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.

Templated synthesis of transition metal phosphide electrocatalysts for oxygen and hydrogen evolution reactions

Transition metal phosphides(TMPs)have been regarded as alternative hydrogen evolution reaction(HER)and oxygen evolution reaction(OER)catalysts owing to their comparable activity to those of noble metal-based catalysts.TMPs have been produced in various morphologies,including hollow and porous nanostructures,which are features deemed desirable for electrocatalytic materials.Templated synthesis routes are often responsible for such morphologies.This paper reviews the latest advances and existing challenges in the synthesis of TMP-based OER and HER catalysts through templated methods.A comprehensive review of the structure-property-performance of TMP-based HER and OER catalysts prepared using different templates is presented.The discussion proceeds according to application,first by HER and further divided among the types of templates used-from hard templates,sacrificial templates,and soft templates to the emerging dynamic hydrogen bubble template.OER catalysts are then reviewed and grouped according to their morphology.Finally,prospective research directions for the synthesis of hollow and porous TMP-based catalysts,such as improvements on both activity and stability of TMPs,design of environmentally benign templates and processes,and analysis of the reaction mechanism through advanced material characterization techniques and theoretical calculations,are suggested.

Recent advances in transition metal phosphide materials:Synthesis and applications in supercapacitors

Supercapacitors(SCs)are considered promising energy storge systems because of their outstanding power density,fast charge and discharge rate and long-term cycling stability.The exploitation of cheap and efficient electrode materials is the key to improve the performance of supercapacitors.As the battery-type materials,transition metal phosphides(TMPs)possess high theoretical specific capacity,good electrical conductivity and superior structural stability,which have been extensively studied to be electrode materials for supercapacitors.In this review,we summarize the up-to-date progress on TMPs materials from diversified synthetic methods,diverse nanostructures and several prominent TMPs and their composites in application of supercapacitors.In the end,we also propose the remaining challenges toward the rational discovery and synthesis of high-performance TMP electrodes materials for energy storage.

New Rural Community Construction or Retention Development:A Comparative Analysis of Rural Settlement Transition Mechanism in Plain Agriculture Area of China Based on Actor Network Theory

It is an important way to realize rural revitalization and sustainable development to guide rural settlement transition(RST)in an appropriate way.This paper uses actor network theory(ANT)to construct a theoretical framework for the study of RST.Taking two typical villages with different transition paths in rural areas of North China Plain as examples,this paper reveals the mechanism of RST and makes a comparative analysis.The results show that:1)after identifying problems and obligatory passage point,key actors recruit heterogeneous actors into the actor network by entrusting them with common interests,and realize RST under the system operation.2)Rural settlements under different transition paths have similarities in the problems to be solved,collective actions and policy factors,but there are differences in the transition process,mechanism and effect.The actor network and mechanism of RST through the path of new rural community construction are more complex and the transition effect is more thorough.In contrast,the degree of RST of retention development path is limited if there is no resource and location advantage.3)Based on the applicable conditions of different paths,this paper designs a logical framework of‘Situation-Structure-Behavior-Result’to scientifically guide the identification of RST paths under the background of rural revitalization.

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.

Photodoping-Modified Charge Density Wave Phase Transition in WS_(2)/1T-TaS_(2) Heterostructure

Controlling collective electronic states hold great promise for development of innovative devices. Here, we experimentally detect the modification of the charge density wave(CDW) phase transition within a 1T-TaS_(2) layer in a WS_(2)/1T-TaS_(2) heterostructure using time-resolved ultrafast spectroscopy. Laser-induced charge transfer doping strongly suppresses the commensurate CDW phase, which results in a significant decrease in both the phase transition temperature(T_(c)) and phase transition stiffness. We interpret the phenomenon that photoinduced hole doping, when surpassing a critical threshold value of ~ 10^(18)cm^(-3), sharply decreases the phase transition energy barrier. Our results provide new insights into controlling the CDW phase transition, paving the way for optical-controlled novel devices based on CDW materials.

