Decision-Making in Driver-Automation Shared Control:A Review and Perspectives

Shared control schemes allow a human driver to work with an automated driving agent in driver-vehicle systems while retaining the driver’s abilities to control.The human driver,as an essential agent in the driver-vehicle shared control systems,should be precisely modeled regarding their cognitive processes,control strategies,and decision-making processes.The interactive strategy design between drivers and automated driving agents brings an excellent challenge for human-centric driver assistance systems due to the inherent characteristics of humans.Many open-ended questions arise,such as what proper role of human drivers should act in a shared control scheme?How to make an intelligent decision capable of balancing the benefits of agents in shared control systems?Due to the advent of these attentions and questions,it is desirable to present a survey on the decision making between human drivers and highly automated vehicles,to understand their architectures,human driver modeling,and interaction strategies under the driver-vehicle shared schemes.Finally,we give a further discussion on the key future challenges and opportunities.They are likely to shape new potential research directions.

Shared Control of Highly Automated Vehicles Using Steer-By-Wire Systems

A shared control of highly automated Steer-by-Wire system is proposed for cooperative driving between the driver and vehicle in the face of driver's abnormal driving. A fault detection scheme is designed to detect the abnormal driving behaviour and transfer the control of the car to the automatic system designed based on a fault tolerant model predictive control(MPC) controller driving the vehicle along an optimal safe path.The proposed concept and control algorithm are tested in a number of scenarios representing intersection, lane change and different types of driver's abnormal behaviour. The simulation results show the feasibility and effectiveness of the proposed method.

The Indirect Shared Steering Control Under Double Loop Structure of Driver and Automation

Due to the critical defects of techniques in fully autonomous vehicles,man-machine cooperative driving is still of great significance in today’s transportation system.Unlike the previous shared control structure,this paper introduces a double loop structure which is applied to indirect shared steering control between driver and automation.In contrast to the tandem indirect shared control,the parallel indirect shared control put the authority allocation system of steering angle into the framework to allocate the corresponding weighting coefficients reasonably and output the final desired steering angle according to the current deviation of vehicle and the accuracy of steering angles.Besides,the active disturbance rejection controller(ADRC)is also added in the frame in order to track the desired steering angle fleetly and accurately as well as restrain the internal and external disturbances effectively which including the steering friction torque,wind speed and ground interference etc.Eventually,we validated the advantages of double loop framework through three sets of double lane change and slalom experiments,respectively.Exactly as we expected,the simulation results show that the double loop structure can effectively reduce the lateral displacement error caused by the driver or the controller,significantly improve the tracking precision and keep great performance in trajectory tracking characteristics when driving errors occur in one of driver and controller.

A Type-2 Fuzzy Approach to Driver-Automation Shared Driving Lane Keeping Control of Semi-Autonomous Vehicles Under Imprecise Premise Variable

The driver-automation shared driving is a transition to fully-autonomous driving,in which human driver and vehicular controller cooperatively share the control authority.This paper investigates the shared steering control of semi-autonomous vehicles with uncertainty from imprecise parameter.By considering driver’s lane-keeping behavior on the vehicle system,a driver-automation shared driving model is introduced for control purpose.Based on the interval type-2(IT2)fuzzy theory,moreover,the driver-automation shared driving model with uncertainty from imprecise parameter is described using an IT2 fuzzy model.After that,the corresponding IT2 fuzzy controller is designed and a direct Lyapunov method is applied to analyze the system stability.In this work,sufficient design conditions in terms of linear matrix inequalities are derived,to guarantee the closed-loop stability of the driver-automation shared control system.In addition,an H∞performance is studied to ensure the robustness of control system.Finally,simulation-based results are provided to demonstrate the performance of proposed control method.Furthermore,an existing type-1 fuzzy controller is introduced as comparison to verify the superiority of the proposed IT2 fuzzy controller.

