Development and implementation of a vision system for decision making in the movements control of humanoid robots

2018 ◽  
Author(s):  
K. Valladares-Yanez ◽  
A.E. Monroy-Meza ◽  
R.A. Suarez-Rivera ◽  
J. Rodriguez-Resendiz ◽  
G.I. Perez-Soto ◽  
...  
Keyword(s):  
Decision Making ◽  
Vision System ◽  
Humanoid Robots

scholarly journals Stereo Camera Head-Eye Calibration Based on Minimum Variance Approach Using Surface Normal Vectors

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3706 ◽  
Author(s):  
Joong-Jae Lee ◽  
Mun-Ho Jeong
Keyword(s):  
Vision System ◽  
Real Data ◽  
Humanoid Robots ◽  
Calibration Method ◽  
Minimum Variance ◽  
Kinematic Data ◽  
Stereo Camera ◽  
Surface Normal ◽  
Normal Vectors ◽  
Variance Approach

This paper presents a stereo camera-based head-eye calibration method that aims to find the globally optimal transformation between a robot’s head and its eye. This method is highly intuitive and simple, so it can be used in a vision system for humanoid robots without any complex procedures. To achieve this, we introduce an extended minimum variance approach for head-eye calibration using surface normal vectors instead of 3D point sets. The presented method considers both positional and orientational error variances between visual measurements and kinematic data in head-eye calibration. Experiments using both synthetic and real data show the accuracy and efficiency of the proposed method.

The Development of Supervised Motion Learning and Vision System for Humanoid Robot

2019 ◽  
Vol 886 ◽  
pp. 188-193 ◽  
Author(s):  
Ssu Ting Lin ◽  
Jun Hu ◽  
Chia Hung Shih ◽  
Chiou Jye Huang ◽  
Ping Huan Kuo
Keyword(s):  
Humanoid Robot ◽  
Physical Mechanism ◽  
Learning Algorithm ◽  
Vision System ◽  
Humanoid Robots ◽  
Learning System ◽  
Automatic Learning ◽  
Swarm Optimization ◽  
Motion Learning ◽  
Important Research Topic

With the development of the concept of Industry 4.0, research relating to robots is being paid more and more attention, among which the humanoid robot is a very important research topic. The humanoid robot is a robot with a bipedal mechanism. Due to the physical mechanism, humanoid robots can maneuver more easily in complex terrains, such as going up and down the stairs. However, humanoid robots often fall from imbalance. Whether or not the robot can stand up on its own after a fall is a key research issue. However, the often used method of hand tuning to allow robots to stand on its own is very inefficient. In order to solve the above problems, this paper proposes an automatic learning system based on Particle Swarm Optimization (PSO). This system allows the robot to learn how to achieve the motion of rebalancing after a fall. To allow the robot to have the capability of object recognition, this paper also applies the Convolutional Neural Network (CNN) to let the robot perform image recognition and successfully distinguish between 10 types of objects. The effectiveness and feasibility of the motion learning algorithm and the CNN based image classification for vision system proposed in this paper has been confirmed in the experimental results.

SPATIOTEMPORAL CONTEXT INTEGRATION IN ROBOT VISION

2010 ◽  
Vol 07 (03) ◽  
pp. 357-377 ◽  
Author(s):  
RODRIGO PALMA-AMESTOY ◽  
JAVIER RUIZ-DEL-SOLAR ◽  
JOSÉ MIGUEL YÁÑEZ ◽  
PABLO GUERRERO
Keyword(s):  
Vision System ◽  
Spatial Coherence ◽  
Robot Vision ◽  
Active Vision ◽  
Humanoid Robots ◽  
Dynamic Environments ◽  
High Performing ◽  
Processing Power ◽  
Context Integration ◽  
Computational Resources

Robust vision in dynamic environments using limited processing power is one of the main challenges in robot vision. This is especially true in the case of biped humanoids that use low-end computers. Techniques such as active vision, context-based vision, and multi-resolution are currently in use to deal with these highly demanding requirements. Thus, having as main motivation the development of robust and high performing robot vision systems, which can operate in dynamic environments, with limited computational resources, we propose a spatiotemporal context integration framework that improves the perceptual capabilities of a given robot vision system. Furthermore, we try to link the vision, tracking, and self-localization problems using a context filter to improve the performance of all these parts together more than to improve them separately. This framework computes: (i) an estimation of the poses of visible and nonvisible objects using Kalman filters; (ii) the spatial coherence of each current detection with all other simultaneous detections and with all tracked objects; and (iii) the spatial coherence of each tracked object with all current detections. Using a Bayesian approach, we calculate the a-posteriori probabilities for each detected and tracked object, which is used in a filtering stage. We choose as a first application of this framework, the detection of static objects in the RoboCup Standard Platform League domain, where Nao humanoid robots are employed. The proposed system is validated in simulations and using real video sequences. In noisy environments, the system is able to decrease largely the number of false detections and to improve effectively the self-localization of the robot.

