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.

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.

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.

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.

Enhancing Energy Efficiency with a Dynamic Trust Measurement Scheme in Power Distribution Network

The application of Intelligent Internet of Things(IIoT)in constructing distribution station areas strongly supports platform transformation,upgrade,and intelligent integration.The sensing layer of IIoT comprises the edge convergence layer and the end sensing layer,with the former using intelligent fusion terminals for real-time data collection and processing.However,the influx of multiple low-voltage in the smart grid raises higher demands for the performance,energy efficiency,and response speed of the substation fusion terminals.Simultaneously,it brings significant security risks to the entire distribution substation,posing a major challenge to the smart grid.In response to these challenges,a proposed dynamic and energy-efficient trust measurement scheme for smart grids aims to address these issues.The scheme begins by establishing a hierarchical trust measurement model,elucidating the trust relationships among smart IoT terminals.It then incorporates multidimensional measurement factors,encompassing static environmental factors,dynamic behaviors,and energy states.This comprehensive approach reduces the impact of subjective factors on trust measurements.Additionally,the scheme incorporates a detection process designed for identifying malicious low-voltage end sensing units,ensuring the prompt identification and elimination of any malicious terminals.This,in turn,enhances the security and reliability of the smart grid environment.The effectiveness of the proposed scheme in pinpointing malicious nodes has been demonstrated through simulation experiments.Notably,the scheme outperforms established trust metric models in terms of energy efficiency,showcasing its significant contribution to the field.

The Spherical q-Linear Diophantine Fuzzy Multiple-Criteria Group Decision-Making Based on Differential Measure

Spherical q-linearDiophantine fuzzy sets(Sq-LDFSs)provedmore effective for handling uncertainty and vagueness in multi-criteria decision-making(MADM).It does not only cover the data in two variable parameters but is also beneficial for three parametric data.By Pythagorean fuzzy sets,the difference is calculated only between two parameters(membership and non-membership).According to human thoughts,fuzzy data can be found in three parameters(membership uncertainty,and non-membership).So,to make a compromise decision,comparing Sq-LDFSs is essential.Existing measures of different fuzzy sets do,however,can have several flaws that can lead to counterintuitive results.For instance,they treat any increase or decrease in the membership degree as the same as the non-membership degree because the uncertainty does not change,even though each parameter has a different implication.In the Sq-LDFSs comparison,this research develops the differentialmeasure(DFM).Themain goal of the DFM is to cover the unfair arguments that come from treating different types of FSs opposing criteria equally.Due to their relative positions in the attribute space and the similarity of their membership and non-membership degrees,two Sq-LDFSs formthis preference connectionwhen the uncertainty remains same in both sets.According to the degree of superiority or inferiority,two Sq-LDFSs are shown as identical,equivalent,superior,or inferior over one another.The suggested DFM’s fundamental characteristics are provided.Based on the newly developed DFM,a unique approach tomultiple criterion group decision-making is offered.Our suggestedmethod verifies the novel way of calculating the expert weights for Sq-LDFSS as in PFSs.Our proposed technique in three parameters is applied to evaluate solid-state drives and choose the optimum photovoltaic cell in two applications by taking uncertainty parameter zero.The method’s applicability and validity shown by the findings are contrasted with those obtained using various other existing approaches.To assess its stability and usefulness,a sensitivity analysis is done.

OsNPF3.1,a nitrate,abscisic acid and gibberellin transporter gene,is essential for rice tillering and nitrogen utilization efficiency

Low-affinity nitrate transporter genes have been identified in subfamilies 4-8 of the rice nitrate transporter 1(NRT1)/peptide transporter family(NPF),but the OsNPF3 subfamily responsible for nitrate and phytohormone transport and rice growth and development remains unknown.In this study,we described OsNPF3.1 as an essential nitrate and phytohormone transporter gene for rice tillering and nitrogen utilization efficiency(NUtE).OsNPF3.1 possesses four major haplotypes of its promoter sequence in 517 cultivars,and its expression is positively associated with tiller number.Its expression was higher in the basal part,culm,and leaf blade than in other parts of the plant,and was strongly induced by nitrate,abscisic acid(ABA)and gibberellin 3(GA_3)in the root and shoot of rice.Electrophysiological experiments demonstrated that OsNPF3.1 is a pH-dependent low-affinity nitrate transporter,with rice protoplast uptake assays showing it to be an ABA and GA_3 transporter.OsNPF3.1 overexpression significantly promoted ABA accumulation in the roots and GA accumulation in the basal part of the plant which inhibited axillary bud outgrowth and rice tillering,especially at high nitrate concentrations.The NUtE of OsNPF3.1-overexpressing plants was enhanced under low and medium nitrate concentrations,whereas the NUtE of OsNPF3.1 clustered regularly interspaced short palindromic repeats(CRISPR)plants was increased under high nitrate concentrations.The results indicate that OsNPF3.1 transports nitrate and phytohormones in different rice tissues under different nitrate concentrations.The altered OsNPF3.1 expression improves NUtE in the OsNPF3.1-overexpressing and CRISPR lines at low and high nitrate concentrations,respectively.

