Deep neural networks (DNNs) have enabled great progress in a variety of application areas, including image processing, text analysis, and speech recognition. DNNs are also being incorporated as an important component in many cyber-physical systems. However, recent research has shown that DNNs are vulnerable to adversarial examples: Adding carefully crafted adversarial perturbations to the inputs can mislead the target DNN into mislabeling them during run time. There have been several techniques proposed to generate adversarial examples and to defend against them. In this blog post we will briefly introduce state-of-the-art algorithms to generate digital adversarial examples, and discuss our algorithm to generate physical adversarial examples on real objects under varying environmental conditions.
Governor Andrew Cuomo of the State of New York declared last month that New York City will join 13 other states in testing self-driving cars: "Autonomous vehicles have the potential to save time and save lives, and we are proud to be working with GM and Cruise on the future of this exciting new technology." For General Motors, this represents a major milestone in the development of its Cruise software, since the the knowledge gained on Manhattan's busy streets will be invaluable in accelerating its deep learning technology. In the spirit of one-upmanship, Waymo went one step further by declaring this week that it will be the first car company in the world to ferry passengers completely autonomously (without human engineers safeguarding the wheel).
NHTSA released their latest draft robocar regulations just a week after the U.S. House passed a new regulatory regime and the senate started working on its own. The proposed regulations preempt state regulation of vehicle design, and allow companies to apply for high volume exemptions from the standards that exist for human-driven cars. It's clear that the new approach will be quite different from the Obama-era one, much more hands-off. There are not a lot of things to like about the Trump administration but this could be one of them. The prior regulations reached 116 pages with much detail, though they were mostly listed as "voluntary."
Nathan is a Reader in the Department of Computer Science at the University of Warwick, whose research into the application of machine learning for autonomous vehicles (or "driverless cars") has been supported by a Royal Society University Research Fellowship. My research uses machine learning to give insights into how objects or people interact and how patterns emerge and evolve. Machine learning algorithms will examine previous behaviours and learn from these behaviours, to then predict what will happen in the future. An accurate algorithm could then be used to inform the decisions vehicles make and predict vehicle journeys and routes.
Recently we've seen a series of startups arise hoping to make robocars with just computer vision, along with radar. That includes recently unstealthed AutoX, the off-again, on again efforts of comma.ai Their optimism is based on the huge progress being made in the use of machine learning, most notably convolutional neural networks, at solving the problems of computer vision. Milestones are dropping quickly in AI and particularly pattern matching and computer vision. There are reasons pushing some teams this way.