International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395 -0056
Volume: 04 Issue: 03 | March -2017
p-ISSN: 2395-0072
www.irjet.net
Design of Robotic Arm based on Hand Gesture Control System using Wireless Sensor Networks R.Raja Prabhu1, R.Sreevidya2 1Assistant
Professor, Dept of Electrical and Electronics Engineering, Imayam College of Engineering, Trichy, Tamilnadu, India, rajaprabhuae@gmail.com 2Assistant Professor, Dept of Electrical and Electronics Engineering, TRP Engineering College, Trichy, Tamilnadu, India, sreevidya202@gmail.com
---------------------------------------------------------------------***--------------------------------------------------------------------2. RELATED WORK
Abstract - In many industries wireless operations are
necessary especially in dangerous or hazards areas. In some of the industries it is necessary to handle few jobs with very high temperature which is not possible by human hand in such cases wireless operations are more efficient. This paper focuses on design of hand gesture controlled robotic arm using microcontroller with the help of X-bee and wireless sensor networks. Simulations are being carried out and the hardware prototype was successfully implemented with the above requirements. Key Words: Robotic manipulator, hand gesture controlled arm, flex sensor, X-bee, Accelerometer.
1. INTRODUCTION In today’s life automation plays very important role. Robotic arm is called as robot manipulator which can perform various functions as human arm performs. Many industries use a robot for various functions where important part of any robot is Robotic arm or called as robot manipulator should be controlled precisely depending upon application. In industry or any application robot manipulator can be used for applications like welding, trimming; picking etc. advantage of such robotic arm is it can work in hazards area, which cannot be accessed by human. Many parameters of robot are designed according to requirement. There are different ways to control robotic arm like Voice Controlled, Keypad Control, Gesture Control, etc. Implemented system consists of transmitter & receiver. Transmitter is nothing but human hand with flex sensors & receiver is robot manipulator. Motion of transmitter is wirelessly transmitted to receiver through X-bee module. Robotic arm which is receiver is nothing but a mechanical system formed by different joints and end and effectors i.e. gripper movements of these fingers or gripper can be carried out using stepper motor or servo motor when user carry out motion of hand for any application at transmitter side same movement is copied by receiver as on transmitter there are flex sensors mounted on glove at transmitter which change its resistance depending on movement of user.
© 2017, IRJET
|
Impact Factor value: 5.181
|
There has been many research works in the field of Hand Gesture based Human Computer Interaction following different algorithms to develop a fast and reliable procedure for gesture recognition. In Paper [1] – [6] by Francisco Arce, Jose Mario Garcia Valdez a three axis accelerometer has been used to read different types of Hand gestures. In Paper [7] – [11] by AnalaPandit, DhairyaDand, Sisil Mehta, ShashankSabesan, AnkitDaftery used a combination of accelerometer and gyroscope and the reading are taken in to for analyzing the gesture. Here accelerometer is dedicated for collecting translational dynamic and static change in positional vector of hand and infer it to the movement of mouse whereas gyroscope has been used for rotation of virtual object. There are many papers where gestures are being analyzed using colour gloves [12] – [15]. A data glove is a type of glove that contains fiber optics sensor or flex sensors embedded in it to recognize the finger movements. Hand gesture recognition using image processing algorithms many times involve use of colour gloves. By tracking this colour glove different hand gestures can be interpreted as described by Luigi Lamberti1 and Francesco Camastra in their paper [16] – [18]. Here they have modelled a colour classifier performed by learning vector Quantization. In Paper [19] by J.S. Kim, C.S. Lee, K.J. Song, B. Min, Z. Bien, a pattern recognizing algorithm has been used to study the features of hand. There are many Papers where training of hands using a large database of near about 5000-10000 positive and negative images are considered. But this procedure is very tiring and time taking. For Hand gesture recognition, some researchers have tried to perform the early segmentation process using skin colour histogram Zhou et al. Paper [20] – [22] used overlapping sub-windows which is useful to extract invariants for gesture recognition, and distinguish them with a local orientation histogram attribute description indicating the distance from the canonical orientation. This makes the process relatively robust to noise, however, much more time consuming indeed. Kuno and Shirai defined seven different stages of hand gesture recognition. It includes position of the figure-tip. This is not practically realistic when we have only pointing gestures, but also several gestures, like grasping. ISO 9001:2008 Certified Journal
|
Page 617