To promote the real-time application of advanced energy management system in hybrid electric vehicles (HEVs), this paper proposes an adaptive hierarchical strategy for a plug-in HEV. In paper, deep learning (DL) and genetic algorithm (GA) are synthesized to derive power split controls between battery internal combustion engine. First, architecture multimode powertrain is founded, wherein particular control actions, state variables, optimization objective explained. Then, framework actions...

An online energy management controller is presented in this paper for a plug-in hybrid electric vehicle (PHEV), which based on driving conditions recognition and genetic algorithm (GA). The proposed can be used the real-time application. First, studied multimode PHEV modeled four traction operation modes are introduced detail. Second, principal component analysis (PCA) utilized to classify real historical data. Four types of constructed describe representative scenarios. Then, GA applied...

Hybrid energy storage systems that combine lithium-ion batteries and supercapacitors are considered as an attractive solution to overcome the drawbacks of battery-only systems, such high cost, low power density, short cycle life, which hinder popularity electric vehicles. A properly sized hybrid system implementable real-time management great importance achieve satisfactory driving mileage battery life. However, dimensioning problems quite complicated challenging in practice. To address...

An adaptive potential field is designed to adapt the acceleration/deceleration and mass of obstacle. The fields are established in a transformed road coordinate system improve feasibility robustness. A path planning method proposed based on driving safety ride comfort autonomous vehicles complex scenarios, which including cut-in, emergency braking, obstacle sudden accelerating during overtaking curve scenarios. effectiveness validated by simulations with constructed real data, respectively....

Abstract There is an increasing awareness of the need to reduce traffic accidents and fatality due vehicle collision. Post-impact hazards can be more serious as driver may fail maintain effective control after collisions. To avoid subsequent crash events stabilize vehicle, this paper proposes a post-impact motion planning stability method for autonomous vehicles. An enabling proposed situations by combining polynomial curve artificial potential field while considering obstacle avoidance. A...

Left turning at unsignalized intersectionis one of the most challenging tasks for urban automated driving, due to various shapes intersections and rapidly changing nature driving scenarios. This article addresses challenges decision making highly uncertain different by proposing a generalized critical point (CTP)-based hierarchical decision-making planning method. The high-level planner takes road map information generates CTPs using parameterized extraction model that is proposed verified...

How to reduce traffic accidents and improve vehicle safety has always aroused widespread concern. Secondary serial collision can result in more serious hazards as the initial easily destabilize a high-speed driver may fail maintain effective control due panic. With this mind, planning-integrated active system is developed for post-impact vehicles avoid subsequent accidents. The dynamics model established considering roll degree of freedom. constraint equivalent methods based on octagon...

Intellectualisation is one of the three reforming technologies in automotive industry, which now changing mobility mode and human society. High safety intelligence are pre-requisites for putting self-driving vehicles into markets. This study presents hardware software architecture intelligent vehicles, as well their road verification typical traffic scenarios. The system includes environmental sensors, computing platforms, vehicle actuators, able to provide redundant protection against main...

A 4-independent wheel driving (4-IWD) electric vehicle has distinctive advantages with both enhanced dynamic and energy efficiency performances since this configuration provides more flexibilities from the design control aspects. However, it is difficult to achieve optimal of a 4-IWD conventional approaches. This work dedicated investigating vehicular approaches, race car aiming at minimizing lap time on given circuit as case study. 14-DOF model that can fully evaluate influences unsprung...

Left-turn planning is one of the formidable challenges for autonomous vehicles, especially at unsignalized intersections due to unknown intentions oncoming vehicles. This paper addresses challenge by proposing a critical turning point (CTP) based hierarchical approach. includes high-level candidate path generator and low-level partially observable Markov decision process (POMDP) planner. The proposed CTP concept, inspired human-driving behaviors intersections, aims increase computational...

