In the distant 1989, there were many major events in the world: the Berlin Wall was torn down, the World Wide Web came out, and Madonna's "Like a Prayer" swept through the major music charts. In Pittsburgh, USA, a refurbished military ambulance was driven on the campus of Carnegie Mellon University without any human intervention. Its name was ALVINN. Self-driving cars may be a technical phenomenon that has only started in recent years, but in fact, about 30 years ago, researchers and engineers have already produced a car with automatic driving ability. Carnegie Mellon University began research on computer-controlled vehicles in 1984 and began producing their research two years later: a car called Navlab 1. ALVINN, known as the Autonomous Land Vehicle In a Neural Network, was born as a test vehicle in the 1990s. Recently, two engineers mentioned this ancient autopilot prototype on Twitter. They are Oliver Cameron, head of Udacity open source autonomous driving project, and Dean Pomerleau, professor of Carnegie Mellon University. I developed ALVINN in one hand. According to Professor Pomerleau, ALVINN used an operating system with 100 million floating-point operations per second, which is only one-tenth of the performance of Apple Watch today. ALVINN's processor is as large as a refrigerator and powered by a 5000W generator. In any case, ALVINN has reached 70 mph (about 112.7 km/h) at that time. Cameron believes that as a military-funded, eight-year research project, ALVINN developed by Carnegie Mellon University Robotics Academy can be seen as the father of autonomous vehicles. This is because its autonomous driving ability comes from a neural network, which was absolutely cutting-edge at the time. This technology is gradually being used by more and more researchers in the future research of autonomous vehicles. Compared to Google's self-driving cars that use 3D maps, ALVINN's use of neural networks makes it intelligent, making decisions without the need for a map. “You can put a neural network-powered car in a position it has never seen before, and it can also travel gracefully using techniques derived from human experience,†Cameron said. By using neural networks to teach car driving, Professor Pomerleau hopes to build an automated driving system that can use different conditions. The prototype he developed was used to control NAVLAB, the self-driving car project launched by Carnegie Mellon in 1984. After that, the neural network of ALIVINN "has an elegant effect, but it is limited by hardware." It is worth mentioning that Chris Urmson, the former chief engineer of the Google Autopilot project, has worked with Carnegie Mellon and Professor Pomerleau. In 2007, Urmson expanded on Navlab and led Carnegie Mellon's team to win the DARPA Urban Grand Challenge. He was then taken by Google and was responsible for the research work of the latter's self-driving car project. At the same time, Uber also spawned an olive branch to more than a dozen robotics experts at Carnegie Mellon, inviting them to join their own self-driving car project. It can be said that the origins of many autonomous car projects today can be traced back to Professor Pomerleau and the NAVLAB project.
Aluminum stub end has many advantages such as long service life, light weight, good heat resistance, good corrosion resistance, good heat preservation, high impact. According to the grad of the aluminum, it can be divided into aluminum 1060 stub end, aluminum 5083 stub end, aluminum 6061 stub end, aluminum B241 stub end.
Item Cold: aluminum stub end
Diameter: 1" 1.5" 2" 2.5" 3" 3.5" 4" 5" 6"
Wall thickness: 1.5mm,1.8mm,2.0mm,2.5mm
Surface treatment: Polish/Raw
Material: Aluminum 6061/Aluminum 6063/Aluminum 5083
MOQ: 50 pieces
Packing: Plastic bags and carton boxes
Aluminum Stub End,Aluminum 1060 Stub End,Aluminum 5083 Stub End,Aluminum 6061 Stub End,Aluminum B241 Stub End HEBEI HANMAC MACHINE CO., LTD. , https://www.chinahanmac.com