The Impact of Privatization on Terminal Efficiency: A Case Study of Tema Port

Port and terminal efficiency are of utmost importance to the container shipping industry due to their significance in enhancing the competitive advantage of ports within a region. Consequently, there have always been notable variations of studies around it. This paper analyzes the impact of privatization on terminal efficiency using the Port of Tema as a Case Study. The main objective of this paper is to analyze the efficiency trends of the public and private terminals in the port over the years. To achieve this objective, DEA-CCR methodology was employed to calculate the annual technical efficiency trends of the private and public terminals using four input variables and three output variables. The main results of the paper indicated that the public and private terminals were efficient for multiple years. However, the efficiency scores over the years demonstrated inconsistency, exhibiting notable fluctuations. The findings of this study will aid policymakers across the region on policies relating to the efficiency and ownership structure of ports and terminals.

A NovelMethod for Determining Tourism Carrying Capacity in a Decision-Making Context Using q−Rung Orthopair Fuzzy Hypersoft Environment

Tourism is a popular activity that allows individuals to escape their daily routines and explore new destinations for various reasons,including leisure,pleasure,or business.A recent study has proposed a unique mathematical concept called a q−Rung orthopair fuzzy hypersoft set(q−ROFHS)to enhance the formal representation of human thought processes and evaluate tourism carrying capacity.This approach can capture the imprecision and ambiguity often present in human perception.With the advanced mathematical tools in this field,the study has also incorporated the Einstein aggregation operator and score function into the q−ROFHS values to supportmultiattribute decision-making algorithms.By implementing this technique,effective plans can be developed for social and economic development while avoiding detrimental effects such as overcrowding or environmental damage caused by tourism.A case study of selected tourism carrying capacity will demonstrate the proposed methodology.

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.

Mg-doped,carbon-coated,and prelithiated SiO_(x) as anode materials with improved initial Coulombic efficiency for lithium-ion batteries

Silicon suboxide(SiO_(x),x≈1)is promising in serving as an anode material for lithium-ion batteries with high capacity,but it has a low initial Coulombic efficiency(ICE)due to the irreversible formation of lithium silicates during the first cycle.In this work,we modify SiO_(x) by solid-phase Mg doping reaction using low-cost Mg powder as a reducing agent.We show that Mg reduces SiO_(2) in SiO_(x) to Si and forms MgSiO_(3) or Mg_(2)SiO_(4).The MgSiO_(3) or Mg_(2)SiO_(4) are mainly distributed on the surface of SiO_(x),which suppresses the irreversible lithium-ion loss and enhances the ICE of SiO_(x).However,the formation of MgSiO_(3) or Mg_(2)SiO_(4) also sacrifices the capacity of SiO_(x).Therefore,by controlling the reaction process between Mg and SiO_(x),we can tune the phase composition,proportion,and morphology of the Mg-doped SiO_(x) and manipulate the performance.We obtain samples with a capacity of 1226 mAh g^(–1) and an ICE of 84.12%,which show significant improvement over carbon-coated SiO_(x) without Mg doping.By the synergistical modification of both Mg doping and prelithiation,the capacity of SiO_(x) is further increased to 1477 mAh g^(–1) with a minimal compromise in the ICE(83.77%).

Multifunctional interfacial molecular bridge enabled by an aggregation-induced emission strategy for enhancing efficiency and UV stability of perovskite solar cells