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.

Unveiling the pressure-driven metal–semiconductor–metal transition in the doped TiS_(2)

Conventional theories expect that materials under pressure exhibit expanded valence and conduction bands,leading to increased electrical conductivity.Here,we report the electrical properties of the doped 1T-TiS_(2) under high pressure by electrical resistance investigations,synchrotron x-ray diffraction,Raman scattering and theoretical calculations.Up to 70 GPa,an unusual metal-semiconductor-metal transition occurs.Our first-principles calculations suggest that the observed anti-Wilson transition from metal to semiconductor at 17 GPa is due to the electron localization induced by the intercalated Ti atoms.This electron localization is attributed to the strengthened coupling between the doped Ti atoms and S atoms,and the Anderson localization arising from the disordered intercalation.At pressures exceeding 30.5 GPa,the doped TiS_(2) undergoes a re-metallization transition initiated by a crystal structure phase transition.We assign the most probable space group as P2_(1)2_(1)2_(1).Our findings suggest that materials probably will eventually undergo the Wilson transition when subjected to sufficient pressure.

Ultrafast Carrier Dynamics in Ba_(6)Cr_(2)S_(10)Modified by Toroidal Magnetic Phase Transition

Ba_(6)Cr_(2)S_(10)is a recently discovered magnetic material,in which the spins are aligned ferromagnetically in the ab-plane and anti-parallelly in a paired form along the c-axis.It is characterized as a quasi-one dimensional(1D)dimerized structure with a ferrotoroidic order,forming the simplest candidate toroidal magnetic(TM)order and exhibiting an anti-ferromagnetic-like transition at around 10 K.Time-resolved ultrafast dynamics investigation of the novel A-Cr-S(A:metal elements)family of quantum materials has rarely been reported.Here,we investigate the time-resolved pump-probe ultrafast dynamics of a Ba6Cr2S10 single crystal.A prominent change in the photo-excited carrier dynamics is observed at T_(c)=10 K,corresponding to the reported TM-paramagnetic phase transition.A potential unknown magnetic transition is also found at T^(*)=29 K.Our results provide new evidence for the TM magnetic transition in Ba_(6)Cr_(2)S_(10),and shed light on phase transitions in TM quantum materials.

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.

Publisher Correction to:Strongly Coupled 2D Transition Metal Chalcogenide‑MXene‑Carbonaceous Nanoribbon Heterostructures with Ultrafast Ion Transport for Boosting Sodium/Potassium Ions Storage

Due to the technical fault,a wrong version of the paper was uploaded.The content of the article was not affected,but the layout of the article was affected.The original article has been corrected.

Advancing neuroscience through real-time processing of big data:Transition from open-loop to closed-loop paradigms

The brain functions as a closed-loop system that continuously generates behavior in response to the external environment and adjusts actions based on the outcomes.Traditional research methodologies in neuroscience,especially those employed in brain imaging experiments,have mainly adopted an open-loop paradigm(Grosenick et al.,2015).Functional neural circuits are analyzed offline and subsequently tested through manipulation of neuronal activities within specific regions or with genetic markers.By establishing a closed-loop research paradigm,functional ensembles can be detected and tested in real time with temporal sequences.These functional ensembles,rather than brain regions or genetically labeled neural populations,serve as fundamental units of neural networks,offering valuable insights into the dissection of neural circuits.The closed-loop research paradigm also enables the capture of high-dimensional activities of internal brain dynamics and precise elucidation of physiological processes such as learning,decision-making,and sleep.

Dissipation-Driven Superradiant Phase Transition of a Two-Dimensional Bose-Einstein Condensate in a Double Cavity

We study superradiant phase transitions in a hybrid system of a two-dimensional Bose–Einstein condensate of atoms and two cavities arranged with a tilt angle.By adjusting the loss rate of cavities,we map out the phase diagram of steady states within a mean field framework.It is found that when the loss rates of the two cavities are different,superradiant transitions may not occur at the same time in the two cavities.A first-order phase transition is observed between the states with only one cavity in superradiance and both in superradiance.In the case that both cavities are superradiant,a net photon current is observed flowing from the cavity with small decay rate to the one with large decay rate.The photon current shows a non-monotonic dependence on the loss rate difference,owing to the competition of photon number difference and cavity field phase difference.Our findings can be realized and detected in experiments.

