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.

Bird species composition and conservation challenges in the Gaoligong Mountains, one of the most diverse bird areas in the world

The Gaoligong Mountains(GLGM),located in southwestern China,extend north to south along the western border of the Hengduan Mountains,spanning approximately 600 km.In this study,we consolidated findings from 17 bird surveys conducted in the GLGM between 2010 and 2022.We found that the GLGM harbors tremendous bird diversity,with a total of 796 documented bird species in the region.Nearly a quarter(23.0%)of these species are listed as state key protected species or as Chinese and global threatened species.Analysis of species richness at the county level showed a decreasing trend with increasing latitude,with the greatest diversity in Yingjiang(661 species).Observations indicated that the GLGM belongs to the Oriental realm,primarily composed of bird species from southern and southwestern China.The GLGM plays an important role in avian conservation by sheltering exceptional bird diversity,providing corridors and flyways for bird migration and dispersal,and mitigating the effects of climate change.In response to the conservation needs of birds and other wildlife,the Chinese government has established numerous protected areas within the GLGM.Despite these efforts,avian conservation still faces considerable challenges in the GLGM due to limitations in the protected area network,transboundary nature of the regions,and existing gaps in monitoring and research.

Achievements and challenges of primate conservation in China

The dual impact of climate change and human activities has precipitated a sharp decline in primate biodiversity globally.China is home to the most diverse primate species in the Northern hemisphere,which face severe ecological threats due to the expansion of modern agriculture,extensive exploitation and consumption of natural resources,and excessive land development during its transition from an agricultural to a modern society.In response,China has implemented various ecological conservation measures,including habitat restoration and protection.These efforts have made substantial strides in biodiversity conservation,with certain regions witnessing an increase in primate populations.In the current study,we conducted a systematic review of historical documents and field research data related to Chinese primates,evaluating the endangered status of primate species in China.Despite improvements in the habitats of most primate species and some population growth,many species still face severe threats,including declining and small populations.Species such as the Myanmar snub-nosed monkey(Rhinopithecus strykeri),eastern black crested gibbon(Nomascus nasutus),and Hainan gibbon(N.hainanus)remain particularly vulnerable due to their limited distribution ranges and extremely small populations.Insufficient scientific data,fragmented information,and not enough studies in conservation biology further compound the challenges.Moreover,there is a notable lack of detailed population monitoring data for species such as the Bengal slow loris(Nycticebus bengalensis),pygmy slow loris(N.pygmaeus),Indochinese gray langur(Trachypithecus crepusculus),Shortridge’s langur(T.shortridgei),and capped langur(T.pileatus),which hinders the development of practical and targeted conservation management strategies.Therefore,for national biodiversity conservation,there is an urgent need for specialized primate surveys,enhancing habitat protection and restoration,and increasing focus on cross-border conservation strategies and regional cooperation.There is also a need to establish a comprehensive and systematic research database platform,conduct continuous and in-depth research in primate biology,and actively engage in the scientific assessment of ecotourism.Additionally,strengthening public awareness and education on wildlife conservation remains essential.Such integrated and systematic efforts will provide scientific support for the current and future conservation and management of primate species in China.

Mammals of Gaoligong Mountain in China:Diversity,distribution,and conservation

Gaoligong Mountain(hereafter,GLGM)is located at the intersection of Myanmar and China’s Yunnan Province and Xizang Zizhiqu,and spans three globally significant biodiversity hotspots:the Himalayas,Indo-Burma,and the Mountains of Southwest China.Although surveys of mammals in this ecologically important region have a long history,there is no comprehensive systematic checklist and distribution account of the mammals of GLGM.Here,we compiled a mammal species checklist of GLGM based on thorough field investigations and literature reviews.We also examined specimen collections and applied camera trapping surveys to explore the region’s mammal diversity and distribution patterns.We recorded 212 mammal species in nine orders,33 families,and 119 genera,which accounts for 30.5%of China’s mammal species,and a high proportion of nationally protected(50)and globally threatened(29)species.Mammal species richness showed a symmetrical unimodal curve along the elevation gradient,peaking at intermediate elevations(2000 to 2500 m above sea level(asl)),and increasing generally from south to north,slightly higher in the east slope than in the west.Cluster analysis and non-metric multidimensional scaling revealed three distinct elevational assemblages(<900 m asl.,900-3500 m asl.,and>3500 m asl)and significant south-to-north variation,but no substantial differences between the east and west slopes.The GLGM present a unique conservation value due to the high proportions of rare and endangered mammal species,complex faunal composition,high endemism,and being the distribution boundary for many species.This study is an important phased account of mammal diversity in GLGM and makes a prospect for future research.