Currently, most hybrid electric vehicles (HEVs) equipped with automated mechanical transmission (AMT) are implemented the conventional two-parameter gear shift schedule based on engineering experience. However, this approach cannot take full advantage of drives. In other words, powertrain an HEV is not able to work at best fuel-economy points during whole driving profile. To solve problem, optimization method for HEVs proposed Dynamic Programming (DP) and a corresponding solving algorithm...

The traditional potential field-based path planning is likely to generate unexpected by strictly following the minimum field, especially in driving scenarios with multiple obstacles closely distributed. A hybrid proposed avoid unsatisfying generation and improve performance of autonomous combining field sigmoid curve. repulsive attractive fields are redesigned considering safety feasibility. Based on objective shortest generation, optimized trajectory obtained vehicle stability constraints...

Dynamic models of a single-shaft parallel hybrid electric vehicle (HEV) equipped with automated mechanical transmission (AMT) were described in different working stages during gear shifting process without disengaging clutch. Parameters affecting the time, components life, and jerk transient states deeply analyzed. The mathematical considering detailed synchronizer which can explain failure, long time shifting, frequent failure phenomenon HEV derived. coordinated control strategy engine,...

For unmanned tracked vehicles (UTVs), drifting can generate the maximum centripetal acceleration to complete challenging tasks, such as high-speed obstacle avoidance. However, due open-loop instability of vehicle motion during drifting, existing research on UTV control focuses avoiding thereby limiting maneuverability UTV. A dynamics model is developed, considering effects acceleration, track tension and slide contact shear forces. Model parameters are identified based moving horizon...

The energy efficiency improvement problems of hybrid electric vehicles (HEVs) with automated manual transmissions are investigated from both the design and control aspects for extended searching space in this work. To optimize transmission, gearshift commands power distribution simultaneously, a combined mixed-integer optimal problem (MIOCP) is formulated. challenging MIOCP then reformulated by introducing augmented terms objective function dynamic model to handle integer variables. solved...

The available road grade information makes a significant impact on improving the quality of vehicle control. In order to solve limited application scenario and insufficient accuracy current estimation methods, this paper presents novel model-based approach. First, Quaternion Unscented Kalman Filter (QUKF) using three-axle angular velocities accelerations from low-cost Inertial Measurement Unit (IMU) speed CAN bus is designed estimate pitch angle vehicle. particular, measurement noise UKF...

Abstract The cooperation between an autonomous vehicle and a nearby is critical to ensure driving safety in the lane-exchanging scenario. trajectory needs be predicted, from which controlled prevent possible collisions. This paper proposes strategy for cooperate with by integrating prediction motion control. A method developed anticipate trajectory. Gaussian mixture model (GMM), together kinematic model, are synthesized predict potential-field-based predictive control (MPC) approach utilized...

Digital quadruplets aiming to improve road safety, traffic efficiency, and driving cooperation for future connected automated vehicles are proposed with the enlightenment of ACP-based parallel driving. The ACP method denotes artificial societies, computational experiments, execution modules cyberphysical-social systems. Four agents designed in framework digital quadruplets: descriptive vehicles, predictive prescriptive real vehicles. three virtual (descriptive, predictive, prescriptive)...

Hybrid energy storage system (HESS) has been recognized as one of the most promising solutions to overcome drawbacks expensive and short life lithium-ion battery with low power density, by introducing a proper number supercapcitors. However, hybridization introduces complicated sizing management problems. This papers aims investigate real-time devised HESS for electric vehicles an race car case study. In particular, proposed multi-objective Bi-level optimal control framework is implemented...

Autonomous tractor semi-trailers are expected to improve safety and efficiency for road freight transportation. However, the complex dynamics introduced by articulated structure of semi-trailer results in poor yaw roll stability, which consequence poses great challenges path tracking under extreme conditions featuring high lateral acceleration or low tire-road friction. In this work, a stability-guaranteed computationally efficient model predictive framework is devised. particular,...