Getting around with help from the Kinect
- Posted: Jun 20, 2012 at 6:00 AM
- 4,304 Views
Today's inspirational project is another example of how the Kinect and Kinect SDK can be so much more than just a game device...
Major Project - "Vehicle for physically challenged" in completion of Bachelor of technology from JIIT, Noida in May 2012.
Concept: The project is Novel in the sense that it is highly economically feasible and equally efficient. The project is novel in the sense that it develops a vehicle for physically challenged/disabled people allowing them to travel intra-city and intercity without getting off the wheelchair. Existing system are modified either to allow the physically disabled to drive but involve getting off the wheelchair which means the disabled is dependent on someone else. The vehicle provides independence to the user to travel intra city as well as intercity.
The vehicle was built from scratch using a scooty engine, wiper motors, power window motors etc.
The Vehicle works in two modes:
1) Joystick control of vehicle -- Involves taking input from user through a joystick and then processing to produce servo commands via a Arduino Board.
2) Autonomous driving in constrained environment -- Using input from Kinect sensor to obtain depth image and process the frames in real-time to perform depth based blob detection combining it with vision based blob tracking to perform a robust obstacle detection. The technique involves using a slice of depth image for detecting obstacles and then finding path taking in view the maximum steering angle, width of the vehicle, turning radius etc.
Joystick Module is built in python 2.5; autonomous module is built in c# and uses emgucv, Aforge image processing libraries and Microsoft Kinect SDK 1.0
Hardware includes - Laptop (Intel core i5-2410M @ 2.30 GHZ, 4GB RAM), Joystick, Kinect Sensor, Arduino Uno Microcontroller, Servo, UPS, Battery, servo motors, h-bridges and wireless transmitter and receiver(Fail safe) .
The vehicle also has a fail-safe mechanism that is used to control vehicle in emergency using a wireless remote.
Group Members: Abhishek Singh, Siddhant Singh
Project Mentor: Prof. Sanjay Goel
Project Information URL: http://www.youtube.com/watch?v=Id05Bc79ScI&feature=youtu.be