Controlling Servo Motor Angle by Exploiting Kinect SDK

Foroughi, Farzin; Zong, Peng

doi:10.5120/20433-2764

Cited by 4 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to these conditions and the need for robots in strenuous circumstances, the recent past has seen tremendous research in mobile robots. The intention is to have such devices, which could automatically perform most tasks without human intervention [4]. All the advantages, which can be achieved with AMR usage, also come along with numerous challenges.…”

Section: Introductionmentioning

confidence: 99%

A CNN-Based System for Mobile Robot Navigation in Indoor Environments via Visual Localization with a Small Dataset

Foroughi

Chen

Wang

2021

WEVJ

Self Cite

View full text Add to dashboard Cite

Deep learning has made great advances in the field of image processing, which allows automotive devices to be more widely used in humans’ daily lives than ever before. Nowadays, the mobile robot navigation system is among the hottest topics that researchers are trying to develop by adopting deep learning methods. In this paper, we present a system that allows the mobile robot to localize and navigate autonomously in the accessible areas of an indoor environment. The proposed system exploits the Convolutional Neural Network (CNN) model’s advantage to extract data feature maps for image classification and visual localization, which attempts to precisely determine the location region of the mobile robot focusing on the topological maps of the real environment. The system attempts to precisely determine the location region of the mobile robot by integrating the CNN model and topological map of the robot workspace. A dataset with small numbers of images is acquired from the MYNT EYE camera. Furthermore, we introduce a new loss function to tackle the bounded generalization capability of the CNN model in small datasets. The proposed loss function not only considers the probability of the input data when it is allocated to its true class but also considers the probability of allocating the input data to other classes rather than its actual class. We investigate the capability of the proposed system by evaluating the empirical studies based on provided datasets. The results illustrate that the proposed system outperforms other state-of-the-art techniques in terms of accuracy and generalization capability.

show abstract

Section: Introductionmentioning

confidence: 99%

A CNN-Based System for Mobile Robot Navigation in Indoor Environments via Visual Localization with a Small Dataset

Foroughi

Chen

Wang

2021

WEVJ

Self Cite

View full text Add to dashboard Cite

show abstract

“…The hypothesis of this study, on the other hand, is to propose a different technique: casting parallel laser lines as a dynamic and automatic visual cuing system for PwP based on Kinect v2 and a set of servo motors suitable for indoor environments. As Kinect has been proven to be a reliable data feed source for controlling servo motors [22, 23], the Kinect camera was chosen for real-time depth data feed for this study. This paper also examines the possibility of using the Kinect v2 sensor for such purposes in terms of accuracy and response time.…”

Section: Introductionmentioning

confidence: 99%

Using Kinect v2 to Control a Laser Visual Cue System to Improve the Mobility during Freezing of Gait in Parkinson’s Disease

Amini

Banitsas

2019

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Different auditory and visual cues have been proven to be very effective in improving the mobility of people with Parkinson’s (PwP). Nonetheless, many of the available methods require user intervention and so on to activate the cues. Moreover, once activated, these systems would provide cues continuously regardless of the patient’s needs. This research proposes a new indoor method for casting dynamic/automatic visual cues for PwP based on their head direction and location in a room. The proposed system controls the behavior of a set of pan/tilt servo motors and laser pointers, based on the real-time skeletal information acquired from a Kinect v2 sensor. This produces an automatically adjusting set of laser lines that can always be in front of the patient as a guideline for where the next footstep would be placed. A user interface was also created that enables users to control and adjust the settings based on the preferences. The aim of this research was to provide PwP with an unobtrusive/automatic indoor system for improving their mobility during a Freezing of gait (FOG) incident. The results showed the possibility of employing such system, which does not rely on the subject’s input nor does it introduce any additional complexities to operate.

show abstract