Diversity of Orchids in Terms of Their Distribution, Uses and Conservation in Annapurna Conservation Area of Nepal

The Annapurna Conservation Area (ACA), the first conservation area and the largest protected area (PA) in Nepal, is incredibly rich in biodiversity. Notwithstanding this, orchids in the ACA have not been explored enough yet thus making the need for ambitious research to be carried out. Previous study only included 81 species of orchids within ACA. This study aims to update the record of species and genera richness in the ACA. In total 198 species of orchids, belonging to 67 genera (40% and 62% of the total recorded orchid species and genera in Nepal) has been recorded in ACA. This represents an increase of 144% in species and 56% in genera over the previous data. Out of the 198 species, 99 were epiphytes, 6 were holomycotrophic and 93 were terrestrial. Among the 67 genera, Bulbophyllum (17) species were dominant, followed by Dendrobium (16), Herminium (10), Coelogyne, Plantanthera (9 each), Eria, Habenaria, Oberonia (8 each), Calanthe (7), and Liparis (6). Fifty-six species were found to be ornamentally significant and 85 species medicinally significant.

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.

Assessing the conservation impact of Chinese indigenous chicken populations between ex-situ and in-situ using genome-wide SNPs

Conservation programs require rigorous evaluation to ensure the preservation of genetic diversity and viability of conservation populations. In this study, we conducted a comparative analysis of two indigenous Chinese chicken breeds, Gushi and Xichuan black-bone, using whole-genome SNPs to understand their genetic diversity, track changes over time and population structure. The breeds were divided into five conservation populations(GS1, 2010, ex-situ;GS2, 2019, ex-situ;GS3, 2019, in-situ;XB1, 2010, in-situ;and XB2, 2019, in-situ) based on conservation methods and generations. The genetic diversity indices of three conservation populations of Gushi chicken showed consistent trends, with the GS3 population under in-situ strategy having the highest diversity and GS2 under ex-situ strategy having the lowest. The degree of inbreeding of GS2 was higher than that of GS1 and GS3. Conserved populations of Xichuan black-bone chicken showed no obvious changes in genetic diversity between XB1 and XB2. In terms of population structure, the GS3 population were stratified relative to GS1 and GS2. According to the conservation priority, GS3 had the highest contribution to the total gene and allelic diversity in GS breed, whereas the contribution of XB1 and XB2 were similar. We also observed that the genetic diversity of GS2 was lower than GS3, which were from the same generation but under different conservation programs(in-situ and ex-situ). While XB1 and XB2 had similar levels of genetic diversity. Overall, our findings suggested that the conservation programs performed in ex-situ could slow down the occurrence of inbreeding events, but could not entirely prevent the loss of genetic diversity when the conserved population size was small, while in-situ conservation populations with large population size could maintain a relative high level of genetic diversity.

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.

Nonuniform Dependence on the Initial Data for Solutions of Conservation Laws

In this paper,we study systems of conservation laws in one space dimension.We prove that for classical solutions in Sobolev spaces H^(s),with s>3/2,the data-to-solution map is not uniformly continuous.Our results apply to all nonlinear scalar conservation laws and to nonlinear hyperbolic systems of two equations.

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.

A LOW-REGULARITY FOURIER INTEGRATOR FOR THE DAVEY-STEWARTSON II SYSTEM WITH ALMOST MASS CONSERVATION

In this work,we propose a low-regularity Fourier integrator with almost mass conservation to solve the Davey-StewartsonⅡsystem(hyperbolic-elliptic case).Arbitrary order mass convergence could be achieved by the suitable addition of correction terms,while keeping the first order accuracy in H~γ×H^(γ+1)for initial data in H^(γ+1)×H^(γ+1)withγ>1.The main theorem is that,up to some fixed time T,there exist constantsτ_(0)and C depending only on T and‖u‖_(L^(∞)((0,T);H^(γ+1)))such that,for any 0<τ≤τ_(0),we have that‖u(t_(n),·)-u^(n)‖H_γ≤C_(τ),‖v(t_(n),·)-v^(n)‖_(Hγ+1)≤C_(τ),where u^(n)and v^(n)denote the numerical solutions at t_(n)=nτ.Moreover,the mass of the numerical solution M(u^(n))satisfies that|M(u^(n))-M(u_0)|≤Cτ~5.

Dimension by Dimension Finite Volume HWENO Method for Hyperbolic Conservation Laws

In this paper,we propose a finite volume Hermite weighted essentially non-oscillatory(HWENO)method based on the dimension by dimension framework to solve hyperbolic conservation laws.It can maintain the high accuracy in the smooth region and obtain the high resolution solution when the discontinuity appears,and it is compact which will be good for giving the numerical boundary conditions.Furthermore,it avoids complicated least square procedure when we implement the genuine two dimensional(2D)finite volume HWENO reconstruction,and it can be regarded as a generalization of the one dimensional(1D)HWENO method.Extensive numerical tests are performed to verify the high resolution and high accuracy of the scheme.

