In less than three years, artificial intelligence (AI) algorithms developed under DARPA’s Air Combat Evolution (ACE) program have progressed from controlling simulated F-16s flying aerial dogfights on computer screens to …
A sampling of PhysicsAI’s 2021 year in review: ✅We trained a deep neural network in less than one hour to drive a 26-ton US Army truck to perform convoy leader …
PhysicsAI is developing novel real-time machine perception technologies using deep neural networks for applications including: robotics, autonomous vehicles, intelligent sensors, and optimal control. The US Army and DARPA are major …
U.S. military researchers are asking artificial intelligence (AI) experts at PhysicsAI in Pacifica, Calif., to develop AI algorithms to enable future experimental high-performance unmanned combat aircraft to formulate teams of …
In this project PhysicsAI is developing a framework for using deep reinforcement learning (DeepRL) to create optimal training data from simulated imagery in order to train machine learning models with …
In this project, PhysicsAI is developing a spatiotemporal video perception capability based on end-to-end deep neural networks (DNNs) for exploiting full-motion EO/IR sensors mounted on vehicles to provide a real-time …
PhysicsAI will participate in a virtual competition designed to demonstrate advanced artificial intelligence (AI) algorithms that can perform simulated within-visual-range air combat maneuvering, colloquially known as a dogfight. Participants will …
PhysicsAI is developing novel real-time machine perception technologies using deep neural networks for applications including: robotics, autonomous vehicles, intelligent sensors, and optimal control. The US Army is a major customer. …
PhysicsAI is developing new real-time machine perception technologies using deep neural networks for applications including: robotics, autonomous vehicles, and intelligent sensors. The US Army is a major customer. We are …
PhysicsAI will develop a framework for using deep reinforcement learning to create optimal training data from simulated imagery in order to train machine learning models with improved accuracy, increased robustness, …
