A Control Strategy to Compensate the Reaction Torque of Active Front Steering System

Noh, Taebong; Kim, Jaesuk; Choi, Jeong‐Woo; Cha, Hangbyong

doi:10.4271/2007-01-3659

Cited by 6 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stochastic policy is defined by formula (7). Deterministic policy is defined by formula (8). Besides TD error is used to estimate critic respite of the importance weight.…”

Section: Deep Deterministic Policy Gradientmentioning

confidence: 99%

“…6,7 The decoupling of hand wheel torque and wheel angle is implemented to solve the unexpected reaction hand wheel torque caused by the additional steering angle. 8 The experimental data of human mechanical impedance properties (HMIPs) of arms in steering operations according to the angle of a steering wheel (limbs posture) and the steering torque (muscle co-contraction) are measured, based on which a novel methodology for designing an adaptive steering control system is proposed. 9 Traditional ASS systems are widely used in driving assistance systems, especially in vehicle handling dynamics control.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A model free controller based on reinforcement learning for active steering system with uncertainties

Zhao

Cheng

Zhang

et al. 2021

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

Vehicle steering control is crucial to autonomous vehicles. However, unknown parameters and uncertainties of vehicle steering systems bring a great challenge to its control performance, which needs to be tackled urgently. Therefore, this paper proposes a novel model free controller based on reinforcement learning for active steering system with unknown parameters. The model of the active steering system and the Brushless Direct Current (BLDC) motor is built to construct a virtual object in simulations. The agent based on Deep Deterministic Policy Gradient (DDPG) algorithm is built, including actor network and critic network. The rewards from environment are designed to improve the effectiveness of agent. Simulations and testbench experiments are implemented to train the agent and verify the effectiveness of the controller. Results show that the proposed algorithm can acquire the network parameters and achieve effective control performance without any prior knowledges or models. The proposed agent can adapt to different vehicles or active steering systems easily and effectively with only retraining of the network parameters.

show abstract

“…Stochastic policy is defined by formula (7). Deterministic policy is defined by formula (8). Besides TD error is used to estimate critic respite of the importance weight.…”

Section: Deep Deterministic Policy Gradientmentioning

confidence: 99%