Collision avoidance and stabilisation are two of the most crucial concerns when an autonomous vehicle finds itself in emergency situations, which usually occur a short time horizon require large actuator inputs, together with highly nonlinear tyre cornering response. In order to avoid collision while stabilising under dynamic driving situations at handling limits, this paper proposes novel steering control strategy based on hierarchical architecture consisting decision-making layer motion...

The challenging issue of "human-machine copilot" opens up a new frontier to enhancing driving safety. However, driver-machine conflicts and uncertain driver/external disturbances are significant problems in cooperative steering systems, which degrade the system's path-tracking ability reduce This paper proposes novel stochastic game-based shared control framework model torque interaction between driver intelligent electric power (IEPS) system. A six-order driver-vehicle dynamic system,...

Stability as well robustness is the major concerns in design of a trajectory tracking controller for an autonomous vehicle. In this paper, novel lateral stability vehicle path developed. First, using dynamic game theory general framework, can be viewed difference so that its two players, namely, active front steering (AFS) system and rear (ARS) work together to provide more control. The interactive control strategies between AFS ARS are obtained by noncooperative closed-loop feedback...

The role of autotransplantation in end-stage hepatic alveolar echinococcosis (AE) is unclear. We aimed to present our 15-case experience and propose selection criteria for autotransplantation. All patients were considered have unresectable AE by conventional resection due critical invasion retrohepatic vena cava, hepatocaval region along with three veins, the tertiary portal arterial branches. successfully underwent ex vivo extended right hepatectomy without intraoperative mortality. median...

Modelling uncertainty, parameter variation and unknown external disturbance are the major concerns in development of an advanced controller for vehicle stability at limits handling. Sliding mode control (SMC) method has proved to be robust against with satisfactory tracking performance. But modelling such as errors caused model simplification, is inevitable model-based design, resulting lowered quality. The adaptive radial basis function network (ARBFN) can effectively improve performance...

In this paper, a new framework for path tracking is proposed through learning to drive like human beings. Firstly, the imitation algorithm (behavior cloning) adopted initialize deep reinforcement (DRL) professional drivers' experience. Secondly, continuous, deterministic, model free optimize our DRL on line trial and error. By combining behavior cloning algorithms, can learn an effective policy quickly using some easy-to-measure vehicle state parameters environment information as inputs....

Abstract The accurate estimation of road friction coefficient in the active safety control system has become increasingly prominent. Most previous studies on have only used vehicle longitudinal or lateral dynamics and often ignored load transfer, which tends to cause inaccurate actual coefficient. A novel method considering transfer front rear axles is proposed estimate based braking dynamic model two-wheeled vehicle. Sliding mode technique build ideal torque controller, target wheel slip...

This article proposes a fault-tolerant control (FTC) strategy for path following of autonomous vehicles considering faults in the braking actuator. Distinguished from other relevant research, fault model is designed, and synthetic factor calculated electrohydraulic brake (EHB) system case differential braking. By as time-varying parameter, robust gain-scheduling linear parameter-varying ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML"...

Steering-by-wire (SBW) systems can enhance driving experience and improve autonomous performance. A key challenge is simultaneously meeting the steering angle tracking requirements for both manual modes when dealing with inconsistent command update cycles, lack of speed sensors, unmodeled dynamics, nonlinear disturbances. This paper adopts a hierarchical cascade control structure comprising an loop velocity loop, focusing on improving performance by optimizing angular controller. The...

In the past decade, several publications have shown that it is advisable to design an advanced driver assistance system using a shared control structure. This paper concerned with modelling and verification of interactive steering strategy between active front (AFS) controller investigate complex interactions human AFS system. Using game theory as general framework, more comprehensive mathematical model potentially applicable explore drivers' behaviours in intelligent vehicles presented...

Path tracking is one of the most crucial issues autonomous vehicles, but uncertain factors including road roughness and wind gusts could cause lateral deviation even divergence control system. Therefore, this paper proposes a hierarchical anti-disturbance architecture based on steer-by-wire (SBW) system to improve accuracy dynamic stability for vehicles. The proposed robust strongly against different types disturbances in path process by means decoupling. Firstly, upper-layer module, model...

A new methodology to design the vehicle GCC (global chassis control) nonlinear controller is developed in this paper. Firstly, handle coupling between sprung and unsprung masses, treated as a mechanical system of two-rigid-bodies which has 6 DOF (degree freedom), including longitudinal, lateral, yaw, vertical, roll pitch dynamics. The equation built yaw frame based on Lagrange's method, it been proved that derived remains important physical properties general system. Then problem formulated...

Road adhesion coefficient is an important parameter in vehicle active safety control system. Many researchers estimate road by total tire self-aligning torque (SAT, also called front-axle aligning torque), which obtains the average of front wheels, thus leading large estimation error. In this paper, a novel based on single SAT, obtained distribution, brought forward. Due to use proposed method available steering only condition. The main idea that estimated SAT instead SAT. closer real state,...

The evaluation of driver's steering comfort, which is mainly concerned with the haptic driver-vehicle interaction, important for optimization advanced driver assistance systems. current approaches to investigating comfort are based on subjective evaluation, time-consuming, expensive, and easily influenced by individual variations. This paper makes some tentative investigation objective electromyogram (EMG) movement trajectory upper limbs during maneuvers. First, a experiment 21 subjects...

One of the most challenging problems in autonomous driving is trajectory planning for lane changes. Conventional generally realized by optimizing a specific cost function. However, model performance required different scenarios makes it repetitive and time-consuming to tune Furthermore, ensure safety, comfort as well traffic efficiency, essential interact with other vehicles predicting their intentions. Therefore, this paper proposes segmented-updated lane-change method on closed highways....

Accurate lateral load transfer estimation plays an important role in improving the performance of active rollover prevention system equipped commercial vehicles. This depends on accurate prediction roll angles for both sprung and unsprung subsystems. paper proposes a novel computational method roll-angle vehicles employing sensors which are already used vehicle dynamic control without additional expensive measurement units. The strategy integrates two blocks. first block contains...

Driver-machine shared control scheme opens up a new frontier for the design of driver assistance system, especially improving active safety in emergency scenario. However, driver's stress response to steering and strong tire nonlinearity are main challenges suffered by controller designing collision avoidance. These unfavorable factors particularly pronounced during maneuvers sharply degrade performance. This paper proposes fuzzy-linear quadratic regulator (LQR) game-based simultaneously...

Autonomous vehicles need to have the ability predict motion of surrounding vehicles, which will help avoid potential accidents and make best decision ensure safety comfort. The interactions among those between them uncertainty driving intention trajectory prediction a challenging task. This study presents long short‐term memory (LSTM) model for task account both mutual information multi‐modal intention. consists data fusion encoder decoder. summarises by multi‐LSTM with shared parameters...

As a significant active safety technology towards fully autonomous driving, driver-automation co-piloting provides new thinking for enhancing vehicle and relieving driver's workload. However, the preview pattern divergence between driver steering assistance system (SAS) may give rise to serious conflicts, which reduces faith in SAS, cause him/her turn off it, even result fatal traffic accidents. Focusing on mimicking behaviour, this paper proposes human-like scheme by adaptively varying time...

This paper proposes a robust gain-scheduling lateral motion control strategy via coordination of the active front-wheel steering (AFS) and direct yaw moment (DYC) for path following autonomous vehicle. Distinguishing from other relevant researches, seamless application DYC is designed to reduce influence braking vehicle longitudinal dynamics. In order achieve this objective, weighting function with self-scheduling parameter designed. Based on above, novel LPV (Linear Parameter Varying)...