Evolution of Superconducting-Transition Temperature with Superfluid Density and Conductivity in Pressurized Cuprate Superconductors

What factors fundamentally determine the value of superconducting transition temperature Tc in high temperature superconductors has been the subject of intense debate.Following the establishment of an empirical law known as Homes'law,there is a growing consensus in the community that the Tc value of the cuprate superconductors is closely linked to the superfluid density(ρ_(s))of its ground state and the conductivity(σ)of its normal state.However,all the data supporting this empirical law(ρ_(s)=AσT_(c))have been obtained from the ambientpressure superconductors.In this study,we present the first high-pressure results about the connection of the quantities of ρ_(s) and σ with T_(c),through the studies on the Bi_(1.74)Pb_(0.38)Sr_(1.88)CuO_(6+δ)and Bi_(2)Sr_(2)CaCu_(2)O_(8+δ),in which the value of their high-pressure resistivity(ρ=1/σ)is achieved by adopting our newly established method,while the quantity ofρs is extracted using Homes'law.We highlight that the Tc values are strongly linked to the joint response factors of magnetic field and electric field,i.e.,ρ_(s) and σ,respectively,implying that the physics determining T_(c) is governed by the intrinsic electromagnetic fields of the system.

Pressure-induced magnetic phase and structural transition in SmSb_(2)

Motivated by the recent discovery of unconventional superconductivity around a magnetic quantum critical point in pressurized CeSb_(2),here we present a high-pressure study of an isostructural antiferromagnetic(AFM) SmSb_(2) through electrical transport and synchrotron x-ray diffraction measurements.At P_(C)~2.5 GPa,we found a pressure-induced magnetic phase transition accompanied by a Cmca→P4/nmm structural phase transition.In the pristine AFM phase below P_(C),the AFM transition temperature of SmSb_(2) is insensitive to pressure;in the emergent magnetic phase above P_(C),however,the magnetic critical temperature increases rapidly with increasing pressure.In addition,at ambient pressure,the magnetoresistivity(MR) of SmSb_(2) increases suddenly upon cooling below the AFM transition temperature and presents linear nonsaturating behavior under high field at 2 K.With increasing pressure above P_(C),the MR behavior remains similar to that observed at ambient pressure,both in terms of temperature-and field-dependent MR.This leads us to argue an AFM-like state for SmSb_(2) above P_(C).Within the investigated pressure of up to 45.3 GPa and the temperature of down to 1.8 K,we found no signature of superconductivity in SmSb_(2).

Comprehensive understanding of glioblastoma molecular phenotypes:classification,characteristics,and transition

Among central nervous system-associated malignancies,glioblastoma(GBM)is the most common and has the highest mortality rate.The high heterogeneity of GBM cell types and the complex tumor microenvironment frequently lead to tumor recurrence and sudden relapse in patients treated with temozolomide.In precision medicine,research on GBM treatment is increasingly focusing on molecular subtyping to precisely characterize the cellular and molecular heterogeneity,as well as the refractory nature of GBM toward therapy.Deep understanding of the different molecular expression patterns of GBM subtypes is critical.Researchers have recently proposed tetra fractional or tripartite methods for detecting GBM molecular subtypes.The various molecular subtypes of GBM show significant differences in gene expression patterns and biological behaviors.These subtypes also exhibit high plasticity in their regulatory pathways,oncogene expression,tumor microenvironment alterations,and differential responses to standard therapy.Herein,we summarize the current molecular typing scheme of GBM and the major molecular/genetic characteristics of each subtype.Furthermore,we review the mesenchymal transition mechanisms of GBM under various regulators.

