Task allocation for munition swarms is constrained by reachable region limitations and real-time requirements.This paper proposes a reachable region guided distributed coalition formation game(RRGDCF)method to address...Task allocation for munition swarms is constrained by reachable region limitations and real-time requirements.This paper proposes a reachable region guided distributed coalition formation game(RRGDCF)method to address these issues.To enable efficient online task allocation,a reachable region prediction strategy based on fully connected neural networks(FCNNs)is developed.This strategy integrates high-fidelity data generated from the golden section method and low-fidelity data from geometric approximation in an optimal mixing ratio to form multi-fidelity samples,significantly enhancing prediction accuracy and efficiency under limited high-fidelity samples.These predictions are then incorporated into the coalition formation game framework.A tabu search mechanism guided by the reachable region center directs munitions to execute tasks within their respective reachable regions,mitigating redundant operations on ineffective coalition structures.Furthermore,an adaptive guidance coalition formation strategy optimizes allocation plans by leveraging the hit probabilities of munitions,replacing traditional random coalition formation methods.Simulation results demonstrate that RRGDCF surpasses the contract network protocol and traditional coalition formation game algorithms in optimality and computational efficiency.Hardware experiments further validate the method's practicality in dynamic scenarios.展开更多
The concept of the spacecraft Reachable Domain(RD)has garnered significant scholarly attention due to its crucial role in space situational awareness and on-orbit service applications.While the existing research has l...The concept of the spacecraft Reachable Domain(RD)has garnered significant scholarly attention due to its crucial role in space situational awareness and on-orbit service applications.While the existing research has largely focused on single-impulse RD analysis,the challenge of Multi-Impulse RD(MIRD)remains a key area of interest.This study introduces a methodology for the precise calculation of spacecraft MIRD.The reachability constraints specific to MIRD are first formulated through coordinate transformations.Two restricted maneuvering strategies are examined.The derivation of two extremum conditions allows for determining the accessible orientation range and the nodes encompassing the MIRD.Subsequently,four nonlinear programming models are developed to address two types of MIRD by skillfully relaxing constraints using scale factors.Numerical results validate the robustness and effectiveness of the proposed approach,showing substantial agreement with Monte Carlo simulations and confirming its applicability to spacecraft on various elliptical orbits.展开更多
This paper studies the reachability problem of the switched linear discrete singular （SLDS） systems. Under the condition that all subsystems are regular, the reachability of the SLDS systems is characterized based o...This paper studies the reachability problem of the switched linear discrete singular （SLDS） systems. Under the condition that all subsystems are regular, the reachability of the SLDS systems is characterized based on a peculiar repeatedly introduced switching sequence. The necessary and sufficient conditions are obtained for the reachability of the SLDS systems.展开更多
Reachability graph is a very important tool to analyze the dynamic properties of Petri nets, but the concurrent relation of transitions in Petri nets cannot be represented by reachability graph. Petri net is a concurr...Reachability graph is a very important tool to analyze the dynamic properties of Petri nets, but the concurrent relation of transitions in Petri nets cannot be represented by reachability graph. Petri net is a concurrent system, while reachability graph is a serial one. However, concurrency is a kind of property which is not only very significant but also difficult to be analyzed and controlled. This paper presents the concepts of concurrent reachable marking and concurrent reachable graph in order to represent and analyze the concurrent system. The algorithm constructing concurrent reachable marking set and concurrent reachability graph is also shown so that we can study the response problems among services in a network computing environment and analyze the throughput of the system. The Dining Philosophers Problem, which is a classic problem of describing the management of concurrent resources, is given as an example to illustrate the significance of concurrent reachability graph.展开更多
A novel reachable set（RS） model is developed within a framework of exoatmospheric interceptor engagement analysis. The boost phase steering scheme and trajectory distortion mechanism of the interceptor are firstly e...A novel reachable set（RS） model is developed within a framework of exoatmospheric interceptor engagement analysis. The boost phase steering scheme and trajectory distortion mechanism of the interceptor are firstly explored. A mathematical model of the distorted RS is then formulated through a dimension–reduction analysis. By treating the outer boundary of the RS on sphere surface as a spherical convex hull, two relevant theorems are proposed and the RS envelope is depicted by the computational geometry theory. Based on RS model, the algorithms of intercept window analysis and launch parameters determination are proposed, and numerical simulations are carried out for interceptors with different energy or launch points. Results show that the proposed method can avoid intensive on-line computation and provide an accurate and effective approach for interceptor engagement analysis. The suggested RS model also serves as a ready reference to other related problems such as interceptor effectiveness evaluation and platform disposition.展开更多
