KEYWORDS: Neural networks, Device simulation, System identification, Control systems, Cameras, Systems modeling, Performance modeling, Mathematical modeling, Data modeling
Deep reinforcement learning (DRL) is based on rigorous mathematical foundations and adjusts network parameters through interactions with the environment. The stability problem of maintaining a vehicle on a continuous path can be achieved by soft actor-critic (SAC). Furthermore, a model predictive control (MPC) with prediction and control horizons under multivariable constraints can precisely follow the path, but the disadvantage is its large computation. In this paper, a DRL control scheme with MPC is proposed to precisely and effectively implement the path following and obstacle avoidance of tracked vehicle. The DRL controller performs the effective obstacle avoidance and is also in accordance with MPC to precisely follow planning paths. To make the training more realistic, a data-driven state-space dynamic model of the tracked vehicle is first estimated via N4SID system identification algorithm. During the DRL training, the MPC output is used as the reward input of the DRL to learn the MPC characteristics and an additional reward function is designed specifically for obstacle avoidance. The parameters of the DRL agent are adjusted based on the environment input and the MPC output. After the training, the MPC can be skipped since it is used as a part of the reward function, and the DRL has learned to imitate the MPC while achieves obstacle avoidance. The simulation and experimental results show that the overall controller has high stability, accuracy, and efficiency.
KEYWORDS: Systems modeling, Agriculture, Vehicle control, Unmanned ground vehicles, Control systems design, Control systems, Applied research, Unmanned vehicles, Process control, Photonics
Unmanned ground vehicles (UGVs) will be widely adopted in agricultural applications. To accomplish autonomous cruising in farm, path following is an essential skill. However, in the process of field cruising, some obstacles such as wild animals or motorcycles are present. In this study, tracked vehicles are utilized with deep deterministic policy gradient (DDPG) compensating for model uncertainties and achieving collision avoidance simultaneously. Among all, the most important issue is to keep the UGV following the predetermined path in specific agricultural field environment and coping with the uncertainty of the surroundings. Path following and obstacle avoidance of field tracked vehicles are conducted by using model predictive control (MPC) with a controller (agent) trained by DDPG. Therefore, we proposed control algorithm fusion with MPC and model-free DDPG.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.