An Advanced Active Vision System with Multimodal Visual Odometry Perception for Humanoid Robots

2017 ◽  
Vol 14 (03) ◽  
pp. 1750006
Author(s):  
Xin Wang ◽  
Pieter Jonker
Keyword(s):  
Eye Movements ◽  
Vision System ◽  
Low Cost ◽  
Active Vision ◽  
Human Perception ◽  
Personal Space ◽  
Visual Odometry ◽  
Humanoid Robots ◽  
Industrial Applications ◽  
Human Vision

Using active vision to perceive surroundings instead of just passively receiving information, humans develop the ability to explore unknown environments. Humanoid robot active vision research has already half a century history. It covers comprehensive research areas and plenty of studies have been done. Nowadays, the new trend is to use a stereo setup or a Kinect with neck movements to realize active vision. However, human perception is a combination of eye and neck movements. This paper presents an advanced active vision system that works in a similar way as human vision. The main contributions are: a design of a set of controllers that mimic eye and neck movements, including saccade eye movements, pursuit eye movements, vestibulo-ocular reflex eye movements and vergence eye movements; an adaptive selection mechanism based on properties of objects to automatically choose an optimal tracking algorithm; a novel Multimodal Visual Odometry Perception method that combines stereopsis and convergence to enable robots to perform both precise action in action space and scene exploration in personal space. Experimental results prove the effectiveness and robustness of our system. Besides, the system works in real-time constraints with low-cost cameras and motors, providing an affordable solution for industrial applications.

Reconstruction and Analysis of Human Walking Patterns Using a Computer 3D Vision System

2012 ◽  
Author(s):  
Juan C. Arellano-González ◽  
Hugo I. Medellín-Castillo ◽  
J. Antonio Cárdenas-Galindo
Keyword(s):  
Young Adults ◽  
Biomedical Engineering ◽  
Vision System ◽  
Research Work ◽  
Humanoid Robots ◽  
Research Area ◽  
Medical Rehabilitation ◽  
Human Walking ◽  
Accurate Information ◽  
3D Vision

Human walking analysis is an important research area of biomedical engineering since it provides accurate information for medical rehabilitation procedures and design of rehabilitation equipment, medical diagnosis and orthopedics, pathological and aging evaluation, design of human prosthesis, and design of humanoid robots. In some applications, such as the design of prosthesis and rehabilitation systems in biomedical engineering, and equipment design and performance analysis in sports engineering, human walking reconstruction under several conditions is required in order to optimize the design. Human walking process is smooth and efficient but it varies from one person to another depending on age, height, gender, weight, health condition, and walking conditions. Most of the research work in the literature has been focused on the analysis of gait patterns of healthy and unhealthy people under normal walking conditions, and they use 2D reconstruction of human walking trajectories. The aim of this paper is to reconstruct and analyse human walking patterns of normal young adults under different gait conditions. A computer vision system to reconstruct 3D human walking trajectories is developed and presented in this paper. Several experiments with young adults walking under several conditions such as carrying a front load, carrying a lateral load, ascending, etc., are conducted. The results of these experiments have shown that human walking patterns vary according to the walking condition and therefore these variations should be considered in the design of prosthesis or rehabilitation systems.

scholarly journals Performance Analysis of Target Information Recognition System for Agricultural Robots

2021 ◽  
Vol 12 (2) ◽  
pp. 49-60
Author(s):  
Yun Ji ◽  
Rajeev Kumar ◽  
Daljeet Singh ◽  
Maninder Singh
Keyword(s):  
Decision Making ◽  
Production Efficiency ◽  
Vision System ◽  
Recognition Rate ◽  
Robot Vision ◽  
Recognition System ◽  
Economic Benefits ◽  
Prototype System ◽  
Target Information ◽  
Information Recognition

