The Defense Advanced Research Projects Agency (DARPA)has awarded researchers at Embry-Riddle Aeronautical University and Creare LLC with a $1 million grant from to develop a extremely refined autonomous flight management system to navigate unmanned aerial automobiles (UAVs) in unknown dynamic environments, similar to crowded city areas, or in harmful or hostile conditions.
“Potential uses for this technology include search and rescue missions or remote surveillance and assessment of conditions too hazardous for humans,” mentioned Dr. Richard Prazenica, Assistant Professor of Aerospace Engineering and Principal Investigator at Embry-Riddle’s Daytona Beach Campus. “This intelligent, autonomous UAV could explore unmapped or unsafe environments to locate someone injured in an earthquake, or assist and communicate with firefighters while gathering information as it moves through a smoke-filled building.”
The enhanced navigational system would incorporate current developments in small, low-power and low-cost sensor know-how and improved pc with out GPS, supported by a high-performance steering, navigation and management (GNC) system.
The Embry-Riddle group consists of graduate college students within the Aerospace Engineering Department led by Prazenica and Co-Principal Investigators Dr. Troy Henderson and Dr. Hever Moncayo.
The autonomous GNC system would come with Three-D terrain sensing capabilities utilizing imaginative and prescient sensors and laser-based LiDAR (mild detection and ranging) sensors. Cutting-edge know-how together with synthetic intelligence-based flight management programs might compensate for disturbances similar to wind gusts, transferring objects and potential system failures.
“These intelligent algorithms would increase mission performance by adding a cognitive capability to the system for decision making while operating under dynamically changing environments,” mentioned Moncayo. “Imagine a system that can decide what path to choose or what maneuvers to perform, without human intervention, should it be faced with unpredicted external or internal scenarios.”
“The UAV would be able to autonomously plan and execute a path by creating a three-dimensional map of any given environment to enable obstacle avoidance,” mentioned Prazenica. “This intelligent flying platform should, without a human operator, be able to simultaneously map and fly a mission to a specific location within a changing environment, regardless of visibility, to gather data and images or perhaps to deliver life-saving medical supplies.”
During the lately accomplished $150,000 Phase I grant, a Droidworx SkyJib X4 quadcopter was outfitted with sensor tools that included monocular, stereo and infrared cameras, a scanning LiDAR and an inertial navigation system with GPS. This UAV served as a take a look at platform for knowledge assortment throughout Phase I and could be used for GNC system growth and validation through the Phase II program.
“The UAV should be able to accomplish its mission using vision and navigation sensors without the aid of GPS, which can be unavailable in cluttered urban or indoor environments,” mentioned Henderson. “Military and law enforcement applications might include bomb damage identification and assessment, or intelligence, surveillance and reconnaissance missions without putting soldiers’ lives at risk.”