Research

21 pages, 9468 KiB

Open AccessArticle

Constraint-Aware Policy for Compliant Manipulation

by Daichi Saito, Kazuhiro Sasabuchi, Naoki Wake, Atsushi Kanehira, Jun Takamatsu, Hideki Koike and Katsushi Ikeuchi

Robotics 2024, 13(1), 8; https://doi.org/10.3390/robotics13010008 - 27 Dec 2023

Viewed by 1429

Abstract

Robot manipulation in a physically constrained environment requires compliant manipulation. Compliant manipulation is a manipulation skill to adjust hand motion based on the force imposed by the environment. Recently, reinforcement learning (RL) has been applied to solve household operations involving compliant manipulation. However, [...] Read more.

Robot manipulation in a physically constrained environment requires compliant manipulation. Compliant manipulation is a manipulation skill to adjust hand motion based on the force imposed by the environment. Recently, reinforcement learning (RL) has been applied to solve household operations involving compliant manipulation. However, previous RL methods have primarily focused on designing a policy for a specific operation that limits their applicability and requires separate training for every new operation. We propose a constraint-aware policy that is applicable to various unseen manipulations by grouping several manipulations together based on the type of physical constraint involved. The type of physical constraint determines the characteristic of the imposed force direction; thus, a generalized policy is trained in the environment and reward designed on the basis of this characteristic. This paper focuses on two types of physical constraints: prismatic and revolute joints. Experiments demonstrated that the same policy could successfully execute various compliant manipulation operations, both in the simulation and reality. We believe this study is the first step toward realizing a generalized household robot. Full article

(This article belongs to the Special Issue Advanced Grasping and Motion Control Solutions)

► Show Figures

Figure 1

14 pages, 4444 KiB

Open AccessArticle

Multi-Log Grasping Using Reinforcement Learning and Virtual Visual Servoing

by Erik Wallin, Viktor Wiberg and Martin Servin

Robotics 2024, 13(1), 3; https://doi.org/10.3390/robotics13010003 - 21 Dec 2023

Cited by 1 | Viewed by 1492

Abstract

We explore multi-log grasping using reinforcement learning and virtual visual servoing for automated forwarding in a simulated environment. Automation of forest processes is a major challenge, and many techniques regarding robot control pose different challenges due to the unstructured and harsh outdoor environment. [...] Read more.

We explore multi-log grasping using reinforcement learning and virtual visual servoing for automated forwarding in a simulated environment. Automation of forest processes is a major challenge, and many techniques regarding robot control pose different challenges due to the unstructured and harsh outdoor environment. Grasping multiple logs involves various problems of dynamics and path planning, where understanding the interaction between the grapple, logs, terrain, and obstacles requires visual information. To address these challenges, we separate image segmentation from crane control and utilise a virtual camera to provide an image stream from reconstructed 3D data. We use Cartesian control to simplify domain transfer to real-world applications. Because log piles are static, visual servoing using a 3D reconstruction of the pile and its surroundings is equivalent to using real camera data until the point of grasping. This relaxes the limits on computational resources and time for the challenge of image segmentation, and allows for data collection in situations where the log piles are not occluded. The disadvantage is the lack of information during grasping. We demonstrate that this problem is manageable and present an agent that is 95% successful in picking one or several logs from challenging piles of 2–5 logs. Full article

(This article belongs to the Special Issue Advanced Grasping and Motion Control Solutions)

► Show Figures

Figure 1

17 pages, 3012 KiB

Open AccessArticle

Improving the Grasping Force Behavior of a Robotic Gripper: Model, Simulations, and Experiments

by Giuseppe Vitrani, Simone Cortinovis, Luca Fiorio, Marco Maggiali and Rocco Antonio Romeo

Robotics 2023, 12(6), 148; https://doi.org/10.3390/robotics12060148 - 31 Oct 2023

Viewed by 1829

Abstract

Robotic grippers allow industrial robots to interact with the surrounding environment. However, control architectures of the grasping force are still rare in common industrial grippers. In this context, one or more sensors (e.g., force or torque sensors) are necessary. However, the incorporation of [...] Read more.

