We would like to share two of our recent and ongoing results related to autonomous exploration and mapping in darkness. As opposed to approaches that rely on localization based on LiDAR systems, the videos below rely on visual-inertial localization with LEDs illuminating the scene appropriately. For the first case, visible-spectrum cameras are used, while for the second near-infrared cameras are employed. We believe that operation in darkness is an important feature for aerial robotics and we would like to see more in that direction.
For more please visit: http://www.autonomousrobotslab.com/
Comments
Great stuff! Are you going to make the work accessible for others to test? If not is there a plan to commercialise the system? As you might have guessed, my interest is in underground mining.
Hi Cameron, thanks for your interest. There is no use of UWB or other external localization system. The system performs localization solely based on the camera images and the IMU. The ToF sensor supports the mapping task. You are very correct regarding the application domain!
Are the cameras it's using localise fixed to the environment or the drone? Does it use UWB to help localise (with reference to your TOF comment)? What I'm getting at is if I drop this in an underground mine, can it map out a newly blasted tunnel without any prior setup?