Delowar Hossain

Verified

Delowar verified their affiliation via an institutional email.

Learn more

Verified

Delowar verified their affiliation via an institutional email.

Learn more

• Doctor of Engineering
• PostDoc Position at University of Calgary

Purpose - Development of autonomous robot manipulator for human-robot assembly tasks is a key component to reach high effectiveness. In assembly tasks, the robot real time object recognition is crucial. In addition, the need for simple and safe teaching techniques need to be considered, because: 1) Small size robot manipulators presence in everyday...

Object recognition is the key problem of automatic robot grasping tasks. In this paper, we propose a Deep Belief Neural Network (DBNN) method for object recognition. After object recognition, the real time robot trajectory is generated. The robot grasps the objects and places them in a predefined destination. Our deep learning model extracts suffic...

We present a vision guided real-time approach to robot object recognition and grasping based on Deep Belief Neural Network (DBNN). In our method, the captured camera image is used as input of the DBNN. The DBNN extracts the object features in the intermediate layers. Our system integrates computer vision to capture the features and recognize the ob...

The need for simple and safe teaching methods for robot manipulators need to be considered because: 1) Small size robots presence in everyday life environments is increasing requiring non-experts operators to teach the robot; 2) In small applications, the operator has to teach several different motions in a short time. In this paper, we evaluate th...

The main challenge of any mobile robot is to detect and avoid obstacles and potholes. This paper presents the development and implementation of a novel mobile robot. An Arduino Uno is used as the processing unit of the robot. A Sharp distance measurement sensor and Ultrasonic sensors are used for taking inputs from the environment. The robot trains...

Background Robots can generate rich kinematic datasets that have the potential to provide far more insight into impairments than standard clinical ordinal scales. Determining how to define the presence or absence of impairment in individuals using kinematic data, however, can be challenging. Machine learning techniques offer a potential solution to...

Background Proprioception is commonly impaired after stroke. Robotic tools precisely measure multiple attributes of position sense and create large datasets. Previously, we quantified individual performance based on single measured robotic parameters and an overall task score in an arm position matching (APM) task. In the present manuscript, we use...

Wake-word detection is an indispensable technology for preventing virtual voice agents from being unintentionally triggered. Although various neural networks were proposed for wake-word detection, less attention has been paid to efficient corpus design, which we address in this study. For this purpose, we collected speech data via a crowdsourcing p...

Visual localization of mobile robot in indoor environments has difficulties due to the similarities of locations in the environment. This paper presents a robot localization method based on multi-feature indexing. The speeded up robust features (SURF) and histogram of oriented gradients (HOG) are combined to form the HOG-SURF feature descriptor. K-...

Robot localization is an important task for mobile robot navigation. There are many methods focused on this issue. Some methods are implemented in indoor and outdoor environments. However, robot localization in textureless environments is still a challenging task. This is because in these environments, the scene appears the same in almost every pos...

This paper presents a low-cost myoelectric robotic hand which was developed by a 3D printer. The purpose of the developed system is to be used as a low-cost prosthesis. It is controlled by electromyogram (EMG) signals from flexor and extensor muscles in the lower arm. Each part of the robotic hand is created using the 3D printer. Arduino MEGA micro...

Outdoor mobile robot applications generally implement Global Positioning Systems (GPS) for localization tasks. However, GPS accuracy in outdoor localization has less accuracy in different environmental conditions. This paper presents two outdoor localization methods based on deep learning and landmark detection. The first localization method is bas...

This paper proposes navigation algorithms for mobile robot through the odometry approach. The proposed algorithms include the odometry-based algorithm which uses only odometry calculated from robot motions, and the visual-assisted algorithm that applies visual data to assist in the navigation. The visual-assisted algorithm takes the convolutional n...

Polishing is a time-consuming and tedious job that needs a considerable amount of high-precision skills. Since it requires human skills, it is difficult to perform with a robot. In this paper, we propose an automatic polishing system. It is composed of two subsystems, a six-axis polishing robot manipulator and a polishing grinder. The proposed syst...

Vision based robot navigation and localization is still an issue in roboticists community. In this paper, we propose a human like robot navigation in indoor environments using controlled by neural networks. The neural networks are trained to map the captured depth image to the robot action. Initially, the user controls the robot to navigate in the...

Many objects in household and industrial environments are commonly found partially occluded. In this paper, we address the problem of recognizing objects for use in partially occluded object recognition. To enable the use of more expensive features and classifiers, a region proposal network (RPN) which shares full-image convolutional feature with d...

Deep Learning (DL) is currently very popular because of its similarity to the hierarchical architecture of human brain with multiple levels of abstraction. DL has many parameters that influence the network performance. In this paper, we introduce a multiobjective evolutionary algorithm (MOEA) to optimize the DBNN parameters subject to the error rat...

This paper presents a method for outdoor localization using deep learning-based landmark detection. The proposed localization method relies on the Faster Regional Convolutional Neural Network (Faster R-CNN) landmark detector and the feedforward neural network (FFNN) trained with GPS data from geotags in images, retrieve location coordinates and com...

This paper addresses the problem of recognizing possible objects for use in partially occluded object recognition. To enable the use of more expensive features and classifiers and thereby progress beyond the state-of-the-art, a region proposal network (RPN) which shares full-image convolutional feature with detector network is needed. We aim to imp...

The performance of deep learning (DL) networks has been increased by elaborating the network structures. However, the DL netowrks have many parameters, which have a lot of influence on the performance of the network. We propose a genetic algorithm (GA) based deep belief neural network (DBNN) method for robot object recognition and grasping purpose....

Robot object recognition and grasping is an important research area in robotics. Recently, deep learning is gaining popularity as a powerful mechanism for object recognition. Deep learning has very complicated configurations including network structures and several parameters, such as the number of hidden units and the number of epochs, which influ...

Intelligent mobile robot navigation in indoor environments is still a challenge. In this paper, we propose a method in which the wheelchair robot imitates human like navigation by interacting with the surrounding environments. Two types of sensor data are used to train neural networks, which are later used to control the robot to reach the goal loc...

Abstract—This paper concerns with the problem of deep learning parameters tuning using a genetic algorithm (GA) in order to improve the performance of deep learning (DL) method. We present a GA based DL method for robot object recognition and grasping. GA is used to optimize the DL parameters in learning procedure in term of the fitness function th...

Individual identification at a distance using gait features has newly gained growing interest from biometrics researchers. Most of the researchers have been shown that different covariate factors can affect different parts of the human body. In this paper, we propose a new approach that minimizes these difficulties, especially for carrying objects...