Direct Perception and Action Decision for Unknown Object Grasping

2017 ◽  
Vol 7 (1) ◽  
pp. 38-51
Author(s):  
Hiroyuki Masuta ◽  
Tatsuo Motoyoshi ◽  
Kei Sawai ◽  
Ken'ichi Koyanagi ◽  
Toru Oshima ◽  
...  
Keyword(s):  
Relative Position ◽  
Perception And Action ◽  
Fuzzy Inference ◽  
Perceptual System ◽  
Direct Perception ◽  
Physical Parameters ◽  
Robot Arm ◽  
Depth Sensor ◽  
Unknown Object ◽  
Action Decision

This paper discusses the direct perception of an unknown object and the action decision to grasp an unknown object using depth sensor for social robots. Conventional methods estimate the accurate physical parameters when a robot wants to grasp an unknown object. Therefore, we propose a perceptual system based on an invariant concept in ecological psychology, which perceives the information relevant to the action of the robot. Firstly, we proposed the plane detection based approach for perceiving an unknown object. In this paper, we propose the sensation of grasping which is expressed by using inertia tensor, and applied with fuzzy inference using the relation between principle moment of inertia. The sensation of grasping encourages the decision for the grasping action directly without inferring from physical value such as size, posture and shape. As experimental results, we show that the sensation of grasping expresses the relative position and posture between the robot and the object, and the embodiment of the robot arm by one parameter. And, we verify the validity of the action decision from the sensation of grasping.

Direct Perception and Action Decision for Unknown Object Grasping

2019 ◽  
pp. 1372-1387
Author(s):  
Hiroyuki Masuta ◽  
Tatsuo Motoyoshi ◽  
Kei Sawai ◽  
Ken'ichi Koyanagi ◽  
Toru Oshima ◽  
...  
Keyword(s):  
Relative Position ◽  
Fuzzy Inference ◽  
Perceptual System ◽  
Moment Of Inertia ◽  
Direct Perception ◽  
Physical Parameters ◽  
Robot Arm ◽  
Depth Sensor ◽  
Unknown Object ◽  
Action Decision

This paper discusses the direct perception of an unknown object and the action decision to grasp an unknown object using depth sensor for social robots. Conventional methods estimate the accurate physical parameters when a robot wants to grasp an unknown object. Therefore, we propose a perceptual system based on an invariant concept in ecological psychology, which perceives the information relevant to the action of the robot. Firstly, we proposed the plane detection based approach for perceiving an unknown object. In this paper, we propose the sensation of grasping which is expressed by using inertia tensor, and applied with fuzzy inference using the relation between principle moment of inertia. The sensation of grasping encourages the decision for the grasping action directly without inferring from physical value such as size, posture and shape. As experimental results, we show that the sensation of grasping expresses the relative position and posture between the robot and the object, and the embodiment of the robot arm by one parameter. And, we verify the validity of the action decision from the sensation of grasping.

scholarly journals Algorithm for recognition of details in the machine vision systems at automation of assembly processes

2018 ◽  
Vol 224 ◽  
pp. 01088 ◽  
Author(s):  
Yaroslav Kulkov ◽  
Arkady Zhiznyakov ◽  
Denis Privezentsev
Keyword(s):  
Computer Vision ◽  
Experimental Research ◽  
Mean Square ◽  
Robot Arm ◽  
Vision Systems ◽  
Binary Images ◽  
Image Contour ◽  
Computer Vision Systems ◽  
Assembly Operations ◽  
Unknown Object

The aim is an experimental research on the flat objects recognition using dimensionless marks of the contours of their binary images and determining the possibility of applying this method in computer vision systems of assembly robots. The main problem with the automation of assembly operations is the recognition of parts for the subsequent picking up of the robot arm. The basis for the formation of attribute vectors is the characteristics of the image contour. Recognition of a class of an unknown object consists in receipt of its contour, calculation of primary parameters and forming of a vector of dimensionless marks. Further mean square deviations of its vector of dimensionless marks from all reference are calculated. The minimum value of a deviation will specify probable belonging to the corresponding class.

New continuum surgical robot based on hybrid concentric tube-tendon driven mechanism

2021 ◽  
pp. 095440622110424
Author(s):  
Mohammed Abdel-Nasser ◽  
Omar Salah
Keyword(s):  
Inverse Kinematics ◽  
High Performance ◽  
Analytical Study ◽  
Fuzzy Inference ◽  
Closed Form Solution ◽  
Form Solution ◽  
Robot Arm ◽  
Inference System ◽  
Neuro Fuzzy ◽  
Intelligent Approach

Robotics technology is used widely in minimally invasive surgery (MIS) which provides high performance and accuracy. The most famous robot arm mechanisms, which are used in MIS, are tendon-driven mechanism (TDM), and concentric tube mechanism (CTM). Unfortunately, these mechanisms until now have some limitations, i.e. making friction with the tissue during extracting and retracting and strain limits, for TDM and CTM respectively. A new hybrid concentric tube-tendon driven mechanism (HCTDM) is proposed to overcome these limitations. HCTDM enables the end-effector to get close to and get away from the surgical area during the operation without harming the tissue and with more flexibility. In addition to that, the workspace increases as a result of this combination, too. This benefit serves MIS, especially endoscopic surgeries (ESs). We did an analytical study of this idea and got the forward kinematics. In the inverse kinematics, an intelligent approach which is called an adaptive neuro-fuzzy inference system (ANFIS) is used because the closed-form solution is more complicated for such these mechanisms. Finally, HCTDM is analyzed and evaluated by using a computer simulation. The simulation results show that the workspace becomes wider and has more dexterity than use TDM or CTM individually. Furthermore, various trajectories are used to test the mechanism and the kinematic analysis, which show the mechanism can follow and track the trajectories with maximum mean error 1.279, 0.7027, and [Formula: see text] for X, Y, and Z axes respectively.