SHARED CONTROL METHOD FOR COMBINATION STATE CONVERSION OF ELECTRO－MECHANICAL EQUIPMENT

The theory of shared control combines organically the control of every controlled ele-ments and with it all the controlled elements share the same control element. Applying theschemes of shared control searched by assembly programs, an integrated control of all the ele-ments is fulfilled. The distinguishing point of the method is that the maximum control output canbe obtained with the least input information. Hence it is the optimum for the conversion of com-bination states. Finally, a thared rotary valve is designed, and it is the simplest with only onegroup of control holes.

An Adaptive Wireless Power Sharing Control for Multiterminal HVDC

Power sharing among multiterminal high voltage direct current terminals(MT-HVDC)is mainly developed based on a priority or sequential manners,which uses to prevent the problem of overloading due to a predefined controller coefficient.Furthermore,fixed power sharing control also suffers from an inability to identify power availability at a rectification station.There is a need for a controller that ensures an efficient power sharing among the MT-HVDC terminals,prevents the possibility of overloading,and utilizes the available power sharing.A new adaptive wireless control for active power sharing among multiterminal(MT-HVDC)systems,including power availability and power management policy,is proposed in this paper.The proposed control strategy solves these issues and,this proposed controller strategy is a generic method that can be applied for unlimited number of converter stations.The rational of this proposed controller is to increase the system reliability by avoiding the necessity of fast communication links.The test system in this paper consists of four converter stations based on three phase-two AC voltage levels.The proposed control strategy for a multiterminal HVDC system is conducted in the power systems computer aided design/electromagnetic transient design and control(PSCAD/EMTDC)simulation environment.The simulation results significantly show the flexibility and usefulness of the proposed power sharing control provided by the new adaptive wireless method.

Adaptive active inceptor design under shared control architecture for nonlinear pilot-induced oscillations

This paper presents a Shared Control Architecture(SCA)between a human pilot and a smart inceptor for nonlinear Pilot Induced Oscillations(PIOs),e.g.,category II or III PIOs.One innovation of this paper is that an intelligent shared control architecture is developed based on the intelligent active inceptor technique,i.e.,Smart Adaptive Flight Effective Cue(SAFE-Cue).A deep reinforcement learning approach namely Deep Deterministic Policy Gradient(DDPG)method is chosen to design a gain adaptation mechanism for the SAFE-Cue module.By doing this,the gains of the SAFE-Cue will be intelligently tuned once nonlinear PIOs triggered;meanwhile,the human pilot will receive a force cue from the SAFE-Cue,and will consequently adapting his/her control policy.The second innovation of this paper is that the reward function of the DDPG based gain adaptation approach is constructed according to flying qualities.Under the premise of considering failure situation,task completion qualities and pilot workload are also taken into account.Finally,the proposed approach is validated using numerical simulation experiments with two types of scenarios:lower actuator rate limits and airframe damages.The Inceptor Peak Power-Phase(IPPP)metric is adopted to analyze the human-vehicle system simulation results.Results and analysis show that the DDPG based sharing control approach can well address nonlinear PIO problems consisting of Categories Ⅱ and Ⅲ PIO events.

A distributed authentication and authorization scheme for in-network big data sharing

Big data has a strong demand for a network infrastructure with the capability to support data sharing and retrieval efficiently. Information-centric networking （ICN） is an emerging approach to satisfy this demand, where big data is cached ubiquitously in the network and retrieved using data names. However, existing authentication and authorization schemes rely mostly on centralized servers to provide certification and mediation services for data retrieval. This causes considerable traffic overhead for the secure distributed sharing of data. To solve this problem, we employ identity-based cryptography （IBC） to propose a Distributed Authentication and Authorization Scheme （DAAS）, where an identity-based signature （IBS） is used to achieve distributed verifications of the identities of publishers and users. Moreover, Ciphertext-Policy Attribnte-based encryption （CP-ABE） is used to enable the distributed and fine-grained authorization. DAAS consists of three phases： initialization, secure data publication, and secure data retrieval, which seamlessly integrate authentication and authorization with the in- terest/data communication paradigm in ICN. In particular, we propose trustworthy registration and Network Operator and Authority Manifest （NOAM） dissemination to provide initial secure registration and enable efficient authentication for global data retrieval. Meanwhile, Attribute Manifest （AM） distribution coupled with automatic attribute update is proposed to reduce the cost of attribute retrieval. We examine the performance of the proposed DAAS, which shows that it can achieve a lower bandwidth cost than existing schemes.