The interface defects between the electron transport layer(ETL)and the perovskite layer,as well as the low ultraviolet(UV)light utilization rate of the perovskite absorption layer,pose significant challenges for the commercialization of perovskite solar cells(PSCs).To address this issue,this paper proposes an innovative multifunctional interface modulation strategy by introducing aggregation-induced emission(AIE)molecule 5-[4-[1,2,2-tri[4-(3,5-dicarboxyphenyl)phenyl]ethylene]phenyl]benzene-1,3-dicarboxylic acid(H_(8)ETTB)at the SnO_(2)ETL/perovskite interface.Firstly,the interaction of H_(8)ETTB with the SnO_(2)surface,facilitated by its carboxyl groups,is effective in passivating surface defects caused by noncoord inated Sn and O vacancies.This interaction enhances the conductivity of the SnO_(2)film and adjusts energy levels,leading to enhanced charge carrier transport.Simultaneously,H_(8)ETTB can passivate noncoord inated Pb^(2+)ions at the perovskite interface,promoting perovskite crystallization and reducing the interface energy barrier,resulting in a perovskite film with low defects and high crystalline quality.More importantly,the H_(8)ETTB molecule,can convert UV light into light absorbable by the perovskite,thereby reducing damage caused by UV light and improving the device's utilization of UV.Consequently,the champion PSC based on SnO_(2)-H_(8)ETTB achieves an impressing efficiency of 23.32%and significantly improved photostability compared with the control device after continuous exposure to intense UV radiation.In addition,the Cs_(0.05)(FA_(0.95)MA_(0.05))_(0.95)Pb(I_(0.95)Br_(0.05))_(3)based device can achieve maximum efficiency of 24.01%,demonstrating the effectiveness and universality of this strategy.Overall,this innovative interface bridging strategy effectively tackles interface defects and low UV light utilization in PSCs,presenting a promising approach for achieving highly efficient and stable PSCs.

High Energy Efficiency Dynamic Connected Hybrid Precoding for mm Wave Massive MIMO Systems

This paper considers a high energy efficiency dynamic connected(HEDC)structure,which promotes the practicability and reduces the power consumption of hybrid precoding system by lowresolution phase shifters(PSs).Based on the proposed structure,a new hybrid precoding algorithm is presented to optimize the energy efficiency,namely,HP-HEDC algorithm.Firstly,via a new defined effective optimal precoding matrix,the problem of optimizing the analog switch precoding matrix is formulated as a sparse representation problem.Thus,the optimal analog switch precoding matrix can be readily obtained by the branch-and-bound method.Then,the digital precoding matrix optimization problem is modeled as a dictionary update problem and solved by the method of optimal direction(MOD).Finally,the diagonal entries of the analog PS precoding matrix are optimized by exhaustive search independently since PS and antenna is one-to-one.Simulation results show that the HEDC structure enjoys low power consumption and satisfactory spectral efficiency.The proposed algorithm presents at least 50%energy efficiency improvement compared with other algorithms when the PS resolution is set as 3-bit.

Optimizing the power conversion processes in diluted donor/acceptor heterojunctions towards 19.4%efficiency all-polymer solar cells

All polymer solar cells(all-PSCs)promise mechanically-flexible and morphologically-stable organic photovoltaics and have aroused increased interests very recently.However,due to their disorderly conformation structures within the photoactive film,inefficient charge generation and carrier transport are observed which lead to inferior photovoltaic performance compared to smaller molecular acceptor-based photovoltaics.Here,by diluting PM6 with a cutting-edge polymeric acceptor PY-IT and diluting PY-IT with PM6 or D18,donor-dominating or acceptor-dominating heterojunctions were prepared.Synchrotron X-ray and multiple spectrometer techniques reveal that the diluted heterojunctions receive increased structural order,translating to enhanced carrier mobility,improved exciton diffusion length,and suppressed non-radiative recombination loss during the power conversion.As the results,the corresponding PM6+1%PY-IT/PY-IT+1%D18 and PM6+1%PY-IT/PY-IT+1%PM6 devices fabricated by layer-by-layer deposition received superior power conversion efficiency(PCE)of 19.4%and 18.8%respectively,along with enhanced operational lifetimes in air,outperforming the PCE of 17.5%in the PM6/PY-IT reference device.

Cooperative activation of sodium channels for downgrading the energy efficiency in neuronal information processing

The Hodgkin–Huxley model assumes independent ion channel activation,although mutual interactions are common in biological systems.This raises the problem why neurons would favor independent over cooperative channel activation.In this study,we evaluate how cooperative activation of sodium channels affects the neuron’s information processing and energy consumption.Simulations of the stochastic Hodgkin–Huxley model with cooperative activation of sodium channels show that,while cooperative activation enhances neuronal information processing capacity,it greatly increases the neuron’s energy consumption.As a result,cooperative activation of sodium channel degrades the energy efficiency for neuronal information processing.This discovery improves our understanding of the design principles for neural systems,and may provide insights into future designs of the neuromorphic computing devices as well as systematic understanding of pathological mechanisms for neural diseases.

