Grant: Engage Grants Program
University of Alberta
$25,000.00
Computer vision-based Human-Robot Interface for handicapped users of Kinova's Jaco robot arm and hand
FY 2013-14
Summary
This projects looks to develop a computer vision based Human-Robot Interface (HRI) for Kinova's Jaco RehabEdition robot arm. Upper body disabled currently need nursing assistance to perform most daily tasks. Kinova'sJaco robot arm and hand is designed to be mounted on a wheelchair, and allow a disable person to pick up andmanipulate many everyday objects (reasonably light and small). Currently the robot motion is controlleddirectly by the wheelchair joystick. Since the joystick only has 2 DOF (Degrees Of Freedom) and the robot andhand 7 DOF, the user has to switch between modes coupling the joystick to different translation, rotation andgrasp motions. This is time consuming and cumbersome. In our proposed project Computer Vision is used toextract objects and 3D locations in the scene. We will add a camera and small LCD screen to the current robotarm and power wheelchair system. With just one joystick motion the user can place a cursor on or near anobject in the screen image of the scene. From this a semi-autonomous robot vision routine will be able to reachtowards that object and align the hand in a suitable grasp orientation. We have discussed this solution withKinova and expect the system to significantly ease the cognitive load for disabled people using the robot aswell as speed up the pace of tasks. This will be of benefit to Kinova, disabled users and can result in broaderuse of robot arms in Canadian rehabilitation health care.
Program
Engage Grants Program
Recipient
Location
Alberta, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
450427-2013
Name nom
Jagersand, Martin
Department département
Computing Science
Organization id
9
Institution établissement
University of Alberta
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2013
Competition year année de concours
2013
Award amount
25000
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1555
Committee name en
Prairie Internal Decision Committee
Committee name fr
Comité de décision interne pour les Prairies
Area of application code
518
Area of application group en
Manufacturing processes and products
Area of application group fr
Procédés et produits industriels
Area of application en
Medical equipment and apparatus
Area of application fr
Appareils et instruments médicaux
Research subject code
2603
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Computer vision
Research subject fr
Vision artificielle
Partie
1
Nb partie
1
Application title
Computer vision-based Human-Robot Interface for handicapped users of Kinova's Jaco robot arm and hand
Keyword
NSERC
Application summary
This projects looks to develop a computer vision based Human-Robot Interface (HRI) for Kinova's Jaco RehabEdition robot arm. Upper body disabled currently need nursing assistance to perform most daily tasks. Kinova'sJaco robot arm and hand is designed to be mounted on a wheelchair, and allow a disable person to pick up andmanipulate many everyday objects (reasonably light and small). Currently the robot motion is controlleddirectly by the wheelchair joystick. Since the joystick only has 2 DOF (Degrees Of Freedom) and the robot andhand 7 DOF, the user has to switch between modes coupling the joystick to different translation, rotation andgrasp motions. This is time consuming and cumbersome. In our proposed project Computer Vision is used toextract objects and 3D locations in the scene. We will add a camera and small LCD screen to the current robotarm and power wheelchair system. With just one joystick motion the user can place a cursor on or near anobject in the screen image of the scene. From this a semi-autonomous robot vision routine will be able to reachtowards that object and align the hand in a suitable grasp orientation. We have discussed this solution withKinova and expect the system to significantly ease the cognitive load for disabled people using the robot aswell as speed up the pace of tasks. This will be of benefit to Kinova, disabled users and can result in broaderuse of robot arms in Canadian rehabilitation health care.