Conservation genomic investigation of an endangered conifer,Thuja sutchuenensis,reveals low genetic diversity but also low genetic load

Endangered species generally have small populations with low genetic diversity and a high genetic load.Thuja sutchuenensis is an endangered conifer endemic to southwestern China.It was once considered extinct in the wild,but in 1999 was rediscovered.However,little is known about its genetic load.We collected 67 individuals from five wild,isolated T.sutchuenensis populations,and used 636,151 SNPs to analyze the level of genetic diversity and genetic load in T.sutchuenensis to delineate the conservation units of T.sutchuenensis,based on whole transcriptome sequencing data,as well as target capture sequencing data.We found that populations of T.sutchuenensis could be divided into three groups.These groups had low levels genetic diversity and were moderately genetically differentiated.Our findings also indicate that T.sutchuenensis suffered two severe bottlenecks around the Last Glaciation Period and Last Glacial Maximum.Among Thuja species,T.sutchuenensis presented the lowest genetic load and hence might have purged deleterious mutations efficiently through purifying selection.However,distribution of fitness effects analysis indicated a high extinction risk for T.sutchuenensis.Multiple lines of evidence identified three management units for T.sutchuenensis.Although T.sutchuenensis possesses a low genetic load,low genetic diversity,suboptimal fitness,and anthropogenic pressures all present an extinction risk for this rare conifer.This might also hold true for many endangered plant species in the mountains all over the world.

The Current Conservation Efforts and Future Prospects for the Endangered Nubian Ibex (Capra nubiana ibex) in Sudan

A comprehensive action plan for the conservation of the endangered species, the Nubian ibex in Sudan, can be developed by gaining a thorough understanding of their current status, conservation strategy, and relevant laws and regulations, as well as raising awareness about the importance of protecting endangered species. The Nubian ibex is listed as an endangered species on The International Union for Conservation of Nature (IUCN) Red List, highlighting the need for further research on population conservation efforts due to insufficient population data. To address this knowledge gap, a questionnaire was conducted with various stakeholders, including police officers, researchers, and lecturers, representing a diverse range of organizations and universities. The findings revealed that hunting is the primary factor contributing to endangerment. Mammals account for 80% of endangered species, while reptiles comprise less than one-tenth. Research centers are recognized as the main governing body, and 85% of participants are concerned about the declining population. Hunting accounted for less than half of the threats to the ibex population in Sudan, while habitat loss made up a quarter. Mining, climate change, human activity, and agriculture were also identified as risks. However, there were no plans, strategies, procedures, or measures in place to conserve the Nubian ibex. There were also no initiatives to preserve its biodiversity, and awareness about endangered species was lacking. Although participants believed that laws were effective in protecting the ibex, no licenses were issued for its conservation, and annual surveys were not conducted. Additionally, there were no recorded instances of Mukhalfat related to the Nubian ibex. In light of these findings, we propose various conservation measures to address these challenges. These measures include the implementation of laws and regulations, conducting annual surveys to monitor population trends, protecting habitats, establishing breeding and releasing programs, launching awareness campaigns, undertaking rehabilitation efforts, enhancing research efforts, and developing comprehensive conservation strategies. Additionally, it is crucial to foster cooperation among wildlife institutes to ensure the effective implementation of these conservation measures.

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.

ENERGY CONSERVATION FOR THE WEAK SOLUTIONS TO THE 3D COMPRESSIBLE NEMATIC LIQUID CRYSTAL FLOW

In this paper,we establish some regularity conditions on the density and velocity fields to guarantee the energy conservation of the weak solutions for the three-dimensional compressible nematic liquid crystal flow in the periodic domain.

Fertilization and Soil Ploughing Practices under Changing Physical Environment Lead to Soil Organic Carbon Dynamics under Conservation Agriculture in Rice-Wheat Cropping System: A Scoping Review

Ploughing and fertilization practices in rice-wheat system have deteriorated the soil carbon (C) pools. Conservation agriculture (CA) based management approaches have proven to enhance C sequestration and reverse the loss of soil-organic-carbon (SOC), which further enhances soil fertility. Different fractions of SOC pools react to the alterations in management practices and indicate changes in SOC dynamics as compared to total C in the soil. Higher SOC levels in soil have been observed in case of reduced/no-till (NT) practices than conventional tillage (CT). However, between CT and zero tillage/NT, total SOC stocks diminished with an increase in soil depth, which demonstrated that the benefits of SOC are more pronounced in the topsoil under NT. Soil aggregation provides physical protection to C associated with different-sized particles, thus, the improvement in soil aggregation through CA is an effective way to mitigate soil C loss. Along with less soil disturbance, residual management, suitable crop rotation, rational application of manures and fertilizers, and integrated nutrient management have been found to be effective in not only improving soil C stock but also enhancing the soil health and productivity. Thus, CA can be considered as a potential method in the build-up of SOC of soil in rice-wheat system.