Autonomous Control of a Line Follower Robot Using a Q-Learning Controller

Saadatmand, Sepehr; Azizi, Sima; Kavousi, Mohammadamir; Wunsch, Donald C.

doi:10.1109/ccwc47524.2020.9031160

Cited by 27 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There are automatic design approaches proposed so far to develop end to end control policies for robotic swarms. However, Q learning techniques provides advantages in two ways [45]: researchers are enabled to develop in an end to end fashion, and in the case of a gigantic parameter space in developing the control policy, fewer computation policy is required. In addition, by pre-training of feature maps using the depth information, Q learning could also be used to explore a corridor environment with the depth information from an RGB sensor only, which enables the controller to achieve obstacle avoidance ability [46][47].…”

Section: Roboticsmentioning

confidence: 99%

Q-learning for single-agent and multi-agent and its application

Yan²

2022

2nd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2022)

View full text Add to dashboard Cite

Q-learning is a reinforcement learning method for solving Markov decision problems with incomplete information proposed by Watkins. With the develop of reinforcement learning, more and more Q-learning related algorithms have been proposed, and their application range has become wider. In this paper, we discussed single agent algorithms including basic Q learning, deep Q learning and double Q learning. In addition, we discussed multi-agent algorithms including modular Q learning, ant Q learning and Nash Q learning with prominent characteristics. This paper will compare their advantages and disadvantages, and put forward our own views on the current application of Q-learning and the future trend of Q-learning.

show abstract

Section: Roboticsmentioning

confidence: 99%

Q-learning for single-agent and multi-agent and its application

Yan²

2022

2nd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2022)

View full text Add to dashboard Cite

show abstract

“…Classical controllers such as PID controllers are not capable of controlling a system with such transients. Hence, researchers have investigated methods such as model predictive control and neural networks to cope with this issue [18]- [23]. To cope with the nonlinearities of the model, Ref [19] has introduced a Taylor expansion algorithm to approximate the variations of the model as a function of the rotor angle and current.…”

Section: Optimal Tracking Current Control Of Switched Reluctance Motomentioning

confidence: 99%

Optimal Tracking Current Control of Switched Reluctance Motor Drives Using Reinforcement Q-Learning Scheduling

et al. 2021

Self Cite

View full text Add to dashboard Cite

In this paper, a novel Q-learning scheduling method for the current controller of a switched reluctance motor (SRM) drive is investigated. The Q-learning algorithm is a class of reinforcement learning approaches that can find the best forward-in-time solution of a linear control problem. An augmented system is constructed based on the reference current signal and the SRM model to allow for solving the algebraic Riccati equation of the current-tracking problem. This paper introduces a new scheduled-Q-learning algorithm that utilizes a table of Q-cores that lies on the nonlinear surface of an SRM model without involving any information about the model parameters to track the reference current trajectory by scheduling the infinite horizon linear quadratic trackers (LQT) handled by Q-learning algorithms. Additionally, a linear interpolation algorithm is proposed to improve the transition of the LQT between trained Q-cores to ensure a smooth response as state variables evolve on the nonlinear surface of the model. Lastly, simulation and experimental results are provided to validate the effectiveness of the proposed control scheme.

show abstract

“…自主控制技术是指在无人干预的情况下, 机器人把自主控制系统的感知、决策、协同和行动能力结合起来, 在非结构化环境下根据一定的控制策略自我决策, 并持续执行一系列控制功能以完成预定目标的能力. 自主控制系统也是实现应急防控机器人智能化的基础, 它往往需要高层次的感知系统, 以实现更为精准和灵活的控制策略, 如视觉系统 [89] 等. Saadatmand 等 [90] 提出了一种基于人工智能的 Q-learning 控制器, 以实现对机器人的最优控制. Hafez 等 [91] 研究了完整性风险作为约束条件时, 模型预测控制器在机器人的跟踪中的应用, 这对机器人自主控制的安全性有重要的意义.…”

Section: 自主控制及专用末端工具unclassified

Research on intelligent robot systems for emergency prevention and control of major pandemics

Zhang

Zhong

et al. 2020

Sci. Sin.-Inf.

View full text Add to dashboard Cite

A novel optimization method of transient stability emergency control based on practical dynamic security region (PDSR) of power systems Science in China Series E-Technological Sciences 47, 376 (2004); Output feedback control for mobile robot systems with significant external disturbances SCIENCE CHINA Information Sciences 63, 199201 (2020); Intelligent modeling and control for nonlinear systems with rate-dependent hysteresis Science in China Series F-Information Sciences 52, 656 (2009);

show abstract

Autonomous Control of a Line Follower Robot Using a Q-Learning Controller

Cited by 27 publications

References 8 publications

Q-learning for single-agent and multi-agent and its application

Q-learning for single-agent and multi-agent and its application

Optimal Tracking Current Control of Switched Reluctance Motor Drives Using Reinforcement Q-Learning Scheduling

Research on intelligent robot systems for emergency prevention and control of major pandemics

Contact Info

Product

Resources

About