Autonomous Navigation and Mapping for Inspection of Penstocks and Tunnels with MAVs
Published in IEEE Robotics and Automation Letters (RA-L), 2017
This paper presents an autonomous inspection system for penstocks and tunnels using micro aerial vehicles (MAVs) equipped with a 3D LiDAR, inertial measurement unit (IMU), and onboard cameras. The system estimates the full 6 Degrees of Freedom (DOF) pose and builds a local map in real time, even in GPS-denied and visually degraded conditions.
The approach models tunnels as generalized cylinders and relies on a fusion framework that integrates range and inertial data to provide accurate state estimation. The proposed method was validated with field deployments inside penstocks at Center Hill Dam, TN, where autonomous and shared-control flights demonstrated precise navigation and mapping in complete darkness.
Recommended citation: Özaslan, T., Loianno, G., Keller, J., Taylor, C. J., Kumar, V., Wozencraft, J. M., & Hood, T. (2017). "Autonomous Navigation and Mapping for Inspection of Penstocks and Tunnels with MAVs." IEEE Robotics and Automation Letters, April 2017.
Download Paper
Related people: Tolga Ozaslan