Optimal surveillance coverage for teams of micro aerial vehicles in GPS-denied environments using onboard vision

This paper deals with the problem of deploying a team of flying robots to perform surveillance-coverage missions over a terrain of arbitrary morphology. In such missions, a key factor for the successful completion of the mission is the knowledge of the terrain’s morphology. The focus of this paper is on the implementation of a two-step procedure that allows us to optimally align a team of flying vehicles for the aforementioned task. Initially, a single L. Doitsidis ( ) Department of Electronics, Technological Educational Institute of Crete, Chania, 73133, Greece e-mail: [email protected] L. Doitsidis · E. Kosmatopoulos Informatics & Telematics Institute, (ITI-CERTH), 57001, Thessaloniki, Greece S. Weiss · M.W. Achtelik · R. Siegwart Autonomous Systems Lab, ETH Zurich, Zurich, Switzerland S. Weiss e-mail: [email protected] M.W. Achtelik e-mail: [email protected] R. Siegwart e-mail: [email protected] A. Renzaglia INRIA Rhône-Alpes, Grenoble, France e-mail: [email protected] E. Kosmatopoulos Dept. of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi 67100, Greece e-mail: [email protected] D. Scaramuzza AI Lab, University of Zurich, Zurich, Switzerland e-mail: [email protected] robot constructs a map of the area using a novel monocularvision-based approach. A state-of-the-art visual-SLAM algorithm tracks the pose of the camera while, simultaneously, autonomously, building an incremental map of the environment. The map generated is processed and serves as an input to an optimization procedure using the cognitive, adaptive methodology initially introduced in Renzaglia et al. (Proceedings of the IEEE international conference on robotics and intelligent system (IROS), Taipei, Taiwan, pp. 3314– 3320, 2010). The output of this procedure is the optimal arrangement of the robots team, which maximizes the monitored area. The efficiency of our approach is demonstrated using real data collected from aerial robots in different outdoor areas.