Congratulations! The paper “Autonomous Power Line Inspection with Drones via Perception-Aware MPC” by J. Xing, G. Cioffi, J. Hidalgo-Carrió, and D. Scaramuzza won the best paper award at the IEEE Conference on Intelligent Robot and Systems.
Inspecting power lines is a tedious, error-prone, and dangerous work for humans. Drones have the potential to revolutionize power line inspection by increasing productivity and quality while at the same time eliminating the risks for human operators. However, current state-of-the-art systems still require precise information about the location of power lines and masts, because control and obstacle avoidance are not coupled with the drone’s visual system. In this paper, the researchers propose an MPC (Model Predictive Controller) that tightly couples perception and action, thus maximizing the visibility of power lines and safely avoiding the masts. The code and datasets are released publicly.