnishsuperior QoS provision. In our empirical investigations, we juxtapose the performance of Deep ReinforcementLearning (DRL) against that of Shortest Path (SP) algorithms in terms of data packet transmission delay. Theexperimental simulation results show that our proposed algorithm has significant efficacy in reducing networkdelay and improving the overall transmission efficiency, which is superior to the traditional methods.

Reinforcement learning based edge computing in B5G

The development of communication technology will promote the application of Internet of Things,and Beyond 5G will become a new technology promoter.At the same time,Beyond 5G will become one of the important supports for the development of edge computing technology.This paper proposes a communication task allocation algorithm based on deep reinforcement learning for vehicle-to-pedestrian communication scenarios in edge computing.Through trial and error learning of agent,the optimal spectrum and power can be determined for transmission without global information,so as to balance the communication between vehicle-to-pedestrian and vehicle-to-infrastructure.The results show that the agent can effectively improve vehicle-to-infrastructure communication rate as well as meeting the delay constraints on the vehicle-to-pedestrian link.

Multi-UAV cooperative maneuver decision-making for pursuitevasion using improved MADRL

Aiming at the problem of multi-UAV pursuit-evasion confrontation, a UAV cooperative maneuver method based on an improved multi-agent deep reinforcement learning(MADRL) is proposed. In this method, an improved Comm Net network based on a communication mechanism is introduced into a deep reinforcement learning algorithm to solve the multi-agent problem. A layer of gated recurrent unit(GRU) is added to the actor-network structure to remember historical environmental states. Subsequently,another GRU is designed as a communication channel in the Comm Net core network layer to refine communication information between UAVs. Finally, the simulation results of the algorithm in two sets of scenarios are given, and the results show that the method has good effectiveness and applicability.

Reinforcement Learning in Process Industries:Review and Perspective

This survey paper provides a review and perspective on intermediate and advanced reinforcement learning(RL)techniques in process industries. It offers a holistic approach by covering all levels of the process control hierarchy. The survey paper presents a comprehensive overview of RL algorithms,including fundamental concepts like Markov decision processes and different approaches to RL, such as value-based, policy-based, and actor-critic methods, while also discussing the relationship between classical control and RL. It further reviews the wide-ranging applications of RL in process industries, such as soft sensors, low-level control, high-level control, distributed process control, fault detection and fault tolerant control, optimization,planning, scheduling, and supply chain. The survey paper discusses the limitations and advantages, trends and new applications, and opportunities and future prospects for RL in process industries. Moreover, it highlights the need for a holistic approach in complex systems due to the growing importance of digitalization in the process industries.

Role Dynamic Allocation of Human-Robot Cooperation Based on Reinforcement Learning in an Installation of Curtain Wall

A real-time adaptive roles allocation method based on reinforcement learning is proposed to improve humanrobot cooperation performance for a curtain wall installation task.This method breaks the traditional idea that the robot is regarded as the follower or only adjusts the leader and the follower in cooperation.In this paper,a self-learning method is proposed which can dynamically adapt and continuously adjust the initiative weight of the robot according to the change of the task.Firstly,the physical human-robot cooperation model,including the role factor is built.Then,a reinforcement learningmodel that can adjust the role factor in real time is established,and a reward and actionmodel is designed.The role factor can be adjusted continuously according to the comprehensive performance of the human-robot interaction force and the robot’s Jerk during the repeated installation.Finally,the roles adjustment rule established above continuously improves the comprehensive performance.Experiments of the dynamic roles allocation and the effect of the performance weighting coefficient on the result have been verified.The results show that the proposed method can realize the role adaptation and achieve the dual optimization goal of reducing the sum of the cooperator force and the robot’s Jerk.