Robotic grippers allow industrial robots to interact with the surrounding environment. However, control architectures of the grasping force are still rare in common industrial grippers. In this context, one or more sensors (e.g., force or torque sensors) are necessary. However, the incorporation of such sensors might heavily affect the cost of the gripper, regardless of its type (e.g., pneumatic or electric). An alternative approach could be open-loop force control strategies. Hence, this work proposes an approach for optimizing the open-loop grasping force behavior of a robotic gripper. For this purpose, a specialized robotic gripper was built, as well as its mathematical model. The model was employed to predict the gripper performance during both static and dynamic force characterization, simulating grasping tasks under different experimental conditions. Both simulated and experimental results showed that by managing the mechanical properties of the finger–object contact interface (e.g., stiffness), the steady-state force variability could be greatly reduced, as well as undesired effects such as finger bouncing. Further, the object’s size is not required unlike most of the grasping approaches for industrial rigid grippers, which often involve high finger velocities. These results may pave the way toward conceiving cheaper and more reliable open-loop force control techniques for use in robotic grippers. Full article

(This article belongs to the Special Issue Advanced Grasping and Motion Control Solutions)

► Show Figures

Figure 1

24 pages, 9695 KiB

Open AccessArticle

CAD-Based Robot Programming Solution for Wire Harness Manufacturing in Aeronautic Sector

by Javier González Huarte, Maite Ortiz de Zarate and Aitor Ibarguren

Robotics 2023, 12(5), 130; https://doi.org/10.3390/robotics12050130 - 14 Sep 2023

Cited by 1 | Viewed by 1765

Abstract

Wire harness manufacturing in the aeronautic sector is highly manual work, with production defined by multiple references and small batches. Although complete automation of the production process is not feasible, a robot-assisted approach could increase the efficiency of the existing production means. This [...] Read more.

Wire harness manufacturing in the aeronautic sector is highly manual work, with production defined by multiple references and small batches. Although complete automation of the production process is not feasible, a robot-assisted approach could increase the efficiency of the existing production means. This paper presents a novel dual-arm robotic solution for workbench configuration and cable routing during the initial steps of wire harness manufacturing. Based on the CAD information of the wire harness, the proposed framework generates trajectories in real-time to complete the initial manufacturing tasks, dividing automatically the whole job between both robots. The presented approach has been validated in a production environment using different wire harness references, obtaining promising results and metrics. Full article

(This article belongs to the Special Issue Advanced Grasping and Motion Control Solutions)

► Show Figures

Figure 1

29 pages, 1668 KiB

Open AccessArticle

Inverse Kinematics of an Anthropomorphic 6R Robot Manipulator Based on a Simple Geometric Approach for Embedded Systems

by Michael Anschober, Raimund Edlinger, Roman Froschauer and Andreas Nüchter

Robotics 2023, 12(4), 101; https://doi.org/10.3390/robotics12040101 - 12 Jul 2023

Cited by 1 | Viewed by 3060

Abstract

This manuscript presents an efficient algorithm for solving the inverse kinematics problem of a 6R robot manipulator to be deployed on embedded control hardware. The proposed method utilizes the geometric relationship between the end-effector and the base of the manipulator, resulting in a [...] Read more.

This manuscript presents an efficient algorithm for solving the inverse kinematics problem of a 6R robot manipulator to be deployed on embedded control hardware. The proposed method utilizes the geometric relationship between the end-effector and the base of the manipulator, resulting in a computationally efficient solution. The approach aims to minimize computational complexity and memory consumption while maintaining the accuracy and real-time performance demonstrated by simulations and verified by experimental results on an embedded system. Furthermore, the manipulator is analyzed in terms of singularities, limits, the workspace, and general solvability. Due to the simplicity of the algorithm, a platform-independent implementation is possible. As a result, the average calculation time is reduced by a factor of five to eight and the average error is decreased by a factor of fifty compared to a powerful analytical solver. Full article

(This article belongs to the Special Issue Advanced Grasping and Motion Control Solutions)

► Show Figures

Figure 1

19 pages, 7235 KiB

Open AccessArticle

Simulated and Real Robotic Reach, Grasp, and Pick-and-Place Using Combined Reinforcement Learning and Traditional Controls

by Andrew Lobbezoo and Hyock-Ju Kwon

Robotics 2023, 12(1), 12; https://doi.org/10.3390/robotics12010012 - 16 Jan 2023

Cited by 7 | Viewed by 4588

Abstract

The majority of robots in factories today are operated with conventional control strategies that require individual programming on a task-by-task basis, with no margin for error. As an alternative to the rudimentary operation planning and task-programming techniques, machine learning has shown significant promise [...] Read more.

