Autonomous Drones

Youtube search... ...Google search

• Robotics ... Vehicles ... Drones ... 3D Model ... 3D Simulation Environments ... Simulated Environment Learning ... Point Cloud
• Cybersecurity ... OSINT ... Frameworks ... References ... Offense ... NIST ... DHS ... Screening ... Law Enforcement ... Government ... Defense ... Lifecycle Integration ... Products ... Evaluating
• Policy ... Policy vs Plan ... Constitutional AI ... Trust Region Policy Optimization (TRPO) ... Policy Gradient (PG) ... Proximal Policy Optimization (PPO)
• DRL’s RacerAI Drone is Here to Push Boundaries and Take on Human Pilots
• Inside Unmanned Systems; inside engineering, policy and practice ...Subscribe
• This AI system locates drone pilots flying too close to airports; The system tracks rogue pilots down by analyzing their flight paths | Thomas Macaulay - TNW
• ‘Pandemic drones’ are flying over the US to detect coronavirus symptoms; The Draganfly drones also check adherence to social distancing | Thomas Macaulay - TNW ...Draganfly
• High-speed AI drone beats world-champion racers for the first time | Benj Edwards - ARS Tecnnica ... University of Zürich creates the first autonomous system capable of beating humans at drone racing.
• ‘Guardian of drone’: Chinese scientists create new invisibility cloak | Jijo Malayil - Interesting Engineering ... Advancement lies in controlling metasurfaces to shape scattering fields across space and frequency using spatiotemporal modulation.

Python

Youtube search... ...Google search

Racing

• DRL - Drone Racing League
• AlphaPilot — Lockheed Martin AI Drone Racing Innovation Challenge

Pilots in drone races fly souped-up quadcopters around an obstacle course at 120 miles per hour. But soon they may be out of a job, as race organizers try to spice things up with drones controlled by AI.

What’s new: The Drone Racing League, which stages contests to promote this so-called sport of the future, recently unveiled an autonomous flier called RacerAI. The new drone includes Nvidia’s Jetson AGX Xavier inference engine, four stereoscopic cameras, and propellers that deliver 20 pounds of thrust.

What’s happening: RacerAI serves as the platform for AI models built by teams competing in AlphaPilot, a competition sponsored by the DRL and Lockheed Martin.

• 420 teams entered and tested their models on a simulated track.
• Virtual trials whittled the teams down to nine, which will compete in four races throughout fall 2019.
• Team USRG from Kaist University in South Korea won the first race on October 8. The second is scheduled for November 2 in Washington D.C.
• The series winner will take a $1 million prize. In early 2020, that model will face a top-rated human pilot for an additional $250,000 purse.

Behind the news: Drone Racing League pilots use standardized drones built and maintained by the league, and train on the same simulator used to train RacerAI. Races are typically a mile long and take place in event spaces across the U.S. and Europe.

Why it matters: Drone racing is fun and games, but the skills learned by autonomous racing models could be transferable to real-world applications like automated delivery. We’re thinking: A recent DRL video shows that current models have a way to go before they graduate from passing through rings to making high-speed maneuvers. Human pilots still have a significant edge — for now.

CoDrone

• CoDrone | RoboLink - the first ever programmable drone that was designed to teach you programming

Defense Against Drones

The current research on using AI to eliminate dangerous drone attacks shows promising developments in machine learning technology and its application in anti-drone systems. These technologies are being used to enhance security and defense capabilities, with a range of products available that demonstrate the effectiveness of AI in countering drone threats. However, ongoing challenges such as adversarial attacks and ethical concerns must be addressed to ensure the responsible and effective use of AI in defense applications.

• AI-Based Anti-Drone Solutions: Recent advancements in AI technology have led to the development of sophisticated anti-drone systems capable of detecting, tracking, and neutralizing potentially dangerous drones. Companies like Mistral and Dedrone have introduced AI-driven platforms that offer a range of security applications, including critical infrastructure protection, border security, and tactical operations. These systems boast high detection accuracy, with some claiming up to 98% effectiveness, and can jam drone communication systems and GPS to neutralize threat
• Machine Learning in Drone Detection: Machine learning (ML) algorithms are at the core of these anti-drone technologies. They process vast amounts of data from various sensors to accurately and efficiently detect drones. These algorithms can classify drones based on size, shape, and flight characteristics, which is crucial for assessing the level of risk posed by a detected drone. Moreover, ML enables these systems to adapt to new drone models and attack techniques, ensuring that the knowledge base is continuously updated.
• Autonomous Response and Mitigation: AI and ML algorithms are not only used for detection but also enable automated response and mitigation strategies against unauthorized drones. This includes the ability to autonomously navigate and adjust flight paths in real-time, providing dynamic surveillance capabilities. AI-driven drones can autonomously execute military operations, which is essential for monitoring and securing borders.
• Positive Results and Available Products: The integration of AI in anti-drone systems has led to the development of various products with positive outcomes. For instance, Dedrone offers a suite of solutions like DedronePortable, DedroneTactical, and DedroneTracker.AI, which are designed for quick deployment and easy use in different environments. These systems have been adopted by US federal and local institutions to protect facilities and personnel.
• Challenges and Ethical Considerations: Despite the positive results, there are challenges and ethical considerations to address. Adversarial attacks designed to fool AI-based detection systems are a constant threat. Ethical and legal concerns regarding privacy and data collection must be considered, as well as the potential for friendly fire due to misidentification. The complexity of modeling a tactical environment and the scarcity of data can also impact the performance of ML algorithms.