In this paper, an ecological adaptive cruise controller (ECO-ACC) for parallel hybrid electric vehicles (HEVs) in a car-following scenario is presented to improve the fuel economy and maintain desired inter-vehicle distance from preceding vehicle. An ACC based on action dependent heuristic dynamic programming (ADHDP) proposed obtain velocity profile realize active control normal driving situations. ADHDP able adapt internal parameters online can thus deal with systems disturbances....

In this paper an ecological adaptive cruise controller to reduce the fuel consumption and ensure safe inter-vehicle distance for vehicles with step-gear transmissions is presented. An optimal control strategy using reinforcement learning a novel actor-gear-critic architecture proposed obtain continuous traction force trajectory discrete gear shift schedule. The determined from actor network maintain desired which improves driving safety in car-following process. schedule derived consumption....

In this paper, an online gear shift and power split strategy for parallel hybrid electric vehicles (HEVs) is proposed to optimize the fuel consumption. The control implemented with a neural network (NN). training of NN performed data obtained from dynamic programming (DP) different driving cycles. Simulation results present that sequences consumption DP are very similar, underlining near-optimal HEVs based on NN. Furthermore, realized action-dependent heuristic (ADHDP). ADHDP does not need...

In this paper a learning-based optimization method for online gear shift and velocity control is presented to reduce the fuel consumption improve driving comfort in car-following process. The continuous traction force discrete are optimized jointly both powertrain operation longitudinal motion. problem formulated as nonlinear mixed-integer solved based on adaptive dynamic programming. A major difference compared existing approaches that developed model-free, i.e. it does not rely vehicle...

Abstract An online trajectory planning method for collision avoidance is proposed to improve vehicle driving safety and comfort simultaneously. The collision-free autonomous formulated as a nonlinear optimization problem. A novel approximate convex approach developed the optimal in both longitudinal lateral directions. First, dual variable used model non-convex constraint calculated by solving problem of relative distance between vehicles. Second, further optimized predictive control...

This paper uses the adaptive dynamic programming (ADP) method to achieve optimal trajectory tracking control for quadrotors. Relying on an established mathematical model of a quadrotor, approximate control, which consists steady-state input and feedback input, is designed nominal system. Considering compound disturbances in position attitude models, disturbance observers are introduced. The estimated values used design robust compensation inputs suppress effect good performance....

During the torque phase, appropriate coordination between two clutches is of vital importance to dual-clutch transmission so that a high-quality shift achieved without clutch interaction and engine flare, because poor-quality definitely extends time increases friction work. Concerning this problem, different power flow conditions during phase are discussed in detail, after investigation downshift process design an H ∞ robust controller for inertia phase. The results obtained indicate that,...

Service-oriented systems are performed in a highly dynamic and heterogeneous environment to achieve user’s business requirements. In this paper, we introduce case-based reasoning approach improve the system’s fault-tolerant ability meeting end-to-end Quality-of-Service (QoS) constraints. We consider quantify fault information QoS together case. addition, one case also includes solution cope with corresponding fault. When new occurs, its failure symptoms extracted matched against base look...

In this paper we present a new vulnerability-targeted black box fuzzing approach to effectively detect errors in the program. Unlike standard techniques that randomly change bytes of input file, our remarkably reduces range by utilizing an efficient dynamic taint analysis technique. It locates regions seed files affect values used at hazardous points. Thus it enables pay more attention deep core Because is directly targeted specific potential vulnerabilities, most detected are with...

For delivering scalable, reliable and on-demand services, cloud services are becoming more prevalent. Due to dynamic flexibility in environment, Service Level Agreement (SLA) plays a crucial role guaranteeing the Quality of (QoS) level agreed by participants. Though lots work on SLA management, few them have adapted well such an environment. In this study, we present novel policy-based adaptive approach solve problem, introduce contract template embedded with policy handle changes service...

This paper addresses the integration of energy management and shift control in parallel hybrid electric vehicles with dual-clutch transmission to reduce fuel consumption, decrease pollutant emissions, improve driving comfort simultaneously. Dynamic programming a varying weighting factor cost function is proposed balance frequency consumption for power-split gear schedule design. Simulation results present that drivability can be improved due fewer events while only slightly increased...

This paper presents an adaptive fault tolerant control approach for autonomous vehicles (AV) under actuator or sensor faults to improve driving safety. A learning-based stochastic model predictive (SMPC) strategy incorporating vehicle real dynamics characteristics is developed realize accurate trajectory tracking. First, a integrating typical and established. Then, online learning designed update the in real-time. Gaussian process (GP) applied identify learn dynamic changes caused by which...

In this paper a hybrid model predictive control (HMPC) strategy for electric vehicles (HEVs) is proposed joint optimization of the power split between engine and motor together with gear shift control. A switched affine system introduced to represent vehicle dynamics under different ratios. The nonlinear characteristics are described by piecewise system. HMPC problem then formulated as mixed integer quadratic programming problem. Simulation results show that developed can not only decrease...

Service-oriented computing is a widely adopted paradigm in real applications. Considering the continuous evolution of services, adaptive service composition has always been major concern. It big challenge to adjust be optimal real-time. In this paper, learning automata-based approach proposed attack problem. consists two important components: random environment and automaton. The former can mapped service's execution environment. latter responsible for adaptation achievement using reward...

We propose a service's reputation model in service-oriented environments. The is built on the base of raters' behavior showing current rated service and other similar services. Both rater's credibility sensitivity are considered our at same time. Furthermore, latter first put forward distinguishing among services to give constructive suggestions for new users. And temporal characteristics ratings throughout establishment. Experiments benchmarked demonstrate that all factors play an important...

Currently, the demand for art talents in society is becoming increasingly diverse. It requires students not only to master professional skills, but also possess a high level of cultural literacy. Especially with increasing emphasis on regional culture by current state and society, integration education can promote enhance identification culture, provide more unique practical resources, promoting progress development education. be seen that great value both Based this, this paper discusses...

The accuracy and robustness of vehicle localization are critical for achieving safe reliable high-level autonomy. Recent results show that GPS is vulnerable to spoofing attacks, which one major threat autonomous driving. In this paper, a novel anomaly detection mitigation method against attacks utilizes onboard camera high-precision maps proposed ensure accurate localization. First, lateral direction in driving lanes calculated by camera-based lane map matching respectively. Then, real-time...