scholarly journals Stereo Vision-Based Object Recognition and Manipulation by Regions with Convolutional Neural Network

Electronics ◽  
2020 ◽  
Vol 9 (2) ◽  
pp. 210 ◽  
Author(s):  
Yi-Chun Du ◽  
Muslikhin Muslikhin ◽  
Tsung-Han Hsieh ◽  
Ming-Shyan Wang
Keyword(s):  
Neural Network ◽  
Object Recognition ◽  
Convolutional Neural Network ◽  
Stereo Vision ◽  
Fuzzy Inference ◽  
Target Object ◽  
Robot Arm ◽  
Segmentation Method ◽  
Inference System ◽  
Six Degree Of Freedom

This paper develops a hybrid algorithm of adaptive network-based fuzzy inference system (ANFIS) and regions with convolutional neural network (R-CNN) for stereo vision-based object recognition and manipulation. The stereo camera at an eye-to-hand configuration firstly captures the image of the target object. Then, the shape, features, and centroid of the object are estimated. Similar pixels are segmented by the image segmentation method, and similar regions are merged through selective search. The eye-to-hand calibration is based on ANFIS to reduce computing burden. A six-degree-of-freedom (6-DOF) robot arm with a gripper will conduct experiments to demonstrate the effectiveness of the proposed system.

Direct Perception of Easily Visible Information for Unknown Object Grasping

2016 ◽  
pp. 78-89 ◽  
Author(s):  
Hiroyuki Masuta ◽  
Tatsuo Motoyoshi ◽  
Ken’ichi Koyanagi ◽  
Toru Oshima ◽  
Hun-ok Lim
Keyword(s):  
Direct Perception ◽  
Unknown Object

How specific and common is common coding?

2001 ◽  
Vol 24 (5) ◽  
pp. 903-905 ◽  
Author(s):  
Andries F. Sanders
Keyword(s):  
Information Processing ◽  
Cognitive Skills ◽  
Perception And Action ◽  
Direct Perception ◽  
Human Information Processing ◽  
Common Coding ◽  
Event Code ◽  
Target Article ◽  
The Common ◽  
Action Coupling

This commentary addresses three points. First, it is argued that the common coding principles, as developed in the target article, may supplement rather than replace stage views of human information processing. Second, the issue of the properties of an event code is briefly discussed. It is concluded that much remains to be specified so as to allow critical tests. Finally, the question of the limits of common coding is raised. It may be particularly relevant to direct perception and action coupling but less useful for the analysis of cognitive skills.

scholarly journals Pattern Recognition & Image Understanding based on Fuzzy Technology

1997 ◽  
Vol 1 (1) ◽  
pp. 71-78 ◽  
Author(s):  
Kaoru Hirota ◽  
◽  
Yoshinori Arai ◽  
Yukiko Nakagawa ◽  
Keyword(s):  
Pattern Recognition ◽  
Time Use ◽  
Additional Data ◽  
Fuzzy Inference ◽  
Vision System ◽  
Image Understanding ◽  
Robot Arm ◽  
Remote Sensing Images ◽  
Dynamic Image ◽  
Hierarchical Pattern

Four image recognition and understanding techniques based on fuzzy technology developed by the authors group have been surveyed. First topics is a fuzzy clustering with additional data applied to the remote sensing images. It is modified version of the well known FCM. A robot arm and vision system on assembling line is presented using fuzzy discriminant tree for a real time use. The repetition method is introduced into the construction of discriminant tree. Third is the pattern recognition for a models of cars which is applied a fuzzy hierarchical pattern recognition based on fixation feedback. Finally, a fuzzy dynamic image understanding system is presented using fuzzy knowledge base and fuzzy inference method to understand dynamic image understanding on general roads in Japan. These techniques are mentioned the algorithms, and some of them are with experimental results.

scholarly journals Ecological approach to perception and action: Fundaments for motor behavior

2007 ◽  
Vol 2 (1) ◽  
pp. 1-10 ◽  
Author(s):  
Sérgio T. Fonseca ◽  
Christina D. C. M. Faria ◽  
Juliana M. Ocarino ◽  
Marisa C. Mancini
Keyword(s):  
Perception And Action ◽  
Motor Behavior ◽  
Direct Perception ◽  
Ecological Approach ◽  
Decision Making Process ◽  
Direct Realism ◽  
The Core ◽  
Core Concepts ◽  
Philosophical Standpoint ◽  
Human Motor

The objective of the present study is to introduce the philosophical position and the core concepts of the Ecological Approach to Perception and Action, emphasizing its principles and its uniqueness in relation to other theories related to motor behavior. The Ecological Approach, as opposed to other approaches, assumes the direct realism as its philosophical standpoint. Thus, the Ecological Approach to Perception and Action proposes the concepts of specificity, direct perception and affordance. By assuming the direct realism, the Ecological Approach to Perception and Action commits to the mutuality animal  environment and perception and action, and proposes that the dualism, commonly found in other theories, does not contribute to the understanding of human motor behavior. The choice of a given theory, during the process of scientific investigation, implies in a commitment to the philosophical views and to the principles and assumptions in which it is based. The knowledge about the core concepts of the Ecological Approach may support the decision making process about accepting or rejecting the ideas advanced by James Gibson and, consequently, direct the use of this theory to the development of investigations on perception and action.

Sign in / Sign up

Export Citation Format

Share Document