In this paper, an agricultural robot vision system is proposed for two typical environments—farmland and orchard—combined with weeding between crops. The system includes orchard production monitoring and prediction tasks, the target information recognition approach, and visual servo decision making. The results obtained from the proposed system show that using the region combination features of image 2D histogram as the decision-making basis, the accurate and rapid indirect identification and positioning of crop seedlings can be accomplished while skipping the complex process of accurately identifying crops and weeds. The algorithm performs reasonably good as the time of target recognition in the prototype system is found to be less than 16 ms, and the average accurate recognition rate of 97.43% is achieved. The benefits of the proposed system are the continuous improvement of the quality of agricultural products, the rise of production efficiency, and the increase of economic benefits.

scholarly journals Social Decision Making with Humans and Robots: Trust and Approachability Mediate Economic Decision Making

2018 ◽  
Author(s):  
Stephanie Tulk ◽  
Eva Wiese
Keyword(s):  
Decision Making ◽  
Ultimatum Game ◽  
Humanoid Robots ◽  
Trust Game ◽  
Social Decision ◽  
Economic Decisions ◽  
Economic Decision Making ◽  
Human Likeness ◽  
Social Decision Making

As humanoid robots become more advanced and commonplace, the average user may find themselves in the position of wondering if their robotic companion truly possesses a mind. It is important for scientists and designers to consider how this will likely affect our interactions with social robots. The current paper explores how social decision making with humanoid robots changes as the degree of their human-likeness changes. For that purpose, we created a spectrum of human-like agents via morphing that ranged from very robot-like to very human-like in physical appearance (in increments of 20%) and measured how this change in physical humanness affected decision-making in two economic games: Ultimatum Game (Experiment 1) and Trust Game (Experiment 2). We expected increases in human-like appearance to lead to a higher rate of punishment for unfair offers in the Ultimatum Game, and to a higher rate of trust in the Trust Game. While physical humanness did not have an impact on economic decisions in either of the experiments, follow-up analyses showed that both subjective ratings of trust and agent approachability mediated the effect of agent appearance on decision-making in both experiments. Possible consequences of these findings for human- robot interactions are discussed.

A Study on Fuzzy Control of Humanoid Soccer Robot EFuRIO for Vision Control System and Walking Movement

2012 ◽  
Vol 16 (3) ◽  
pp. 444-452
Author(s):  
Indra Adji Sulistijono ◽  
◽  
Son Kuswadi ◽  
One Setiaji ◽  
Inzar Salfikar ◽  
...  
Keyword(s):  
Fuzzy Logic Control ◽  
Humanoid Robot ◽  
Vision System ◽  
Humanoid Robots ◽  
Soccer Robot ◽  
Balance Condition ◽  
Logic Control ◽  
Control Scheme ◽  
Vision Control ◽  
The Stability

Instability is one of the major defects in humanoid robots. Recently, various methods on the stability and reliability of humanoid robots have been studied actively. We propose a new fuzzy-logic control scheme for vision systems that would enable a robot to search for and to kick a ball towards an opponent goal. In this paper, a stabilization algorithm is proposed using the balance condition of the robot, which is measured using accelerometer sensors during standing and walking, and turning movement are estimated from these data. From this information the robot selects the appropriate motion pattern effectively. In order to generate the appropriate reaction in various body of robot situations, a fuzzy algorithm is applied in finding the appropriate angle of the joint from the vision system. The performance of the proposed algorithm is verified by searching for a ball, walking, turning tap and ball kicking movement experiments using an 18-DOF humanoid robot, called EFuRIO.

DEVELOPMENT OF A HIGH-PERFORMANCE HUMANOID SOCCER ROBOT

2008 ◽  
Vol 05 (03) ◽  
pp. 353-373 ◽  
Author(s):  
REO MATSUMURA ◽  
HIROSHI ISHIGURO
Keyword(s):  
Decision Making ◽  
Data Processing ◽  
High Performance ◽  
Humanoid Robot ◽  
Developmental Process ◽  
Humanoid Robots ◽  
Soccer Robot ◽  
World Cup ◽  
Robot Soccer ◽  
Sensory Data

The RoboCup, which is a worldwide robot soccer competition, has set an ambitious goal for itself: to have a humanoid robot team win against human teams in World Cup Soccer by 2050. In order to achieve this goal, the robots require highly sophisticated sensory-data processing and decision-making functions. The development of robots for the RoboCup Humanoid League also has significant meaning for the development of robotics. However, this development is not easy and there are few papers covering it and its design policy. This paper reports the design policy for humanoids developed by Team Osaka, whose robots have been selected as the best humanoid robots four times in the last four years. In addition to the design policy, this paper also reports on the developmental process and comparisons among humanoid versions developed by Team Osaka. We believe that this paper will offer much information to other researchers who are developing humanoids for the RoboCup.

Sign in / Sign up

Export Citation Format

Share Document