http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Recurrent Neural Network-Based Model Predictive Control for Waypoint Tracking
Ying Shuai Quan,Woo Young Choi,Seung-Hi Lee,Chung Choo Chung 한국자동차공학회 2019 한국자동차공학회 부문종합 학술대회 Vol.2019 No.5
This paper presents an recurrent neural network-based model predictive control for an autonomous driving vehicle. Model predictive control is effective in vehicle lateral control but too computationally expensive to be applied in real-time control. To resolve this problem, we propose a recurrent neural network-based approximate model predictive control. The offline-trained neural network exhibits the ability to model the waypoint tracking system and provided the closed-loop performance. The performance of the approximate recurrent neural network-model predictive control (RNN-MPC) is validated by computational experiments of waypoints tracking control scheme.
Ying Shuai Quan,Jin Sung Kim,정정주 제어·로봇·시스템학회 2022 International Journal of Control, Automation, and Vol.20 No.7
This paper presents a robust controller using a Linear Parameter Varying (LPV) model of a lane-keeping system with parameter reduction. Both varying vehicle speed and roll motion on a curved road influence the lateral vehicle model’s parameters, such as tire cornering stiffness. Thus, we use the LPV technique to take the parameter variations into account in vehicle dynamics. However, multiple varying parameters lead to a high number of scheduling variables and cause massive computational complexity. In this paper, to reduce the computational complexity, Principal Component Analysis (PCA)-based parameter reduction is performed to obtain a reduced model with a tighter convex set. We designed the LPV robust feedback controller using the reduced model solving a set of Linear Matrix Inequality (LMI). The effectiveness of the proposed system is validated with full vehicle dynamics from CarSim on an interchange road. From the simulation, we confirmed that the proposed method largely reduces the lateral offset error, compared with other controllers based on a Linear Time-Invariant (LTI) system.
Q learning-based Autonomous Valet Parking System
Ying Shuai Quan(전영수),Dae Jung Kim(김대정),Seung-Hi Lee,Chung Choo Chung 한국자동차공학회 2020 한국자동차공학회 부문종합 학술대회 Vol.2020 No.7
In this paper, we propose a brand new vehicle lateral motion control algorithm for autonomous parking system utilizing Q-learning algorithm. Normally for optimal vehicle control, linearization is introduced to deal with the nonlinearity of vehicle dynamics, which reduces the optimality of the derived control laws. To solve the problem, a Q-learning based vehicle parking control algorithm is proposed. A path planning method is introduced to the design of the state vector in the Q-learning algorithm for vehicle lateral control. Feasibility of the proposed algorithm is validated by computational simulation results showing satisfactory performances on the test scenario.
Ying Shuai Quan,Jin Sung Kim,Chung Choo Chung 제어로봇시스템학회 2021 제어로봇시스템학회 국제학술대회 논문집 Vol.2021 No.10
In this paper, we propose a Robust Model Predictive Control combined with Control Barrier Function (RMPC-CBF) for a nonholonomic robot with obstacle avoidance subject to additive input disturbances. Both Input-to-State Stability (ISS) and Input-to-State Safety (ISSf) are provided to theoretically guarantee the system’s stability and safety. CBF-based safety conditions are formulated as constraints inside a robust MPC strategy. Robust satisfaction of the constraints is ensured by tightening the state constraint set. With admissible disturbances under a certain bound, ISS and robust recursive feasibility are guaranteed by computing the terminal region and state constraint set. For obstacle avoidance, Input-to-State Safe Control Barrier Function (ISSf-CBF) is chosen to provide robust set safety for the dynamic systems under input disturbances, which always guarantees that states stay inside or close to the safe set. With the proposed method, the future state prediction is taken into consideration and optimal performance is accomplished via MPC, and the system’s safety is ensured via CBF. Numerical simulation results confirm the effectiveness and validity of the proposed approach.