Controlled quantum state sharing of arbitrary two-qubit states with five-qubit cluster states

In this paper, we propose a controlled quantum state sharing scheme to share an arbitrary two-qubit state using a five-qubit cluster state and the Bell state measurement. In this scheme, the five-qubit cluster state is shared by a sender （Alice）, a controller （Charlie）, and a receiver （Bob）, and the sender only needs to perform the Bell-state measurements on her particles during the quantum state sharing process, the controller performs a single-qubit projective measurement on his particles, then the receiver can reconstruct the arbitrary two-qubit state by performing some appropriate unitary transformations on his particles after he has known the measured results of the sender and the controller.

Human-robot shared control system based on 3D point cloud and teleoperation

Owing to the constraints of unstructured environments,it is difficult to ensure safe,accurate,and smooth completion of tasks using autonomous robots.Moreover,for small-batch and customized tasks,autonomous operation requires path planning for each task,thus reducing efficiency.We propose a human-robot shared control system based on a 3D point cloud and teleoperation for a robot to assist human operators in the performance of dangerous and cumbersome tasks.The system leverages the operator’s skills and experience to deal with emergencies and perform online error correction.In this framework,a depth camera acquires the 3D point cloud of the target object to automatically adjust the end-effector orientation.The operator controls the manipulator trajectory through a teleoperation device.The force exerted by the manipulator on the object is automatically adjusted by the robot,thus reducing the workload for the operator and improving the efficiency of task execution.In addition,hybrid force/motion control is used to decouple teleoperation from force control to ensure that force and position regulation will not interfere with each other.The proposed framework was validated using the ELITE robot to perform a force control scanning task.

Human-machine shared control:New avenue to dexterous prosthetic hand manipulation

At present,albeit the dexterous hand prostheses of multiple degrees of freedom(DOFs)have become prosperous on the market,the user’s demand on intuitively operating these devices have not been well addressed so that their acceptance rate is relatively low.The unintuitive control method and inadequate sensory feedback are frequently cited as the two barriers to the successful application of these dexterous products.Recently,driven by the wave of artificial intelligence(AI),a series of shared control methods have emerged,in which"bodily function"(myoelectric control)and"artificial intelligence"(local autonomy,computer vision,etc.)are tightly integrated,and provided a new conceptual solution for the intuitive operation of dexterous prostheses.In this paper,the background and development trends of this type of methods are described in detail,and the potential development directions and the key technologies that need breakthroughs are indicated.In practice,we instantiate this shared control strategy by proposing a new method combining simultaneous myoelectric control,multi-finger grasp autonomy,and augmented reality(AR)feedback together.This method"divides"the human sophisticated reach-and-grasp task into several subtasks,and then"conquers"them by using different strategies from either human or machine perspective.It is highly expected that the shared control methods with hybrid human-machine intelligence could address the control problem of dexterous prostheses.

Toward Shared Control Between Automated Vehicles and Users

Technological developments in the domain of vehicle automation are targeted toward driver-less,or driver-out-of-the-loop driving.The main societal motivation for this ambition is that the majority of(fatal)accidents with manually driven vehicles are due to human error.However,when interacting with technology,users often experience the need to customize the technology to their personal preferences.This paper considers how this might apply to vehicle automation,by a conceptual analysis of relevant use cases.The analysis proceeds by comparing how handling of relevant situations is likely to differ between manual driving and automated driving.The results of the analysis indicate that full out-of-the-loop automated driving may not be acceptable to users of the technology.It is concluded that a technology that allows shared control between the vehicle and the user should be pursued.Furthermore,implications of this view are explored for the concrete temporal dynamics of shared control,and general characteristics of human machine interface that support shared control are proposed.Finally,implications of the proposed view and directions for further research are discussed.