High-Efficiency Dynamic Scanning Strategy for Powder Bed Fusion by Controlling Temperature Field of the Heat-Affected Zone

Improvement of fabrication efficiency and part performance was the main challenge for the large-scale powder bed fusion(PBF)process.In this study,a dynamic monitoring and feedback system of powder bed temperature field using an infrared thermal imager has been established and integrated into a four-laser PBF equipment with a working area of 2000 mm×2000 mm.The heat-affected zone(HAZ)temperature field has been controlled by adjusting the scanning speed dynamically.Simultaneously,the relationship among spot size,HAZ temperature,and part performance has been established.The fluctuation of the HAZ temperature in four-laser scanning areas was decreased from 30.85℃to 17.41℃.Thus,the consistency of the sintering performance of the produced large component has been improved.Based on the controllable temperature field,a dynamically adjusting strategy for laser spot size was proposed,by which the fabrication efficiency was improved up to 65.38%.The current research results were of great significance to the further industrial applications of large-scale PBF equipment.

Technical efficiency of cocoa farms at varying elevation levels in Davao City, Philippines: implications to sustainable upland farming systems

Elevation is one of many components that influence agriculture, and this in turn affects the level of both inputs and outputs of farmers. This article focuses on the productivity and technical efficiency of 100 cocoa farms using cross-sectional data from areas ranging from 190 to 1021 m above sea level which were classified as low, medium, and high elevation in Davao City, considered as the chocolate capital of the Philippines. Using stochastic frontier analysis, the results showed that the cost of inputs per ha and the number of cocoa trees per ha significantly increase yield. Farms at high elevations were less technically efficient, as this entails lower temperatures and increased rainfall, and cocoa farming in those areas and conditions can be more challenging, especially with changes in farming practices, terrain, and distance to markets. Other significant variables were age of cocoa farms, married farmers, and age of the farmers. Older farms may be more developed, farmers who are married benefit from their spouses being able to readily contribute as farm labor, and lastly, older farmers' inefficiency may likely stem from nonadaptation of newer farming practices. With an average technical efficiency of 0.61, 0.63, and 0.26 in low, medium, and high elevation areas, respectively, farmers therefore have an incentive to improve farm practices and consider topographical variations found in high elevation areas. Recommendations for the improvement of technical efficiency of cocoa farms are better connectivity to markets, enhancing farm practices, and continuation and improvement of government programs on cocoa with an added emphasis on research. For farmers in high elevation areas, mitigating solutions such as sustainable agriculture practices and ecolabelling are key to improving efficiency and minimizing the potential negative impact on upland farming systems. Moreover, such adaptation measures may also contribute to sustainability of cocoa farming in high elevation areas.

A hierarchical salt-rejection strategy for sustainable and high-efficiency solar-driven desalination

Solar steam generation(SSG)is widely regarded as one of the most sustainable technologies for seawater desalination.However,salt fouling severely compromises the evaporation performance and lifetime of evaporators,limiting their practical applications.Herein,we propose a hierarchical salt-rejection(HSR)strategy to prevent salt precipitation during long-term evaporation while maintaining a rapid evaporation rate,even in high-salinity brine.The salt diffusion process is segmented into three steps—insulation,branching diffusion,and arterial transport—that significantly enhance the salt-resistance properties of the evaporator.Moreover,the HSR strategy overcomes the tradeoff between salt resistance and evaporation rate.Consequently,a high evaporation rate of 2.84 kg m^(-2) h^(-1),stable evaporation for 7 days cyclic tests in 20 wt%NaCl solution,and continuous operation for 170 h in natural seawater under 1 sun illumination were achieved.Compared with control evaporators,the HSR evaporator exhibited a>54%enhancement in total water evaporation mass during 24 h continuous evaporation in 20 wt%salt water.Furthermore,a water collection device equipped with the HSR evaporator realized a high water purification rate(1.1 kg m^(-2) h^(-1)),highlighting its potential for agricultural applications.

Reheat effect on the improvement in efficiency of the turbine driven by pulse detonation

Due to the strong unsteadiness of pulse detonation,large flow losses are generated when the detonation wave interacts with the turbine blades,resulting in low turbine efficiency.Considering that the flow losses are dissipated into the gas as heat energy,some of them can be recycled during the expansion process in subsequent stages by the reheat effect,which should be helpful to improve the detonationdriven turbine efficiency.Taking this into account,this paper developed a numerical model of the detonation chamber coupled with a two-stage axial turbine,and a stoichiometric hydrogen-air mixture was used.The improvement in turbine efficiency attributable to the reheat effect was calculated by comparing the average efficiency of the stages with the efficiency of the two-stage turbine.The research indicated that the first stage was critical in suppressing the flow unsteadiness caused by pulse detonation,which stabilized the intake condition of the second stage and consequently allowed much of the flow losses from the first stage to be recycled,so that the efficiency of the two-stage turbine was improved.At a 95%confidence level,the efficiency improvement was stable at 4.5%—5.3%,demonstrating that the reheat effect is significant in improving the efficiency of the detonation-driven turbine.