Researcher makes drones smarter, team-oriented, and situationally aware

A researcher makes drones smarter, team-oriented, and situationally aware as part of an NSF-funded project to allow UAVs, taking into account various situations, to track themselves and each other.

Researcher makes drones smarter, team-oriented, and situationally aware

Recent developments in 人工智能 ( AI) have opened the door to an extraordinary number of applications for unmanned autonomous vehicles (UAVs). Drone groups can now work together in networks for uses such as traffic management, smart farming, security and surveillance systems, law enforcement, public safety, and many more.

Present drone systems, however, lack crucial considerations, such as the ability to properly recognize and respond to environmental and behavioral factors, says Abolfazl Razi, an assistant professor at the University of Northern Arizona‘s School of Informatics, Computation, and Cyber Systems (SICCS).

That’s why Razi works to make drones more intelligent and autonomous. For his project entitled “Proactive Inverse Learning of Network Topology for Predictive Communication among Unmanned Vehicles,” Razi, director of NAU’s Wireless Networking and Smart Health (WiNeSH) Center, obtained a $480,000 grant from the National Science Foundation.

The director of NAU’s Wireless Networking and Smart Health (WiNeSH) Lab, Razi has received a $480,000 grant from the National Science Foundation for his project titled, “Proactive Inverse Learning of Network Topology for Predictive Communication among Unmanned Vehicles.”

He believes drones can be developed through computer programming to demonstrate situational awareness, identify malfunctioning, suspect or invading UAVs, and make changes on the move.

“When we have hundreds of drones with limited communication ranges flying together, we need to keep connectivity and information flow uninterrupted,” Razi said in a news release. “The focus of this project is to enable UAVs to monitor themselves and each other, taking into account different scenarios.”

Adversity addresses an essential aspect of the project. “A drone that has joined a mission may show an anomaly and violate the set regulations for the mission. Instead of following the pre-planned motion trajectory, it may go dangerously close to other drones, for example,” he said. “We want other drones to be able to analyze the trajectory and identify misbehavior or misconduct, or even interference of an outside drone and diagnose the problems within a network.”

Razi says vital missions could include forest fires, traffic collisions, 搜索和救援, or military activities. “If someone tries to penetrate your mission by sending in their own drones and making problems either on purpose or by accident, we want the UAVs to find the intrusion and cope with the situation.”

The study is intended to make drones more independent of human control and observation, by communicating with other unmanned aircraft in their area, behaving like teammates, and being able to distinguish intruding or enemy drones.

In his WiNeSH lab and outdoors in northern Arizona, Razi will perform tests with UAV teams. “Each drone will be equipped with software capable to make decisions about the environment,” Razi said. “Also, each will have its eyes on the other drones and will observe whether its neighbors are making decisions that are rational or irrational.”

The thesis would cover the human-inspired constructive learning process from minimal knowledge by presenting the program to varying situations and requiring reverse engineering of the decision support system ( DSS) of the UAVs.

“This approach serves for AI-enabled networking by incorporating the predicted responses into system protocols,” Razi said.

With the ultimate goal of creating improved systems with multiple autonomous drones, the three-year project is intended to support US government departments, organizations, and researchers.

保持联系！

If you’d like to stay up to date with all the latest drone news, scoops, rumors, and reviews, follow us on 推特, 在 Facebook 上, YouTube, Instagram, or…

订阅我们的每日无人机新闻电子邮件*。

提交提示 如果您想与我们分享信息或技巧，请随时提交 这里. 支持 DroneXL.co： 您可以在下次购买无人机时使用这些链接来支持 DroneXL.co： Adorama, 亚马逊, B&H, 百思买, 易趣网, 大疆创新, 鹦鹉和 Yuneec.我们会在您不支付额外费用的情况下收取少量佣金。感谢您帮助 DroneXL 发展！ 联邦贸易委员会： DroneXL.co 使用可产生收入的联盟链接。

* 我们绝不出售、共享、出租或发送垃圾邮件。我们的电子邮件在工作日下午 5:30 左右发出。

Courtesy Northern Arizona University