Using Baire metric, this paper proposes a generalized framework of transition system approximation by developing the notions of approximate reachability and approximate bisimulation equivalences. The proposed framewor...Using Baire metric, this paper proposes a generalized framework of transition system approximation by developing the notions of approximate reachability and approximate bisimulation equivalences. The proposed framework captures the traditional exact equivalence as a special case. Approximate reachability equivalence is coarser than approximate bisimulation equivalence, just like the hierarchy of the exact ones. Both approximate equivalences satisfy the transitive property, consequently, they can be used in transition system approximation.展开更多
For spacecraft formation flight,the information of relative motion reachable set is very important,which can be used to predict the operating boundary of adjacent spacecraft and thus to ensure the safety of spacecraft...For spacecraft formation flight,the information of relative motion reachable set is very important,which can be used to predict the operating boundary of adjacent spacecraft and thus to ensure the safety of spacecraft operation.In this paper,we aim at developing a numerical method to approximate the reachable set for spacecraft relative motion.In particular,we focus on the quality of the approximation and the computational cost.Based on the bang-bang control principle,a polyhedral approximation algorithm is proposed to compute the reachable set of a relative motion spacecraft system.An inner approximation and an outer approximation of the reachable set for the system can be obtained.We prove that the approximation quality measured in Hausdorff distance can be guaranteed.The method is easy to implement and has low computational cost.Finally,the effectiveness of the algorithm is demonstrated by experimental simulation.展开更多
It is important to calculate the reachable domain(RD)of the manned lunar mission to evaluate whether a lunar landing site could be reached by the spacecraft. In this paper, the RD of free return orbits is quickly eval...It is important to calculate the reachable domain(RD)of the manned lunar mission to evaluate whether a lunar landing site could be reached by the spacecraft. In this paper, the RD of free return orbits is quickly evaluated and calculated via the classification and regression neural networks. An efficient databasegeneration method is developed for obtaining eight types of free return orbits and then the RD is defined by the orbit’s inclination and right ascension of ascending node(RAAN) at the perilune. A classify neural network and a regression network are trained respectively. The former is built for classifying the type of the RD, and the latter is built for calculating the inclination and RAAN of the RD. The simulation results show that two neural networks are well trained. The classification model has an accuracy of more than 99% and the mean square error of the regression model is less than 0.01°on the test set. Moreover, a serial strategy is proposed to combine the two surrogate models and a recognition tool is built to evaluate whether a lunar site could be reached. The proposed deep learning method shows the superiority in computation efficiency compared with the traditional double two-body model.展开更多
Autonomous aerial refueling(AAR)has demonstrated significant benefits to aviation by extending the aircraft range and endurance.It is of significance to assess system safety for autonomous aerial refueling.In this pap...Autonomous aerial refueling(AAR)has demonstrated significant benefits to aviation by extending the aircraft range and endurance.It is of significance to assess system safety for autonomous aerial refueling.In this paper,the reachability analysis method is adopted to assess system safety.Due to system uncertainties,the aerial refueling system can be considered as a stochastic system.Thus,probabilistic reachability is considered.Since there is a close relationship between reachability probability and collision probability,the collision probability of the AAR system is analyzed by using reachability analysis techniques.Then,the collision probability is accessed by using the Monte-Carlo experiment method.Finally,simulations demonstrate the effectiveness of the proposed safety assessment method.展开更多
The paper studies reachability problem of autonomous ai^ine systems on n-dimensional polytopes.Our goal is to obtain both the largest positive invariant set in the polytope and the backward reachable set(the attractio...The paper studies reachability problem of autonomous ai^ine systems on n-dimensional polytopes.Our goal is to obtain both the largest positive invariant set in the polytope and the backward reachable set(the attraction domain)of each facet.Special attention is paid to the largest stable invariant affine subspace.After presenting several useful properties of those sets,a partition procedure is given to determine the largest positive invariant set in the polytope and all the attraction domains of facets.展开更多
Reachability testing is an approach to testing concurrent programs, which can systematically exercise every partially ordered SYN-sequence without constructing the static model. In fact, not all the SYN-sequences need...Reachability testing is an approach to testing concurrent programs, which can systematically exercise every partially ordered SYN-sequence without constructing the static model. In fact, not all the SYN-sequences need to be tested. This paper proposed a SYN-sequence selection strategy for reachability testing, which can reduce the number of SYN-sequences generated without decreasing the effectiveness of detecting programs＇ errors. We described a simple algorithm to implement the strategy, and then discussed several optimizations to the algorithm. Experiments have been carried out in a case study to verify the efficacy of the strategy.展开更多