The majority of robots in factories today are operated with conventional control strategies that require individual programming on a task-by-task basis, with no margin for error. As an alternative to the rudimentary operation planning and task-programming techniques, machine learning has shown significant promise for higher-level task planning, with the development of reinforcement learning (RL)-based control strategies. This paper reviews the implementation of combined traditional and RL control for simulated and real environments to validate the RL approach for standard industrial tasks such as reach, grasp, and pick-and-place. The goal of this research is to bring intelligence to robotic control so that robotic operations can be completed without precisely defining the environment, constraints, and the action plan. The results from this approach provide optimistic preliminary data on the application of RL to real-world robotics. Full article

(This article belongs to the Special Issue Advanced Grasping and Motion Control Solutions)

► Show Figures

Figure 1

33 pages, 8756 KiB

Open AccessArticle

Three-Dimensional Printing of Cylindrical Nozzle Elements of Bernoulli Gripping Devices for Industrial Robots

by Roman Mykhailyshyn, František Duchoň, Mykhailo Mykhailyshyn and Ann Majewicz Fey

Robotics 2022, 11(6), 140; https://doi.org/10.3390/robotics11060140 - 03 Dec 2022

Cited by 4 | Viewed by 1790

Abstract

The application of additive technologies, namely, fused deposition modeling, is a new reality for prototyping gripping devices of industrial robots. However, during 3D printing of holes and nozzle elements, difficulties arise with reducing their diameter. Therefore, this article conducts a comprehensive study of [...] Read more.

The application of additive technologies, namely, fused deposition modeling, is a new reality for prototyping gripping devices of industrial robots. However, during 3D printing of holes and nozzle elements, difficulties arise with reducing their diameter. Therefore, this article conducts a comprehensive study of the Bernoulli gripping device prototype with a cylindrical nozzle, manufactured by fused deposition modeling 3D printing. The three main reasons for reducing the diameter of the gripper nozzle after printing were due to the poor-quality model, excessive extrusion of plastic in the middle of the arc printing path, and linear shrinkage of printing material after cooling. The proposed methodology consisted of determining the three coefficients that allowed the determination of the diameter of the designed nozzle. The use of air pressure distributions on the surface of the manipulation object, and lifting forces of gripping devices with different 3D printing layer heights were found. It was experimentally determined that as the height of the printing layer increased, the lifting force decreased. This was due to the formation of swirls due to the increased roughness of the grip surface. It was proven that as the height between the manipulation object and the grip increased, the effect of surface roughness on the lifting force decreased, resulting in an increase in the lifting force. Determination of the rational operating parameters of gripping devices manufactured by 3D printing from the point of view of maximum lifting force, were determined. Full article

(This article belongs to the Special Issue Advanced Grasping and Motion Control Solutions)

► Show Figures

Figure 1

11 pages, 20167 KiB

Open AccessArticle

Adaptive Pincer Grasping of Soft Pneumatic Grippers Based on Object Stiffness for Modellable and Controllable Grasping Quality

by Chaiwuth Sithiwichankit and Ratchatin Chanchareon

Robotics 2022, 11(6), 132; https://doi.org/10.3390/robotics11060132 - 21 Nov 2022

Cited by 2 | Viewed by 1812

Abstract

In this study, adaptive pincer grasping of soft pneumatic grippers (SPGs) is considered, and we propose how the performance of soft pneumatic actuators (SPAs) and the stiffness of grasped objects can be accounted for in modeling and control. The grasping kinetics was analyzed. [...] Read more.

In this study, adaptive pincer grasping of soft pneumatic grippers (SPGs) is considered, and we propose how the performance of soft pneumatic actuators (SPAs) and the stiffness of grasped objects can be accounted for in modeling and control. The grasping kinetics was analyzed. The connection between grasping quality and SPA performance is discussed. We also devised a subjective definition of grasping quality due to SPA performance. A modeling technique was established, which makes dominant factors of grasping quality due to the SPA performance predictable over the gripper input. Later, a control architecture was developed. This architecture demonstrates how the grasping is implemented. The modeling technique was used to forecast grasping quality due to the SPA performance and its factors. An experiment was conducted to obtain actual results. The predicted and actual results were correspondingly compared. The results show minute deviation, thereby validating the reliability of the grasping. This study clarifies the association between grasping quality and SPA performance and contributes an advancement toward modellable and controllable task-level variables, such as grasping quality, in SPG pincer grasping. Full article

(This article belongs to the Special Issue Advanced Grasping and Motion Control Solutions)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Advanced Grasping and Motion Control Solutions

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Related Special Issue

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI