NAO robot obstacle avoidance based on fuzzy Q-learning

Wen, Shuhuan; Hu, Xueheng; Li, Zhen; Lam, Hak‐Keung; Sun, Fei; Fang, Bin

doi:10.1108/ir-01-2019-0002

Cited by 10 publications

(7 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fuzzy logic control rationalized rules from the previous information for the obstacle avoidance method. It is proven to show great performance and less reliance on the environment [16]. As shown in Fig.…”

Section: Fuzzy Logic Control Methodsmentioning

confidence: 99%

Development of a Logistics Autonomous Mobile Robot (EasyBot)

Hussain

Mohd‐Mokhtar

2021

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

This paper presents the development of a logistics autonomous mobile robot by using the line following method which has 3 features of the robot: (1) Line Following; (2) Obstacle Detection; (3) Bluetooth Control. The aim is to replace the need for humans to transportation blood bags for storage in hospitals as an autonomous system design. Infra-Red (IR) sensors are implemented in the robot to detect the path required for the robot to move from point A to B. Ultrasonic sensors are used to detect obstacles. Bluetooth module is used to manually control the robot in case of (1) obstacles cannot be move; (2) relocating the robot. The robot utilizes the Arduino Uno board as the main controller to make the project runs. Finally, the robot's performance is assessed to get it to follow the line accurately and smoothly without drifting away from the line. Experiments are carried out on the best programming, controls, and mechanical design for the best performance of the robots. From results, the robot able to achieve the objectives set to it. This development can give another robot tasking that capable of performing logistic jobs in a designed environment.

show abstract

Section: Fuzzy Logic Control Methodsmentioning

confidence: 99%

Development of a Logistics Autonomous Mobile Robot (EasyBot)

Hussain

Mohd‐Mokhtar

2021

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

show abstract

“…Therefore, the selection of each action plays an extremely important role for the agent to take the optimal path in the end (Yao et al , 2010). However, according to our previous research results (Wen et al , 2019a), in the action space, if all possible actions are selected with equal probability, the optimal path will not be selected in path planning. In some states, other actions may be selected instead of the optimal action.…”

Section: Active Fastslam Based On Probability Dueling Dqnmentioning

confidence: 99%

Probability Dueling DQN active visual SLAM for autonomous navigation in indoor environment

Wen

Lam

et al. 2021

Self Cite

View full text Add to dashboard Cite

Purpose This paper aims to use the Monodepth method to improve the prediction speed of identifying the obstacles and proposes a Probability Dueling DQN algorithm to optimize the path of the agent, which can reach the destination more quickly than the Dueling DQN algorithm. Then the path planning algorithm based on Probability Dueling DQN is combined with FastSLAM to accomplish the autonomous navigation and map the environment. Design/methodology/approach This paper proposes an active simultaneous localization and mapping (SLAM) framework for autonomous navigation under an indoor environment with static and dynamic obstacles. It integrates a path planning algorithm with visual SLAM to decrease navigation uncertainty and build an environment map. Findings The result shows that the proposed method offers good performance over existing Dueling DQN for navigation uncertainty under the indoor environment with different numbers and shapes of the static and dynamic obstacles in the real world field. Originality/value This paper proposes a novel active SLAM framework composed of Probability Dueling DQN that is the improved path planning algorithm based on Dueling DQN and FastSLAM. This framework is used with the Monodepth depth image prediction method with faster prediction speed to realize autonomous navigation in the indoor environment with different numbers and shapes of the static and dynamic obstacles.

show abstract

“…The algorithm focuses on value-based reinforcement learning that is updated as the environment is explored by means of the Q-value function [57][58][59][60]. Recently, combining intelligent control and Q-learning are also applied [61][62][63][64][65]. However, these studies are only carried out on simulations, as well as experiments with simple static objects.…”

Section: Introductionmentioning

confidence: 99%

“…This means that the training is difficult to perform in a real environment and tends to be done mostly in simulation. From [61][62][63][64][65] it can be seen that Q-learning are trainable in virtual environments and afterward transferable to the real world in robot applications. To address these challenges, in this research the training environment for the RL agent in a virtual environment is developed.…”

Section: Introductionmentioning

confidence: 99%

Path Following and Avoiding Obstacle for Mobile Robot Under Dynamic Environments Using Reinforcement Learning

Hanh

Cong

2023

Journal of Robotics and Control

View full text Add to dashboard Cite

Obstacle avoidance for mobile robot to reach the desired target from a start location is one of the most interesting research topics. However, until now, few works discuss about working of mobile robot in the dynamic and continuously changing environment. So, this issue is still the research challenge for mobile robots. Traditional algorithm for obstacle avoidance in the dynamic, complex environment had many drawbacks. As known that Q-learning, the type of reinforcement learning, has been successfully applied in computer games. However, it is still rarely used in real world applications. This research presents an effectively method for real time dynamic obstacle avoidance based on Q-learning in the real world by using three-wheeled mobile robot. The position of obstacles including many static and dynamic obstacles and the mobile robot are recognized by fixed camera installed above the working space. The input for the robot is the 2D data from the camera. The output is an action for the robot (velocities, linear and angular parameters). Firstly, the simulation is performed for Q-learning algorithm then based on trained data, The Q-table value is implemented to the real mobile robot to perform the task in the real scene. The results are compared with intelligent control method for both static and dynamic obstacles cases. Through implement experiments, the results show that, after training in dynamic environments and testing in a new environment, the mobile robot is able to reach the target position successfully and have better performance comparing with fuzzy controller.

show abstract

NAO robot obstacle avoidance based on fuzzy Q-learning

Cited by 10 publications

References 30 publications

Development of a Logistics Autonomous Mobile Robot (EasyBot)

Development of a Logistics Autonomous Mobile Robot (EasyBot)

Probability Dueling DQN active visual SLAM for autonomous navigation in indoor environment

Path Following and Avoiding Obstacle for Mobile Robot Under Dynamic Environments Using Reinforcement Learning

Contact Info

Product

Resources

About