13 June 2018 in IEEE Transactions on Industrial Electronics
The challenging issue of "human-machine co-pilot" opens up a new frontier to enhance driving safety. However, driver-machine conflicts and uncertain driver/external disturbances are significant problems in cooperative steering system, which degrades the system's path-tracking ability and lowers driving safety. This paper proposes a novel stochastic game-based shared control framework to model steering torque interaction between driver and intelligent electric power steering (IEPS) system. A six-order driver-vehicle dynamic system including driver/external uncertainty is established for path-tracking. Then the affine-linear quadratic (LQ)-based path-tracking problem is proposed to model the maneuvers of driver and IEPS. Particularly, the feedback Nash and Stackelberg frameworks to the affine-quadratic problem are derived by stochastic dynamic programming (SDP). Two cases of co-pilot lane change driving scenarios are studied via computer simulation. The intrinsic relation between stochastic Nash and Stackelberg strategies are investigated based on the results. And the steering-in-the-loop (SIL) experiment reveals the potential of applying the proposed shared control framework to handle driver-IEPS conflicts and uncertain driver/external turbulence. Finally, the co-piloting experiments with human driver further demonstrate the rationality of the game-based pattern between both agents.
21 April 2022 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
In intelligent vehicle cooperative systems, the mismatch in driving characteristics between a human and a machine and the driver misoperation caused by this mismatch result in human–machine conflicts, which significantly affect driving safety. Therefore, an intelligent vehicle human–machine cooperative steering torque control method is proposed herein. To adapt the intelligent system to the varying previewing characteristics of a human, a time-varying previewing driver model is constructed, and a penalty factor for human–machine intervention is designed based on fuzzy rules to assign driving control rights by assessing the driver’s state. Consequently, a human–vehicle–road model with driver preview time and penalty factor as varying parameters is established. Based on gain-scheduling control, a human–machine cooperative steering torque controller is designed to adapt to the varying previewing characteristics of a human and the change in human–machine intervention. The stability and robustness of the entire parameter space are guaranteed by constraining the poles in a certain region. Finally, the proposed human–machine cooperative control scheme demonstrates the effective alleviation of conflicts between the driver and the intelligent driving system.
8 May 2018 in IEEE Transactions on Vehicular Technology
Stability as well as robustness are the major concerns in the design of trajectory tracking controller for autonomous vehicle. In this paper, a novel lateral stability controller design for vehicle path tracking is developed. Firstly, using dynamic game theory as a general framework, vehicle lateral stability can be viewed as a dynamic difference game so that its two players, namely, the active front steering (AFS) system and active rear steering (ARS) system can work together to provide more stability for vehicle path tracking control. The interactive steering control strategies between AFS and ARS are obtained by non-cooperative closed-loop feedback Stackelberg game theory to ensure optimal performance for vehicle path tracking. Then based on the proposed path-following shared control paradigm, by applying the method of zero-sum game theory, a finite-time robust regulator is developed to make the interaction model more robust to uncertain lateral disturbances. Finally, double lane change and serpentine driving condition with and without uncertain time-varying lateral disturbance are used to evaluate the proposed control algorithm. Simulation and hardware-in-loop (HIL) implementation results show that the proposed shared control paradigm-based robust path-tracking controller can robustly provide better lateral stability when time-varying lateral disturbances are bounded.
11 December 2020 in IEEE Transactions on Intelligent Vehicles
Haptic guidance in a shared steering assistance system has drawn significant attention in intelligent vehicle fields, owing to its mutual communication ability for vehicle control. By exerting continuous torque on the steering wheel, both the driver and support system can share lateral control of the vehicle. However, current haptic guidance steering systems demonstrate some deficiencies in assisting lane changing. This study explored a new steering interaction method, including the design and evaluation of an intention-based haptic shared steering system. Such an intention-based method can support both lane keeping and lane changing assistance, by detecting a driver's lane change intention. By using a deep learning-based method to model a driver's decision timing regarding lane crossing, an adaptive gain control method was proposed for realizing a steering control system. An intention consistency method was proposed to detect whether the driver and the system were acting towards the same target trajectories and to accurately capture the driver's intention. A driving simulator experiment was conducted to test the system performance. Participants were required to perform six trials with assistive methods and one trial without assistance. The results demonstrated that the supporting system decreased the lane departure risk in the lane keeping tasks and could support a fast and stable lane changing maneuver.
25 March 2019 in Journal of Dynamic Systems, Measurement, and Control
Driver-machine shared control scheme opens up a new frontier for the design of driver assistance system, especially for improving active safety in emergency scenario. However, the driver's stress response to steering assistance and strong tire nonlinearity are main challenges suffered by controller designing for collision avoidance. These unfavorable factors are particularly pronounced during emergency steering maneuvers and sharply degrade shared control performance. This paper proposes a fuzzy-linear quadratic regulator (LQR) game-based control scheme to simultaneously enhance vehicle stability while compensating driver's inappropriate steering reaction in emergency avoidance. A piecewise linear-based Takagi–Sugeno (T–S) fuzzy structure is presented to mimic driver's knowledge about vehicle lateral nonlinearity, and the control authority is shared between driver and emergency steering assistance (ESA) system through steer-by-wire (SBW) assembly. An identical piecewise internal model is chosen for ESA and the shared lane-keeping problem is modeled as a fuzzy linear quadratic (LQ) problem, where the symmetrical fuzzy structure further enhances vehicle's ability to handle extreme driving conditions. In particular, the feedback Stackelberg equilibrium solutions of the fuzzy-LQ problem are derived to describe the interactive steering behavior of both agents, which enables the ESA to compensate driver's irrational steering reaction. Hardware-in-the-loop (HIL) experiment demonstrates the ESA's capability in compensating driver's aggressive steering behavior, as well as the copiloting system's excellent tracking and stabilizing performance in emergency collision avoidance.
20 March 2019 in Vehicle System Dynamics
As a significant active safety technology towards fully autonomous driving, driver-automation co-piloting provides a new thinking for enhancing vehicle active safety and relieving driver’s workload. However, the preview pattern divergence between driver and steering assistance system (SAS) may give rise to serious steering conflicts, which reduces driver’s faith in SAS, cause him/her to turn off it, and even result in fatal traffic accidents. Focusing on mimicking the driver’s steering behaviour, this paper proposes a human-like steering assistance scheme by adaptively varying the preview time and assistance gain of the SAS controller. Driver’s preview behaviour of the road curvature is numerically identified using simulator tests along a multi-curves road, based on which a nominal preview-scheduled driver model is established. Based on the nominal driver model, a co-piloting system featuring human-like preview behaviour and a time-varying assistance penalty is proposed to formulate the steering torque-overlay dynamics of both agents in path-tracking. Next, a linear parameter varying (LPV)/H∞ controller satisfying pole placement is integrated to ensure the robustness and stability within the entire parameter space. This enables the steering assistance scheme to have a scheduled preview pattern like a human driver. Results of driving simulator experiment indicate that the proposed steering assistance scheme is able to mitigate driver-SAS conflicts and improve driver’s path-tracking performance.