Presentation Title

Autonomous Navigation of UAVs in the Indoor Environment for Search and Rescue Missions

Faculty Mentor

Subodh Bhandari

Start Date

17-11-2018 8:30 AM

End Date

17-11-2018 10:30 AM

Location

HARBESON 15

Session

POSTER 1

Type of Presentation

Poster

Subject Area

engineering_computer_science

Abstract

This presentation talks about the research on developing capabilities for autonomous navigation of small unmanned aerial vehicles (UAVs) for indoor search and rescue missions. Indoor environment poses unique challenges for autonomous navigation of vehicles such as lack of GPS signal and pre-existing maps, and presence of many obstacles. The use of lightweight multicopters makes them ideal for maneuvering through tight spaces and locating targets in shorter times. Simultaneous localization and mapping (SLAM) techniques and collision avoidance system (CAS) are used to autonomously navigate the vehicle in the GPS-denied environments. SLAM, CAS, and target recognition software can help rescuers locate victims for disaster relief. Using a LIDAR and camera, it is possible to build a map of an indoor environment while localizing the UAVs within that map. An RPLidar system is used in conjunction with the HectorSLAM algorithm for creating the map of the indoor environment in real-time. A Mobius Actioncam is used for the target detection. Identification of targets and collision avoidance is achieved using deep learning algorithm, which is trained using deep neural network (DNN). The detection algorithm runs on an NVidia Jetson TX1 microcomputer. The Jetson TX1 communicates with the onboard Pixhawk flight controller, while also transmitting data to a ground control station using Xbee radio modules. Simulation and test results will be presented. This research has potential to aid the rescuers in the disaster-hit areas by helping them locate and rescue the victims faster without endangering the rescuers’ lives.

This document is currently not available here.

Share

COinS
 
Nov 17th, 8:30 AM Nov 17th, 10:30 AM

Autonomous Navigation of UAVs in the Indoor Environment for Search and Rescue Missions

HARBESON 15

This presentation talks about the research on developing capabilities for autonomous navigation of small unmanned aerial vehicles (UAVs) for indoor search and rescue missions. Indoor environment poses unique challenges for autonomous navigation of vehicles such as lack of GPS signal and pre-existing maps, and presence of many obstacles. The use of lightweight multicopters makes them ideal for maneuvering through tight spaces and locating targets in shorter times. Simultaneous localization and mapping (SLAM) techniques and collision avoidance system (CAS) are used to autonomously navigate the vehicle in the GPS-denied environments. SLAM, CAS, and target recognition software can help rescuers locate victims for disaster relief. Using a LIDAR and camera, it is possible to build a map of an indoor environment while localizing the UAVs within that map. An RPLidar system is used in conjunction with the HectorSLAM algorithm for creating the map of the indoor environment in real-time. A Mobius Actioncam is used for the target detection. Identification of targets and collision avoidance is achieved using deep learning algorithm, which is trained using deep neural network (DNN). The detection algorithm runs on an NVidia Jetson TX1 microcomputer. The Jetson TX1 communicates with the onboard Pixhawk flight controller, while also transmitting data to a ground control station using Xbee radio modules. Simulation and test results will be presented. This research has potential to aid the rescuers in the disaster-hit areas by helping them locate and rescue the victims faster without endangering the rescuers’ lives.