Robotic Grasping using Deep Reinforcement Learning

Joshi, Shirin; Kumra, Sulabh; Sahin, Ferat

doi:10.1109/case48305.2020.9216986

Cited by 72 publications

(41 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The evaluation indicates that DQL performs better on grasping tasks than other algorithms in low-data regimes for learning with both off-policy and on-policy and, furthermore, has the desirable property of being relatively robust to the hyperparameter choice [17]. The results also show that DQN, as well as the double-DQN, have comparatively higher resolution and success rates than the basic quality learning framework.…”

Section: Reinforcement Learningmentioning

confidence: 86%

Vision-Based Robotic Arm Control Algorithm Using Deep Reinforcement Learning for Autonomous Objects Grasping

et al. 2021

View full text Add to dashboard Cite

While working side-by-side, humans and robots complete each other nowadays, and we may say that they work hand in hand. This study aims to evolve the grasping task by reaching the intended object based on deep reinforcement learning. Thereby, in this paper, we propose a deep deterministic policy gradient approach that can be applied to a numerous-degrees-of-freedom robotic arm towards autonomous objects grasping according to their classification and a given task. In this study, this approach is realized by a five-degrees-of-freedom robotic arm that reaches the targeted object using the inverse kinematics method. You Only Look Once v5 is employed for object detection, and backward projection is used to detect the three-dimensional position of the target. After computing the angles of the joints at the detected position by inverse kinematics, the robot’s arm is moved towards the target object’s emplacement thanks to the algorithm. Our approach provides a neural inverse kinematics solution that increases overall performance, and its simulation results reveal its advantages compared to the traditional one. The robot’s end grip joint can reach the targeted location by calculating the angle of every joint with an acceptable range of error. However, the accuracy of the angle and the posture are satisfied. Experiments reveal the performance of our proposal compared to the state-of-the-art approaches in vision-based grasp tasks. This is a new approach to grasp an object by referring to inverse kinematics. This method is not only easier than the standard one but is also more meaningful for multi-degrees of freedom robots.

show abstract

Section: Reinforcement Learningmentioning

confidence: 86%

Vision-Based Robotic Arm Control Algorithm Using Deep Reinforcement Learning for Autonomous Objects Grasping

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In recent years, simulation has emerged as a popular means of initially testing a research hypothesis in robotics manipulation research, since it is faster and less resource intensive than real-world testing with a physical robot [7], [11], [23]. The simulation environment developed in this research was informed by a number of recent studies involving the simulation of robotic grasping, including [24] and [25].…”

Section: Methodsmentioning

confidence: 99%

Using Tactile Sensing to Improve Performance when Grasping Moving Objects

Lynch

McGinn

2021

2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

View full text Add to dashboard Cite

To operate in unstructured settings, robots require control strategies that effectively respond to temporal changes in their environment. In the domain of robotic manipulation, most state-of-the-art approaches assume the objects to be grasped are static. Although some research has investigated the challenges of grasping moving objects, these studies have tended to use grasping plans which require a real-time estimate of a gripper-object interception point, which can be difficult to precisely obtain. The goal of this research was to investigate the performance benefits of using a controller with a reactive component for grasping tasks involving moving objects. We hypothesised that using a reactive control strategy, based on tactile sensing in the fingertips, would lead to improved performance and robustness across a wider range of grasping conditions. To test this hypothesis, the ability of a two-finger gripper to grasp a moving ball under a range of dynamic conditions was tested in simulation using the Gazebo robotic simulator and ODE physics engine. Tests revealed that for controllers where the grasp was not informed by tactile sensing, grasping success dropped significantly with increased misalignment between the centre point of the gripper and the point of interception with the moving object. In contrast, the performance of a reactive grasping strategy based on tactile sensing was found to be more robust across these conditions. These findings indicate that tactile sensing could play an important role in enabling robots to interact more effectively with dynamic objects.

show abstract

“…Joshi et al, in [ 73 ], demonstrate a method based on deep reinforcement learning to solve a robotic gripping problem using visio-motor feedback. A posture assessment system based on the “eye-to-hand” camera has been developed in [ 74 ] for robotic machining, and the accuracy of the estimated pose is improved using two different approaches, namely sparse regression, and LSTM neural networks.…”

Section: Related Work and Problem Statementmentioning

confidence: 99%

Machine Learning Techniques for Increasing Efficiency of the Robot’s Sensor and Control Information Processing

Kondratenko

Atamanyuk

Sidenko

et al. 2022

Sensors

View full text Add to dashboard Cite

Real-time systems are widely used in industry, including technological process control systems, industrial automation systems, SCADA systems, testing, and measuring equipment, and robotics. The efficiency of executing an intelligent robot’s mission in many cases depends on the properties of the robot’s sensor and control systems in providing the trajectory planning, recognition of the manipulated objects, adaptation of the desired clamping force of the gripper, obstacle avoidance, and so on. This paper provides an analysis of the approaches and methods for real-time sensor and control information processing with the application of machine learning, as well as successful cases of machine learning application in the synthesis of a robot’s sensor and control systems. Among the robotic systems under investigation are (a) adaptive robots with slip displacement sensors and fuzzy logic implementation for sensor data processing, (b) magnetically controlled mobile robots for moving on inclined and ceiling surfaces with neuro-fuzzy observers and neuro controllers, and (c) robots that are functioning in unknown environments with the prediction of the control system state using statistical learning theory. All obtained results concern the main elements of the two-component robotic system with the mobile robot and adaptive manipulation robot on a fixed base for executing complex missions in non-stationary or uncertain conditions. The design and software implementation stage involves the creation of a structural diagram and description of the selected technologies, training a neural network for recognition and classification of geometric objects, and software implementation of control system components. The Swift programming language is used for the control system design and the CreateML framework is used for creating a neural network. Among the main results are: (a) expanding the capabilities of the intelligent control system by increasing the number of classes for recognition from three (cube, cylinder, and sphere) to five (cube, cylinder, sphere, pyramid, and cone); (b) increasing the validation accuracy (to 100%) for recognition of five different classes using CreateML (YOLOv2 architecture); (c) increasing the training accuracy (to 98.02%) and testing accuracy (to 98.0%) for recognition of five different classes using Torch library (ResNet34 architecture) in less time and number of epochs compared with Create ML (YOLOv2 architecture); (d) increasing the training accuracy (to 99.75%) and testing accuracy (to 99.2%) for recognition of five different classes using Torch library (ResNet34 architecture) and fine-tuning technology; and (e) analyzing the effect of dataset size impact on recognition accuracy with ResNet34 architecture and fine-tuning technology. The results can help to choose efficient (a) design approaches for control robotic devices, (b) machine-learning methods for performing pattern recognition and classification, and (c) computer technologies for designing control systems and simulating robotic devices.

show abstract

Robotic Grasping using Deep Reinforcement Learning

Cited by 72 publications

References 17 publications

Vision-Based Robotic Arm Control Algorithm Using Deep Reinforcement Learning for Autonomous Objects Grasping

Vision-Based Robotic Arm Control Algorithm Using Deep Reinforcement Learning for Autonomous Objects Grasping

Using Tactile Sensing to Improve Performance when Grasping Moving Objects

Machine Learning Techniques for Increasing Efficiency of the Robot’s Sensor and Control Information Processing

Contact Info

Product

Resources

About