This paper is concerned with the reachable set estimation problem for neutral Markovian jump systems with bounded peak disturbances, which was rarely proposed for neutral Markovian jump systems. The main consideration...This paper is concerned with the reachable set estimation problem for neutral Markovian jump systems with bounded peak disturbances, which was rarely proposed for neutral Markovian jump systems. The main consideration is to find a proper method to obtain the no-ellipsoidal bound of the reachable set for neutral Markovian jump system as small as possible. By applying Lyapunov functional method, some derived conditions are obtained in the form of matrix inequalities. Finally, numerical examples are presented to demonstrate the effectiveness of the theoretical results.展开更多
Answering reachability queries is one of the fundamental graph operations.Existing approaches either accelerate index construction by constructing an index that covers only partial reachability relationship,which may ...Answering reachability queries is one of the fundamental graph operations.Existing approaches either accelerate index construction by constructing an index that covers only partial reachability relationship,which may result in performing cost traversing operation when answering a query;or accelerate query answering by constructing an index covering the complete reachability relationship,which may be inefficient due to comparing the complete node labels.We propose a novel labeling scheme,which covers the complete reachability relationship,to accelerate reachability queries processing.The idea is to decompose the given directed acyclic graph(DAG)G into two subgraphs,G1 and G2.For G1,we propose to use topological labels consisting of two integers to answer all reachability queries.For G2,we construct 2-hop labels as existing methods do to answer queries that cannot be answered by topological labels.The benefits of our method lie in two aspects.On one hand,our method does not need to perform the cost traversing operation when answering queries.On the other hand,our method can quickly answer most queries in constant time without comparing the whole node labels.We confirm the efficiency of our approaches by extensive experimental studies using 20 real datasets.展开更多
In this paper,the reachable set estimation problem is studied for a class of dynamic neural networks subject to polytopic uncertainties.The problem addressed here is to find a set as small as possible to bound the sta...In this paper,the reachable set estimation problem is studied for a class of dynamic neural networks subject to polytopic uncertainties.The problem addressed here is to find a set as small as possible to bound the states starting from the origin by inputs with peak values.The maximal Lyapunov functional is proposed to derive a sufficient condition for the existence of a non-ellipsoidal bound to estimate the states of neural networks.It is theoretically shown that this method is superior to the traditional one based on the common Lyapunov function.Finally,two examples illustrate the advantages of our proposed result.展开更多
Risk assessment is a crucial component of collision warning and avoidance systems for intelligent vehicles.Reachability-based formal approaches have been developed to ensure driving safety to accurately detect potenti...Risk assessment is a crucial component of collision warning and avoidance systems for intelligent vehicles.Reachability-based formal approaches have been developed to ensure driving safety to accurately detect potential vehicle collisions.However,they suffer from over-conservatism,potentially resulting in false–positive risk events in complicated real-world applications.In this paper,we combine two reachability analysis techniques,a backward reachable set(BRS)and a stochastic forward reachable set(FRS),and propose an integrated probabilistic collision–detection framework for highway driving.Within this framework,we can first use a BRS to formally check whether a two-vehicle interaction is safe;otherwise,a prediction-based stochastic FRS is employed to estimate the collision probability at each future time step.Thus,the framework can not only identify non-risky events with guaranteed safety but also provide accurate collision risk estimation in safety-critical events.To construct the stochastic FRS,we develop a neural network-based acceleration model for surrounding vehicles and further incorporate a confidence-aware dynamic belief to improve the prediction accuracy.Extensive experiments were conducted to validate the performance of the acceleration prediction model based on naturalistic highway driving data.The efficiency and effectiveness of the framework with infused confidence beliefs were tested in both naturalistic and simulated highway scenarios.The proposed risk assessment framework is promising for real-world applications.展开更多
基金supported by the National Natural Science Foundation of China(Grant 52372347,52425211,52272360)。
文摘Task allocation for munition swarms is constrained by reachable region limitations and real-time requirements.This paper proposes a reachable region guided distributed coalition formation game(RRGDCF)method to address these issues.To enable efficient online task allocation,a reachable region prediction strategy based on fully connected neural networks(FCNNs)is developed.This strategy integrates high-fidelity data generated from the golden section method and low-fidelity data from geometric approximation in an optimal mixing ratio to form multi-fidelity samples,significantly enhancing prediction accuracy and efficiency under limited high-fidelity samples.These predictions are then incorporated into the coalition formation game framework.A tabu search mechanism guided by the reachable region center directs munitions to execute tasks within their respective reachable regions,mitigating redundant operations on ineffective coalition structures.Furthermore,an adaptive guidance coalition formation strategy optimizes allocation plans by leveraging the hit probabilities of munitions,replacing traditional random coalition formation methods.Simulation results demonstrate that RRGDCF surpasses the contract network protocol and traditional coalition formation game algorithms in optimality and computational efficiency.Hardware experiments further validate the method's practicality in dynamic scenarios.
