Goto

Collaborating Authors

Is 'The Jetsons' flying car finally here?

AITopics Original Links

Aerospace company Terrafugia is working on the concept of a flying electric car Called TF-X, the vehicle is designed to be capable of vertical take-offs and landings The goal is to make personal aviation accessible to a broader segment of the population The company estimates a period of 8-12 years before it's able to develop TF-X The company estimates a period of 8-12 years before it's able to develop TF-X Point taken, but perhaps now, as our childhood dreams move slowly closer to reality, we should also start pondering this: if a flying car was here today, in the real world and not in the realm of science fiction, would we feel comfortable controlling it safely while cruising thousands of feet up in the air? Would we possess the technical skills required to even get it off the ground, let alone land it without a scratch? Before you dash to the door and sprint to your nearest pilot school to sign up for flight lessons, take a moment to meet Carl Dietrich, the chief executive and co-founder of aerospace company Terrafugia. Dietrich and his team are working to bring consumers closer to the prospect of a practical flying car, envisioning a vehicle that does not require its operator to be a trained pilot. Thus, Boston -based Terrafugia announced last May it had started working on the concept of TF-X, a four-seat, plug-in hybrid electric car that can do vertical take-offs and landings.


Runtime Safety Assurance Using Reinforcement Learning

arXiv.org Artificial Intelligence

The airworthiness and safety of a non-pedigreed autopilot must be verified, but the cost to formally do so can be prohibitive. We can bypass formal verification of non-pedigreed components by incorporating Runtime Safety Assurance (RTSA) as mechanism to ensure safety. RTSA consists of a meta-controller that observes the inputs and outputs of a non-pedigreed component and verifies formally specified behavior as the system operates. When the system is triggered, a verified recovery controller is deployed. Recovery controllers are designed to be safe but very likely disruptive to the operational objective of the system, and thus RTSA systems must balance safety and efficiency. The objective of this paper is to design a meta-controller capable of identifying unsafe situations with high accuracy. High dimensional and non-linear dynamics in which modern controllers are deployed along with the black-box nature of the nominal controllers make this a difficult problem. Current approaches rely heavily on domain expertise and human engineering. We frame the design of RTSA with the Markov decision process (MDP) framework and use reinforcement learning (RL) to solve it. Our learned meta-controller consistently exhibits superior performance in our experiments compared to our baseline, human engineered approach.



NASA's Replica Orion Spacecraft's Drop-Test Footage Studying Complex Parachute System Released

International Business Times

NASA's Orion mission is an upcoming Multi-Purpose Crew Vehicle (MPCW), which is under development for launch on the Space Launch System (SLS) designed to carry humans into deep space in the future. It is currently undergoing stringent testing and development at NASA. The latest success in the project came when NASA tested out the parachute landing system for Orion in the southwestern Arizona desert.


Recovery effort suspended for airman lost in Gulf of Mexico

FOX News

The Air Force has identifies the missing airman who fell into Gulf of Mexico from a C-130 aircraft. He is presumed dead as recovery efforts continue. The search for an Air Force special tactics combat controller who fell into the Gulf of Mexico after falling out of a plane earlier this month has been suspended, military officials said over the weekend. The Air Force, along with other military branches, has conducted round-the-clock searches in an effort to recover the remains of Staff Sgt. Cole Condiff, 29, fell out of a plane earlier this month into the Gulf of Mexico.