Institutional Repository
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI: | http://purl.tuc.gr/dl/dias/1C68019B-D783-486E-98A5-5A2EE7AC4EF9 | ||
| Year | 2018 | ||
| Type of Item | Diploma Work | ||
| License |
|
||
| Bibliographic Citation | Dimitrios Chatziparaschis, "Aerial and ground robot collaboration for autonomous mapping in search and rescue missions", Diploma Work, School of Electrical and Computer Engineering, Technical University of Crete, Chania, Greece, 2018 https://doi.org/10.26233/heallink.tuc.79097 | ||
| Appears in Collections |
Nowadays, Humanitarian Crisis scenarios occur on daily basis and typically require immediate rescue intervention. In most cases, the scene conditions may be prohibitive for human rescuers to provide instant aid, because of hazardous, unexpected, and human-unfriendly situations. Those scenarios are ideal for autonomous mobile robot systems to act on, by searching and even rescuing individuals, therefore enhancing rescuers' actions and keeping them safe. In this thesis, we present a ground-aerial robot collaboration approach, in which a quadcopter and a humanoid robot solve a search-and-rescue scenario locally, without any GNSS/GPS system dependencies. Specifically, the quadcopter uses a combination of Simultaneous Localization and Mapping (SLAM) and OctoMapping approaches to extract a 2.5D occupancy grid map of the unknown area in relation to the height of the humanoid robot. At the same time, the quadcopter searches for the humanoid robot in the field and localizes it in the map frame. The humanoid robot awaits for a goal position in the created map and executes a path planning algorithm to estimate the footstep navigation trajectory for reaching the goal. As the humanoid robot navigates, it localizes itself in the map using an adaptive Monte-Carlo Localization algorithm by combining local odometry data with spatial observations from the quadcopter. Finally, the humanoid robot performs visual human body detection using camera data through a Darknet pre-trained neural network. The entire project has been implemented within the Robot Operating System (ROS) and is available as an open source package. The proposed robot collaboration scheme has been tested both in interior and exterior physical environments under real-time conditions. The main advantage of the proposed scheme is the joint-ability to perceive the unknown scene from the air using the quadcopter, while at the same time performing close inspections on the ground using the humanoid robot.
Copyright © DIAS 2013
