I want to make a self driving (autonomous) wheelchair where I want to create a map for localisation of the wheelchair.

I do not want to use LIDAR as it is very expensive. Also, I do not mind if the map is not created dynamically. I want to create a virtual 3D map of my building along with a virtual wheelchair inside it.

Then, I want to use a machine learning technique as suggested by these videos:

Finally, I can apply the learnt model on my wheelchair. So, my questions are:

  1. How can I create a virtual 3D map of my building?

  2. Is there any other better technique I can use in making the autonomous wheelchair?

  • $\begingroup$ Have you thought about using a Kinect to collect point cloud data to create your map? This process might be really good to get started as it is not very expensive, and you can easily(IF YOU ARE COMFORTABLE WITH ROS) set it up with ROS to look at the dynamic point cloud data collection. Alternatively you could lean towards a visual slam method using stereo cameras. $\endgroup$ – JJerome Aug 26 '19 at 23:31

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.