基金supported by the National Natural Science Foundation of China(Nos.12372052,12125207)the Young Elite Scientists Sponsorship Program,China(No.2021JCJQ-QT-047)+1 种基金the Natural Science Foundation of Hunan Province,China(No.2023JJ20047)the Technology Innovation Team of Manned Space Engineering,China。
文摘The concept of the spacecraft Reachable Domain(RD)has garnered significant scholarly attention due to its crucial role in space situational awareness and on-orbit service applications.While the existing research has largely focused on single-impulse RD analysis,the challenge of Multi-Impulse RD(MIRD)remains a key area of interest.This study introduces a methodology for the precise calculation of spacecraft MIRD.The reachability constraints specific to MIRD are first formulated through coordinate transformations.Two restricted maneuvering strategies are examined.The derivation of two extremum conditions allows for determining the accessible orientation range and the nodes encompassing the MIRD.Subsequently,four nonlinear programming models are developed to address two types of MIRD by skillfully relaxing constraints using scale factors.Numerical results validate the robustness and effectiveness of the proposed approach,showing substantial agreement with Monte Carlo simulations and confirming its applicability to spacecraft on various elliptical orbits.
基金This work was supported by the National Natural Science Foundation of China (No. 6022130, 60334040, 60428304).
文摘This paper studies the reachability problem of the switched linear discrete singular （SLDS） systems. Under the condition that all subsystems are regular, the reachability of the SLDS systems is characterized based on a peculiar repeatedly introduced switching sequence. The necessary and sufficient conditions are obtained for the reachability of the SLDS systems.
文摘Reachability graph is a very important tool to analyze the dynamic properties of Petri nets, but the concurrent relation of transitions in Petri nets cannot be represented by reachability graph. Petri net is a concurrent system, while reachability graph is a serial one. However, concurrency is a kind of property which is not only very significant but also difficult to be analyzed and controlled. This paper presents the concepts of concurrent reachable marking and concurrent reachable graph in order to represent and analyze the concurrent system. The algorithm constructing concurrent reachable marking set and concurrent reachability graph is also shown so that we can study the response problems among services in a network computing environment and analyze the throughput of the system. The Dining Philosophers Problem, which is a classic problem of describing the management of concurrent resources, is given as an example to illustrate the significance of concurrent reachability graph.
基金co-supported by the National Natural Science Foundation of China (No. 11272346)the National Basic Research Program of China (No. 2013CB733100)
文摘A novel reachable set（RS） model is developed within a framework of exoatmospheric interceptor engagement analysis. The boost phase steering scheme and trajectory distortion mechanism of the interceptor are firstly explored. A mathematical model of the distorted RS is then formulated through a dimension–reduction analysis. By treating the outer boundary of the RS on sphere surface as a spherical convex hull, two relevant theorems are proposed and the RS envelope is depicted by the computational geometry theory. Based on RS model, the algorithms of intercept window analysis and launch parameters determination are proposed, and numerical simulations are carried out for interceptors with different energy or launch points. Results show that the proposed method can avoid intensive on-line computation and provide an accurate and effective approach for interceptor engagement analysis. The suggested RS model also serves as a ready reference to other related problems such as interceptor effectiveness evaluation and platform disposition.
