Abstract
Autonomous mobile devices operating in confined environments, such as pipes, underground tunnel systems, and cave networks, face multiple open challenges from the robotics perspective. Those challenges, such as mobility, localization, and mapping in GPS denied scenarios, are receiving particular attention from the academy and industry. One example is the Brazilian mining company Vale S.A., which is employing a robot – EspeleoRobo (SpeleoRobot) – to access restricted and dangerous areas for human workers. The EspeleoRobo is a robot initially designed for natural cave inspection during teleoperated missions. It is now being used to monitor other types of confined environments, such as dam galleries and other restrained or dangerous areas. This paper describes the platform in its current version and the pipeline used for semi-autonomous inspection in confined environments. The pipeline includes photorealistic mapping techniques, Simultaneous Localization and Mapping (SLAM) with LiDAR, path planning based on mobility optimization, and navigation control using vector fields to reduce operator dependency of the robot operation. The proposed concept was validated in simulations with a realistic underground tunnel system and in representative real-world scenarios. The results endorse the viability of using the proposed concept for real deployments.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have