Driver-automation shared steering control considering driver neuromuscular delay characteristics based on stackelberg game

To promote the intelligent vehicle safety and reduce the driver steering workload,stackelberg game theory is adopted to design the shared steering control strategy that takes the driver neuromuscular delay characteristics into account.First,a shared steering control framework with adjustable driving weight is proposed,and a coupling interaction model considering the driver neuromuscular delay characteristics is constructed by using the stackelberg game theory.Moreover,the driver-automation optimal control strategy is deduced theoretically when the game equilibrium is reached.Finally,simulation and virtual driving tests are carried out to verify the superiority of the proposed method.The results illustrate that the raised method can enhance the vehicle safety with low driving weight intervention,and it can achieve better auxiliary effect with less control cost.In addition,the driver-in-the-loop test results show that the proposed strategy can achieve better performance in assisting drivers with low driving skills.

Intelligent-Assist Algorithm for Remote Shared-Control Driving Based on Game Theory

Contemporary autonomous-driving technology relies on good environmental-perception systems and high-precision maps.For unknown environments or scenarios where perception fails,a human-in-the-loop remote-driving system can effectively complement common solutions,although safety remains an issue for its application.A haptic shared-control algorithm based on non-cooperative game theory is presented in this paper.The algorithm generates collision-free reference paths with model predictive control and predicts the driver’s path using a two-point preview model.Man-machine torque interaction is modeled as a Nash game,and the assist system’s degree of intervention is regulated in real time,according to assessments of collision risk and the driver’s concentration.Simulations of several representative scenarios demonstrate how the proposed method improves driving safety,while respecting driver decisions.

GACS:Generative Adversarial Imitation Learning Based on Control Sharing

Generative adversarial imitation learning(GAIL)directly imitates the behavior of experts from human demonstration instead of designing explicit reward signals like reinforcement learning.Meanwhile,GAIL overcomes the defects of traditional imitation learning by using a generative adversary network framework and shows excellent performance in many fields.However,GAIL directly acts on immediate rewards,a feature that is reflected in the value function after a period of accumulation.Thus,when faced with complex practical problems,the learning efficiency of GAIL is often extremely low and the policy may be slow to learn.One way to solve this problem is to directly guide the action(policy)in the agents'learning process,such as the control sharing(CS)method.This paper combines reinforcement learning and imitation learning and proposes a novel GAIL framework called generative adversarial imitation learning based on control sharing policy(GACS).GACS learns model constraints from expert samples and uses adversarial networks to guide learning directly.The actions are produced by adversarial networks and are used to optimize the policy and effectively improve learning efficiency.Experiments in the autonomous driving environment and the real-time strategy game breakout show that GACS has better generalization capabilities,more efficient imitation of the behavior of experts,and can learn better policies relative to other frameworks.

Real-time comprehensive driving ability evaluation algorithm for intelligent assisted driving

To meet the needs of the human-machine co-driving decision problem in the intelligent assisted driving system for real-time comprehensive driving ability evaluation of drivers,this paper proposes a real-time comprehensive driving ability evaluation method that integrates driving skill,driving state,and driving style.Firstly,by analyzing the driving experiment data obtained based on the intelligent driving simulation platform(the experiment can effectively distinguish the driver's driving skills and avoid the interference of driving style),the feature values that significantly represent driving skills and driving state are selected,and the time correlation between driving state and driving skills is pointed out.Furthermore,the concept of relativity in comprehensive driving ability evaluation is further proposed.Under this concept,the natural driving trajectory dataset-HighD is used to establish the distribution map of feature values of the human driver group as the evaluation benchmark to realize the relative evaluation of driving skill and driving state.Similarly,HighD is used to establish a distribution map of human driver style feature values as an evaluation benchmark to achieve relative driving style evaluation.Finally,a comprehensive driving ability evaluation model with a“punishment”and“affirmation”mechanism is proposed.The experimental comparative analysis shows that the evaluation algorithm proposed in this paper can take into account the driver's driving skill,driving state,and driving style in the real-time comprehensive driving ability evaluation,and draw differential evaluation conclusions based on the“punishment”and“affirmation”mechanism model to achieve a comprehensive and objective evaluation of the driver's driving ability.It can meet the needs of human-machine shared driving decisions for driver's driving ability evaluation.