Collaborating Authors

Staff Systems Engineer, Perception & Sensing


Argo AI was founded to tackle one of the most challenging applications in computer science, robotics and artificial intelligence with self-driving vehicles. Argo AI is developing and deploying the latest advancements in artificial intelligence, machine learning and computer vision to help build safe and efficient self-driving vehicles that enable these transformations and more. The challenges are significant, but we are a team that believes in tackling hard, meaningful problems to improve the world. We are building a high-performance team that is excited by complex engineering challenges and is passionate about making transportation safer, more affordable and accessible for all. Within this organization, the Functional Architecture systems team at Argo AI is responsible for defining the top level functionality and requirements of the self driving system and following through with functional and requirements decomposition, definition of the functional architecture and allocation of functionality to the various subsystems and modules that comprise the autonomous vehicle.

Germany legalizes self-driving car tests


German automakers won't have to bring their experimental autonomous cars to California for testing anymore. The country has just approved a law allowing companies to test their self-driving cars on its roads, so long as they follow a set of conditions. Perhaps the most important requirement is that drivers must be sitting behind the wheel all the time. They can take their eyes off the road to, say, use their phone and browse the internet, but they need to be able to take over if the vehicle's AI needs them to. In addition, the vehicles need to have a black box to record the journey and log whether it's the AI or the driver that's in charge.

Explanations in Autonomous Driving: A Survey


The automotive industry is seen to have witnessed an increasing level of development in the past decades; from manufacturing manually operated vehicles to manufacturing vehicles with high level of automation. With the recent developments in Artificial Intelligence (AI), automotive companies now employ high performance AI models to enable vehicles to perceive their environment and make driving decisions with little or no influence from a human. With the hope to deploy autonomous vehicles (AV) on a commercial scale, the acceptance of AV by society becomes paramount and may largely depend on their degree of transparency, trustworthiness, and compliance to regulations. The assessment of these acceptance requirements can be facilitated through the provision of explanations for AVs' behaviour. Explainability is therefore seen as an important requirement for AVs.

Unlike most of US, autonomous vehicles in the UK won't require riders


As soon as this year, self-driving cars in the UK could be truly driverless. That is, except for the remote control driver monitoring the vehicle while it drives in trial runs. But no one has to be in the car, so the future really is here. The UK's Department for Transport put out an updated "Code of Practice" Wednesday for testing autonomous vehicles. In the new guidelines (the previous report was from 2015) for companies trialing self-driving vehicles it outlines what's permitted.

Michigan may no longer require humans behind the wheel of self-driving cars

AITopics Original Links

Michigan would no longer require that someone be inside a self-driving car while testing it on public roads under legislation passed unanimously Wednesday by the state Senate, where backers touted the measures as necessary to keep the U.S. auto industry's home state ahead of the curve on rapidly advancing technology. The expansive bills, which are on track for final legislative approval by year's end, would make Michigan a rare state to explicitly end a requirement that a researcher be inside an autonomous test vehicle. The researcher would have to "promptly" take control of its movements remotely if necessary, or the vehicle would have to be able to stop or slow on its own. Supporters said the human-operator requirement is seen as an impediment that could put Michigan at risk of losing research and development to other states. Other provisions would allow for public operation of driverless vehicles when they are sold, ease the "platooning" of autonomous commercial trucks traveling closely together at electronically coordinated speeds and help create a facility to test autonomous and wirelessly connected cars at highway speeds at the site of a defunct General Motors plant that once churned out World War II bombers.