基金Supported by the National Natural Science Foundation of China(No.11371003 and No.11461006)the Natural Science Foundation of Guangxi(No.2011GXNSFA018154 and No.2012GXNSFGA060003)
文摘Using Baire metric, this paper proposes a generalized framework of transition system approximation by developing the notions of approximate reachability and approximate bisimulation equivalences. The proposed framework captures the traditional exact equivalence as a special case. Approximate reachability equivalence is coarser than approximate bisimulation equivalence, just like the hierarchy of the exact ones. Both approximate equivalences satisfy the transitive property, consequently, they can be used in transition system approximation.
基金partially supported by the National Natural Science Foundation of China(No.12071025)the Natural Science Foundation of Guangdong Province,China(No.2022A1515011172)+1 种基金the Science and Technology on Space Intelligent Control Laboratory for National Defense,China(No.KGJZDSYS-2018-13)the Scientific and Technological Innovation of Shunde Graduate School of University of Science and Technology Beijing,China(No.BK20AE004)。
文摘For spacecraft formation flight,the information of relative motion reachable set is very important,which can be used to predict the operating boundary of adjacent spacecraft and thus to ensure the safety of spacecraft operation.In this paper,we aim at developing a numerical method to approximate the reachable set for spacecraft relative motion.In particular,we focus on the quality of the approximation and the computational cost.Based on the bang-bang control principle,a polyhedral approximation algorithm is proposed to compute the reachable set of a relative motion spacecraft system.An inner approximation and an outer approximation of the reachable set for the system can be obtained.We prove that the approximation quality measured in Hausdorff distance can be guaranteed.The method is easy to implement and has low computational cost.Finally,the effectiveness of the algorithm is demonstrated by experimental simulation.
基金supported by the National Natural Science Foundation of China (12072365)the Natural Science Foundation of Hunan Province of China (2020JJ4657)。
文摘It is important to calculate the reachable domain(RD)of the manned lunar mission to evaluate whether a lunar landing site could be reached by the spacecraft. In this paper, the RD of free return orbits is quickly evaluated and calculated via the classification and regression neural networks. An efficient databasegeneration method is developed for obtaining eight types of free return orbits and then the RD is defined by the orbit’s inclination and right ascension of ascending node(RAAN) at the perilune. A classify neural network and a regression network are trained respectively. The former is built for classifying the type of the RD, and the latter is built for calculating the inclination and RAAN of the RD. The simulation results show that two neural networks are well trained. The classification model has an accuracy of more than 99% and the mean square error of the regression model is less than 0.01°on the test set. Moreover, a serial strategy is proposed to combine the two surrogate models and a recognition tool is built to evaluate whether a lunar site could be reached. The proposed deep learning method shows the superiority in computation efficiency compared with the traditional double two-body model.
基金This work was supported by the National Natural Science Foundation of China(No.61933010).
文摘Autonomous aerial refueling(AAR)has demonstrated significant benefits to aviation by extending the aircraft range and endurance.It is of significance to assess system safety for autonomous aerial refueling.In this paper,the reachability analysis method is adopted to assess system safety.Due to system uncertainties,the aerial refueling system can be considered as a stochastic system.Thus,probabilistic reachability is considered.Since there is a close relationship between reachability probability and collision probability,the collision probability of the AAR system is analyzed by using reachability analysis techniques.Then,the collision probability is accessed by using the Monte-Carlo experiment method.Finally,simulations demonstrate the effectiveness of the proposed safety assessment method.
基金Supported by National Natural Science Foundation of China(60504024)Zhejiang Provincial Natural Science Foundation of China(Y106010)the Specialized Research Fund for the Doctoral Program of Higher Education of China(20060335022)
文摘The paper studies reachability problem of autonomous ai^ine systems on n-dimensional polytopes.Our goal is to obtain both the largest positive invariant set in the polytope and the backward reachable set(the attraction domain)of each facet.Special attention is paid to the largest stable invariant affine subspace.After presenting several useful properties of those sets,a partition procedure is given to determine the largest positive invariant set in the polytope and all the attraction domains of facets.
基金supported by National Natural Science Foundation of China(61374148,61472361,61374005)Natural Science Foundation of Zhejiang Province(LY15F030003,LY15F030002,LR14F020001)+3 种基金the National Science Foundation of USA(CMMI-1162482)the Opening Project of State Key Laboratory for Manufacturing Systems Engineering(sklms2014011)Zhejiang NNST Key Laboratory(2015C31064)the State Scholarship Fund of China
基金Supported by the "Tenth-Five Years" National Science Pre-Research Foundation of China (41315.9.2)the Natural Science Founda-tion of Hubei Province (2005ABA266)
文摘Reachability testing is an approach to testing concurrent programs, which can systematically exercise every partially ordered SYN-sequence without constructing the static model. In fact, not all the SYN-sequences need to be tested. This paper proposed a SYN-sequence selection strategy for reachability testing, which can reduce the number of SYN-sequences generated without decreasing the effectiveness of detecting programs＇ errors. We described a simple algorithm to implement the strategy, and then discussed several optimizations to the algorithm. Experiments have been carried out in a case study to verify the efficacy of the strategy.
