A Novel Hybrid Path Planning Method Based on Q-Learning and Neural Network for Robot Arm

Abdi, Ali; Adhikari, Dibash; Park, Ju Hong

doi:10.3390/app11156770

Cited by 20 publications

(20 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We tested this computer vision-based path planning algorithm through simulation and experimental methods. The results revealed that this research overcame the limitations of our previous research [9].…”

Section: Discussionmentioning

confidence: 65%

“…To this end, first, we compare our method with other methods in terms of speed which is a crucial feature in real-time path planning. To compare this method with other path planning methods, we refer to our previous study [9]. In that paper, we compared the speed of running time in our hybrid path planning method and other conventional path planning methods such as RL-based, APF, PRM, and RRT.…”

Section: Discussionmentioning

confidence: 99%

“…To this end, although we tried to address those limitations in our previous paper [9], some of them remain. This article that is, in fact, an extension of our previous study, tries to address the limitations of prior work.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Computer Vision-Based Path Planning for Robot Arms in Three-Dimensional Workspaces Using Q-Learning and Neural Networks

Abdi

Ranjbar

Park

2022

Sensors

Self Cite

View full text Add to dashboard Cite

Computer vision-based path planning can play a crucial role in numerous technologically driven smart applications. Although various path planning methods have been proposed, limitations, such as unreliable three-dimensional (3D) localization of objects in a workspace, time-consuming computational processes, and limited two-dimensional workspaces, remain. Studies to address these problems have achieved some success, but many of these problems persist. Therefore, in this study, which is an extension of our previous paper, a novel path planning approach that combined computer vision, Q-learning, and neural networks was developed to overcome these limitations. The proposed computer vision-neural network algorithm was fed by two images from two views to obtain accurate spatial coordinates of objects in real time. Next, Q-learning was used to determine a sequence of simple actions: up, down, left, right, backward, and forward, from the start point to the target point in a 3D workspace. Finally, a trained neural network was used to determine a sequence of joint angles according to the identified actions. Simulation and experimental test results revealed that the proposed combination of 3D object detection, an agent-environment interaction in the Q-learning phase, and simple joint angle computation by trained neural networks considerably alleviated the limitations of previous studies.

show abstract

Section: Discussionmentioning

confidence: 65%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Computer Vision-Based Path Planning for Robot Arms in Three-Dimensional Workspaces Using Q-Learning and Neural Networks

Abdi

Ranjbar

Park

2022

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…It can be assumed that the link of the robot arm makes a kinematic chain and the end of this chain is termed an end effector to execute the normal operations, like, cutting, grasping, and so forth. The robot arm is mostly applied in current society (Soria et al, 2019; Abdi et al, 2021), and also it is applied in industrial manufacturing to perform operations, like, welding, assembly, spraying, and so forth. Besides, it is applied as a surgical aid in the medical domain (Misra & Singh, 2019).…”

Section: Introductionmentioning

confidence: 99%

Combinations of novel hybrid optimization algorithms‐based trajectory planning analysis for an industrial robotic manipulators

Singh

Banga

2022

Journal of Field Robotics

View full text Add to dashboard Cite

In this paper, an optimal collision-free trajectory is developed based on the hybrid optimization algorithms for industrial robotic manipulators (IRMs). Three IRMs such as PUMA 560 (six degrees of freedom-6DOF), KUKA LBR iiwa 14 R820 (7DOF), and ABB IRB 140 (6DOF) are considered. The key objective is to enhance the smoothness and efficiency of manufacturing robots by optimum joint trajectory design using the seventh-order polynomial function. The proposed approach is to solve both kinematics and trajectory planning problems by using the different combinations of the hybrid meta-heuristic algorithms. The kinematic parameters including jerk, acceleration, and velocity mostly impact the travel smoothness of the robot end-effector on the trajectory path. Therefore, these parameters are to be constrained for generating the collision-free path. The endurance of velocity and acceleration can be obtained by reducing the jerk which leads to smooth robotic motion. The proposed work is executed using a robotic toolbox in MATLAB with a graphical user interface. The values of acceleration, velocity, and jerk are computed for the robot joints. Each robot obtained the minimum traveling time for without and with an obstacle which is 0.0118 and 0.0313 s for PUMA and 0.0117 and 0.0310 s for KUKA, and 0.0114 and 0.0120 s for ABB IRB 140 robot. From the experimental outcomes, the proposed scheme of the hybrid optimization algorithms is more effective for the trajectory planning of IRMs than that of other works.

show abstract

“…After setting a reward mechanism, with the Q-learning, robot can find an optimal path which obtains the max rewards among all, staring from the current state. On the one hand, for solitary robots, Q-learning combined with neural network present a new hybrid path planning method for robot arm [5]. Besides, using Q-learning helps high-level path planning for an autonomous sailboat robot [6].…”

Section: Introductionmentioning

confidence: 99%

A simple implement of Q-learning in robot path planning

Gao

Liu²,

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

This paper firstly gives an introduction of robot path planning problem, which includes the brief definition of path planning, some representative methods and previous applications of Q-learning. Secondly, the paper compares some typical methods, like Breadth First Search and Depth-First-Search, A* and deep learning, with corresponding pseudo codes in detail. Their advantages and disadvantages are also listed in this part. Thirdly, we carry out a simple simulation experiment by applying Q-learning method. The experiment is clearly presented in several parts which includes environment establishment, realizing the Q-learning, simulation experiment and interpretation of the Q-table. In the end, a short conclusion summarizes the achievement of our results.

show abstract

A Novel Hybrid Path Planning Method Based on Q-Learning and Neural Network for Robot Arm

Cited by 20 publications

References 14 publications

Computer Vision-Based Path Planning for Robot Arms in Three-Dimensional Workspaces Using Q-Learning and Neural Networks

Computer Vision-Based Path Planning for Robot Arms in Three-Dimensional Workspaces Using Q-Learning and Neural Networks

Combinations of novel hybrid optimization algorithms‐based trajectory planning analysis for an industrial robotic manipulators

A simple implement of Q-learning in robot path planning

Contact Info

Product

Resources

About