Human-Centered Autonomous Vehicle Systems: Principles of Effective Shared Autonomy

arXiv.org Artificial Intelligence

Building effective, enjoyable, and safe autonomous vehicles is a lot harder than has historically been considered. The reason is that, simply put, an autonomous vehicle must interact with human beings. This interaction is not a robotics problem nor a machine learning problem nor a psychology problem nor an economics problem nor a policy problem. It is all of these problems put into one. It challenges our assumptions about the limitations of human beings at their worst and the capabilities of artificial intelligence systems at their best. This work proposes a set of principles for designing and building autonomous vehicles in a human-centered way that does not run away from the complexity of human nature but instead embraces it. We describe our development of the Human-Centered Autonomous Vehicle (HCAV) as an illustrative case study of implementing these principles in practice.


AgeLab researching autonomous vehicle systems in ongoing collaboration with Toyota

MIT News

The MIT AgeLab will build and analyze new deep-learning-based perception and motion planning technologies for automated vehicles in partnership with the Toyota Collaborative Safety Research Center (CSRC). The new research initiative, called CSRC Next, is part of a five-year-old ongoing relationship with Toyota. The first phase of projects with Toyota CSRC has been led by Bryan Reimer, a research scientist at MIT AgeLab, which is part of the MIT Center for Transportation and Logistics. Reimer manages a multidisciplinary team of researchers and students has focused on understanding how drivers respond to the increasing complexity of the modern operating environment. He and his team studied the demands of modern in-vehicle voice interfaces and found that they draw drivers' eyes away from the road to a greater degree than expected, and that the demands of these interfaces need to be considered in the time course optimization of systems.


How AI Is Driving The Next Phase Of Autonomy

#artificialintelligence

Artificial intelligence is transforming virtually every industry, from healthcare, to manufacturing, to education. However, one of the most significant areas that AI is influencing is the way people and goods move. At this year's GPU Technology Conference (GTC) in Silicon Valley, companies, researchers, media and analysts will gather to hear, see and experience the latest in AI innovations. Among those are the automakers, suppliers and startups working to make safe self-driving a reality. Industry experts, analysts and media gather at GTC Silicon Valley to see the latest in autonomous driving technology.NVIDIA Virtually every type of automotive company is leveraging the performance of GPUs to develop AI-powered autonomous driving systems.


Tesla Has Begun Making All Its New Cars Self-Driving

NPR

Tesla has begun equipping all its new cars with self-driving hardware. Elon Musk, Tesla's CEO, tweeted Wednesday night that the new Tesla drives itself with no human input, using has eight cameras, 12 ultrasonars, and radar. All this hardware is mounted so the technology is not visible to drivers. The company's current slate of cars being built now, the Model S sedan and the Model X SUV, have the hardware that will eventually make full autonomy possible. Cars previously built don't have the new hardware and -- this is the moment, in the article where early adopters groan -- Musk said in a tweet that retrofitting vehicles won't be possible.


Waymo dumped partial self-driving features after discovering people sleeping while driving

Mashable

Self-driving vehicle innovators Waymo revealed the company abandoned partially autonomous features because it found people napping in cars while traveling at high speeds, threatening their ability to grab hold of the wheel -- if necessary. During a tour of Waymo's testing facility on Monday, CEO John Krafcik told Reuters the company discovered the snoozing drivers during highway testing in 2013. SEE ALSO: Here's why Apple co-founder Steve Wozniak is skeptical of Tesla's Autopilot system "What we found was pretty scary," said Krafcik "It's hard to take over because they have lost contextual awareness." After seeing this unsettling behavior on video, Waymo decided it would only focus on completely autonomous self-driving, as opposed to cars that accelerated, decelerated, and navigated on their own, but still required people to pay attention and potentially intervene. Waymo is currently testing its completely autonomous driving technology in the Phoenix area, and they're looking for more volunteers to take part in its Early Rider Program.