文摘This paper is concerned with the reachable set estimation problem for neutral Markovian jump systems with bounded peak disturbances, which was rarely proposed for neutral Markovian jump systems. The main consideration is to find a proper method to obtain the no-ellipsoidal bound of the reachable set for neutral Markovian jump system as small as possible. By applying Lyapunov functional method, some derived conditions are obtained in the form of matrix inequalities. Finally, numerical examples are presented to demonstrate the effectiveness of the theoretical results.
基金This work was partly supported by National Key R&D Program of China,Grant No.2017YFB0309800the grants from the Natural Science Foundation of China(No.61472339,No.61303040,No.61572421,No.61272124)+1 种基金Shanghai Alliance Program(LM201552)Shanghai University of Engineering and Technology School-Enterprise cooperation projects(15)(DZ-025).
文摘Answering reachability queries is one of the fundamental graph operations.Existing approaches either accelerate index construction by constructing an index that covers only partial reachability relationship,which may result in performing cost traversing operation when answering a query;or accelerate query answering by constructing an index covering the complete reachability relationship,which may be inefficient due to comparing the complete node labels.We propose a novel labeling scheme,which covers the complete reachability relationship,to accelerate reachability queries processing.The idea is to decompose the given directed acyclic graph(DAG)G into two subgraphs,G1 and G2.For G1,we propose to use topological labels consisting of two integers to answer all reachability queries.For G2,we construct 2-hop labels as existing methods do to answer queries that cannot be answered by topological labels.The benefits of our method lie in two aspects.On one hand,our method does not need to perform the cost traversing operation when answering queries.On the other hand,our method can quickly answer most queries in constant time without comparing the whole node labels.We confirm the efficiency of our approaches by extensive experimental studies using 20 real datasets.
基金Supported by the National Natural Science Foundation of China under Grant Nos.60774039,60974024,61074089,61174129Program for New Century Excellent Talents in University under Grant No.NCET-11-0379the Independent Innovation Foundation of Tianjin University
文摘In this paper,the reachable set estimation problem is studied for a class of dynamic neural networks subject to polytopic uncertainties.The problem addressed here is to find a set as small as possible to bound the states starting from the origin by inputs with peak values.The maximal Lyapunov functional is proposed to derive a sufficient condition for the existence of a non-ellipsoidal bound to estimate the states of neural networks.It is theoretically shown that this method is superior to the traditional one based on the common Lyapunov function.Finally,two examples illustrate the advantages of our proposed result.
基金supported by the proactive SAFEty systems and tools for a constantly UPgrading road environment(SAFE-UP)projectfunding from the European Union’s Horizon 2020 Research and Innovation Program(861570)。
文摘Risk assessment is a crucial component of collision warning and avoidance systems for intelligent vehicles.Reachability-based formal approaches have been developed to ensure driving safety to accurately detect potential vehicle collisions.However,they suffer from over-conservatism,potentially resulting in false–positive risk events in complicated real-world applications.In this paper,we combine two reachability analysis techniques,a backward reachable set(BRS)and a stochastic forward reachable set(FRS),and propose an integrated probabilistic collision–detection framework for highway driving.Within this framework,we can first use a BRS to formally check whether a two-vehicle interaction is safe;otherwise,a prediction-based stochastic FRS is employed to estimate the collision probability at each future time step.Thus,the framework can not only identify non-risky events with guaranteed safety but also provide accurate collision risk estimation in safety-critical events.To construct the stochastic FRS,we develop a neural network-based acceleration model for surrounding vehicles and further incorporate a confidence-aware dynamic belief to improve the prediction accuracy.Extensive experiments were conducted to validate the performance of the acceleration prediction model based on naturalistic highway driving data.The efficiency and effectiveness of the framework with infused confidence beliefs were tested in both naturalistic and simulated highway scenarios.The proposed risk assessment framework is promising for real-world applications.