Significantly enhanced thermal stability of HMX by phase-transition lysozyme coating

A new robust bio-inspired route by using lysozyme aqueous solution for surface modification on 1,3,5,7-tetranitro-1,3,5,7-tetrazocane(HMX)was described in this paper.HMX crystals were coated by in situ phase transition of lysozyme(PTL)molecules.The HMX decorated by PTL was characterized by SEM,XRD,FTIR and XPS,demonstrating a dense core-shell coating layer.The coverage of lysozyme on HMX crystal was calculated by the ratio of sulfur content.The surface coverage increased from 60.5% to 93.5% when the content of PTL was changed from 0.5 wt% to 2.0 wt%,indicating efficient coating.The thermal stability of HMX was investigated by in situ XRD and DSC.The thermal phase transition temperature of HMX(β to δ phase)was delayed by 42℃ with 2.0 wt% PTL coating,which prevented HMX from thermal damage and sensitivity by the effect of PTL coating.After heating at 215℃,large cracks appeared in the naked HMX crystal,while the PTL coated HMX still maintained intact,with the impact energy of HMX dropped dramatically from 5 J to 2 J.However,the impact energy of HMX with 1.0 wt% and 2.0 wt% coating content(HMX@PTL-1.0 and HMX@PTL-2.0)was unchanged(5 J).Present results potentially enable large-scale fabrication of polymorphic energetic materials with outstanding thermal stability by novel lysozyme coating.

Temperature-sensing array using the metal-to-insulator transition of Nd_(x)Sm_(1-x)NiO_(3)

Rare-earth nickelates(RENiO_(3))show widely tunable metal-to-insulator transition(MIT)properties with ignorable variations in lattice constants and small latent heat across the critical temperature(TMIT).Particularly,it is worth noting that compared with the more commonly investigated vanadium oxides,the MIT of RENiO_(3)is less abrupt but usually across a wider range of temperatures.This sheds light on their alternative applications as negative temperature coefficient resistance(NTCR)thermistors with high sensitivity compared with the current NTCR thermistors,other than their expected use as critical temperature resistance thermistors.In this work,we demonstrate the NTCR thermistor functionality for using the adjustable MIT of Nd_(x)Sm_(1-x)NiO_(3)within 200–400 K,which displays larger magnitudes of NTCR(e.g.,more than 7%/K)that is unattainable in traditional NTCR thermistor materials.The temperature dependence of resistance(R–T)shows sharp variation during the MIT of Nd_(x)Sm_(1-x)NiO_(3)with no hysteresis via decreasing the Nd content(e.g.,x≤0.8),and such a R–T tendency can be linearized by introducing an optimum parallel resistor.The sensitive range of temperature can be further extended to 210–360 K by combining a series of Nd_(x)Sm_(1-x)NiO_(3)with eight rare-earth co-occupation ratios as an array,with a high magnitude of NTCR(e.g.,7%–14%/K)covering the entire range of temperatures.

Mass-Based Environmental Factor and Energy Assessment of Microwave-Assisted Synthesized Transition Metal Nanostructures

This paper describes mass-based energy phase-space projection of microwave-assisted synthesis of transition metals (zinc oxide, palladium, silver, platinum, and gold) nanostructures. The projection uses process energy budget (measured in kJ) on the horizontal axes and process density (measured in kJg−1) on the vertical axes. These two axes allow both mass usage efficiency (Environmental-Factor) and energy efficiency to be evaluated for a range of microwave applicator and metal synthesis. The metrics are allied to the: second, sixth and eleventh principle of the twelve principle of Green Chemistry. This analytical approach to microwave synthesis (widely considered as a useful Green Chemistry energy source) allows a quantified dynamic environmental quotient to be given to renewable plant-based biomass associated with the reduction of the metal precursors. Thus allowing a degree of quantification of claimed “eco-friendly” and “sustainable” synthesis with regard to waste production and energy usage.