Unleashing the Power of Multi-Agent Reinforcement Learning for Algorithmic Trading in the Digital Financial Frontier and Enterprise Information Systems

In the rapidly evolving landscape of today’s digital economy,Financial Technology(Fintech)emerges as a trans-formative force,propelled by the dynamic synergy between Artificial Intelligence(AI)and Algorithmic Trading.Our in-depth investigation delves into the intricacies of merging Multi-Agent Reinforcement Learning(MARL)and Explainable AI(XAI)within Fintech,aiming to refine Algorithmic Trading strategies.Through meticulous examination,we uncover the nuanced interactions of AI-driven agents as they collaborate and compete within the financial realm,employing sophisticated deep learning techniques to enhance the clarity and adaptability of trading decisions.These AI-infused Fintech platforms harness collective intelligence to unearth trends,mitigate risks,and provide tailored financial guidance,fostering benefits for individuals and enterprises navigating the digital landscape.Our research holds the potential to revolutionize finance,opening doors to fresh avenues for investment and asset management in the digital age.Additionally,our statistical evaluation yields encouraging results,with metrics such as Accuracy=0.85,Precision=0.88,and F1 Score=0.86,reaffirming the efficacy of our approach within Fintech and emphasizing its reliability and innovative prowess.

Combining reinforcement learning with mathematical programming:An approach for optimal design of heat exchanger networks

Heat integration is important for energy-saving in the process industry.It is linked to the persistently challenging task of optimal design of heat exchanger networks(HEN).Due to the inherent highly nonconvex nonlinear and combinatorial nature of the HEN problem,it is not easy to find solutions of high quality for large-scale problems.The reinforcement learning(RL)method,which learns strategies through ongoing exploration and exploitation,reveals advantages in such area.However,due to the complexity of the HEN design problem,the RL method for HEN should be dedicated and designed.A hybrid strategy combining RL with mathematical programming is proposed to take better advantage of both methods.An insightful state representation of the HEN structure as well as a customized reward function is introduced.A Q-learning algorithm is applied to update the HEN structure using theε-greedy strategy.Better results are obtained from three literature cases of different scales.

Safety-Constrained Multi-Agent Reinforcement Learning for Power Quality Control in Distributed Renewable Energy Networks

This paper examines the difficulties of managing distributed power systems,notably due to the increasing use of renewable energy sources,and focuses on voltage control challenges exacerbated by their variable nature in modern power grids.To tackle the unique challenges of voltage control in distributed renewable energy networks,researchers are increasingly turning towards multi-agent reinforcement learning(MARL).However,MARL raises safety concerns due to the unpredictability in agent actions during their exploration phase.This unpredictability can lead to unsafe control measures.To mitigate these safety concerns in MARL-based voltage control,our study introduces a novel approach:Safety-ConstrainedMulti-Agent Reinforcement Learning(SC-MARL).This approach incorporates a specialized safety constraint module specifically designed for voltage control within the MARL framework.This module ensures that the MARL agents carry out voltage control actions safely.The experiments demonstrate that,in the 33-buses,141-buses,and 322-buses power systems,employing SC-MARL for voltage control resulted in a reduction of the Voltage Out of Control Rate(%V.out)from0.43,0.24,and 2.95 to 0,0.01,and 0.03,respectively.Additionally,the Reactive Power Loss(Q loss)decreased from 0.095,0.547,and 0.017 to 0.062,0.452,and 0.016 in the corresponding systems.

Reinforcement learning based adaptive control for uncertain mechanical systems with asymptotic tracking

This paper mainly focuses on the development of a learning-based controller for a class of uncertain mechanical systems modeled by the Euler-Lagrange formulation.The considered system can depict the behavior of a large class of engineering systems,such as vehicular systems,robot manipulators and satellites.All these systems are often characterized by highly nonlinear characteristics,heavy modeling uncertainties and unknown perturbations,therefore,accurate-model-based nonlinear control approaches become unavailable.Motivated by the challenge,a reinforcement learning(RL)adaptive control methodology based on the actor-critic framework is investigated to compensate the uncertain mechanical dynamics.The approximation inaccuracies caused by RL and the exogenous unknown disturbances are circumvented via a continuous robust integral of the sign of the error(RISE)control approach.Different from a classical RISE control law,a tanh(·)function is utilized instead of a sign(·)function to acquire a more smooth control signal.The developed controller requires very little prior knowledge of the dynamic model,is robust to unknown dynamics and exogenous disturbances,and can achieve asymptotic output tracking.Eventually,co-simulations through ADAMS and MATLAB/Simulink on a three degrees-of-freedom(3-DOF)manipulator and experiments on a real-time electromechanical servo system are performed to verify the performance of the proposed approach.