I am interested in autonomous machines that operate in harsh environments capable robots that explore and work in construction, mining, agricultural and planetary-exploration environments. Most robot tasks require terrain and environment models . Sensors able to perceive under all visibility conditions provide the information to build these models under extreme conditions and enable continuos robot operations in harsh environments.
My focus is on using radar for precise environmental imaging and terrain models. Vacuum, dust, fog, rain, snow and light conditions compromise the effectiveness of laser and stereo. Radar can offer remarkable advantages as a robotic perception mode because it is not as vulnerable to the aforementioned conditions. However, radar has shortcomings such as a large footprint, sidelobes, specularity effects and limited range resolution, all of which result in poor perception models. I investigate interpretation techniques for building high-resolution and high-fidelity perception models from radar sensing.