New research finds verbal prompts can make semi-automated driving safer

New approaches in driving,

New research finds verbal prompts can make semi-automated driving safer

by Amy McCaig, Rice University

Semi-automated cars are becoming increasingly common, but real dangers exist when technology fails and drivers don't intervene.

New research from Rice University and Old Dominion University finds that verbal prompts as simple as "Is January the first month of the year?" help drivers maintain attention during semi-automated driving.

"Boring but Demanding: Using Secondary Tasks to Counter the Driver Vigilance Decrement for Partially Automated Driving" is published in the journal Human Factors: The Journal of the Human Factors and Ergonomics Society. Jing Chen, an assistant professor of psychological sciences at Rice and the senior author of the study, was interested in learning more about how to make semi-automated driving a safer experience with fewer accidents.

"As recent automated driving tragedies have illustrated, this technology is not always perfect at identifying dangerous situations, including objects in the road," she said. "Identifying these hazards and responding in a safe way is sometimes more difficult for automation."

Chen referenced one of her recent studies that demonstrated that human users do not understand how computer vision can be easily deceived. She cited an example of how carefully crafted stickers attached to road signs can be misclassified as critical to safety. As a result, the human driver may need to make up for the limitations of the automated system and assist or take over control of the vehicle.

In the study, 117 students at Old Dominion participated in a simulated, partially automated driving task. The researchers found drivers' attention decreased over the 45-minute task, but asking eight simple questions at random times during the drive significantly increased attention, demonstrated by faster and better responses to hazards.

"With better attention, drivers know when they need to look out for a hazard or take over operation of the automated driving system, which can help prevent accidents," Chen said.

Scott Mishler, a doctoral student at Old Dominion, was the lead author of the study.

More information: Scott Mishler et al, Boring But Demanding: Using Secondary Tasks to Counter the Driver Vigilance Decrement for Partially Automated Driving, Human Factors: The Journal of the Human Factors and Ergonomics Society (2023). DOI: 10.1177/00187208231168697

Provided by Rice University

Self-Driving Cars Must Learn the Language of Cyclists to Keep Roads Safe

ACM TECHNEWS

Self-Driving Cars Must Learn the Language of Cyclists to Keep Roads Safe

By University of Glasgow (U.K.) April 28, 2023 

Dashboard of a self-driving car.

Said Stephen Brewster of the University of Glasgow’s School of Computing Science, “Cars and bikes share the same spaces on the roads, which can be dangerous – between 2015 and 2020, 84% of fatal bike accidents involved a motor vehicle."

Credit: readwrite.com

A study of communications between drivers and cyclists by researchers at the U.K.'s University of Glasgow suggests new autonomous vehicle (AV) systems must be able to replicate those social interactions to ensure safety on the road.

The researchers said integrated displays on the exterior of AVs, or traffic-light-colored LEDs on the edges of the vehicles, could help indicate their intentions, while cyclists could wear smart glasses that allow direct communications from AVs in the form of vibrations.

The researchers found cyclists rely on road signs and traffic signals in controlled intersections, but look at cars to assess drivers' intentions in roundabouts, uncontrolled intersections, and construction areas.

From University of Glasgow (U.K.) ... '

Tesla Autopilots Still a Problem

Seems a fundamental are of their autopilot system.  No resulting injuries known. 

Tesla recalls 363,000 cars over self-driving software  in the BBC

Tesla is updating its self-driving software after US safety officials raised concerns that it could allow drivers to exceed speed limits or travel through intersections unsafely.

The recall affects nearly 363,000 vehicles in the US, according to filings with the US government.

Tesla said it was not aware of any injuries or deaths related to the issues.

US authorities have been investigating the firm's autopilot system.

Officials from the National Highway Traffic Safety Administration (NHTSA) met with Tesla in January to raise concerns about the "full self-driving beta" software, according to the recall notice.

NHTSA said the system allowed behaviour that could "infringe" on local laws or customs such as driving through a yellow light, travelling straight through an intersection from a turn-only lane or not coming to full stop at a stop sign.

"FSD Beta software that allows a vehicle to exceed speed limits or travel through intersections in an unlawful or unpredictable manner increases the risk of a crash," it said. ... ' 

Putting Limits to Vehicle Tech

Limits of autonomous vehicle tech?

Carmakers Are Pushing Autonomous Tech. This Engineer Wants Limits.   By The New York Times.February 16, 2023

Systems like General Motors Super Cruise can steer, brake and accelerate vehicles on their own.

Companies sometimes market these systems as if they made cars autonomous. But their legal fine print requires drivers to stay alert and be ready to take control of the vehicle at any time.

Last fall, Missy Cummings sent a document to her colleagues at the National Highway Traffic Safety Administration that revealed a surprising trend: When people using advanced driver-assistance systems die or are injured in a car crash, they are more likely to have been speeding than people driving cars on their own.

The two-page analysis of nearly 400 crashes involving systems like Tesla's Autopilot and General Motors' Super Cruise is far from conclusive. But it raises fresh questions about the technologies that have been installed in hundreds of thousands of cars on U.S. roads. Dr. Cummings said the data indicated that drivers were becoming too confident in the systems' abilities and that automakers and regulators should restrict when and how the technology was used.

People "are over-trusting the technology," she said. "They are letting the cars speed. And they are getting into accidents that are seriously injuring them or killing them."

From The New York Times

View Full Article    

Uncertain US Self Driving?

 More indication of key elements of uncertainty.  But still, I believe,  in time ultimate success.

Self-Driving Cars Face Uncertain Path to U.S. Deployment

By Reuters, October 31, 2022

The Cruise Origin autonomous vehicle, a Honda and General Motors self-driving car partnership, seen during its unveiling in 2020.

The difficult path to deploying autonomous vehicles (AVs) was highlighted by an announcement  that Ford Motor Co. and Volkswagen AG would close their self-driving startup Argo AI, citing the fact that the technology is still a long way off.

This comes as legislation to amend regulations to include self-driving cars remains stalled in Congress, and officials at the U.S. National Highway Traffic Safety Administration (NHTSA) have not revealed when they might act on petitions to grant initial approval to self-driving vehicles without human controls.

Meanwhile, lawmakers and industry representatives have called on U.S. Transportation Secretary Pete Buttigieg to develop a comprehensive federal framework for AVs to ensure the nation remains competitive, especially as China has made substantial investments in autonomous and connected vehicle technologies.

From Reuters

View Full Article   

Truly Autonomous Cars May Be Impossible Without Helpful Human Touch

Interesting take, but I think they will ultimately be fully possible and used.  We have too much desire for convenience and AI will fill in enough of that to ignore deficiencies. 

Truly Autonomous Cars May Be Impossible Without Helpful Human Touch

By Reuters, September 15, 2022

Although autonomous vehicle (AV) startups have promised to develop truly driverless cars, industry executives and experts say remote human supervisors may need to become permanent.

Self-driving software systems cannot predict and evaluate risk with human-like speed, especially when dealing with unexpected incidents or "edge cases."

Remote human supervisors could monitor video feeds from multiple AVs, ready to intervene and get stalled robot drivers moving again.   Many startups employ remote supervisors to help AVs handle edge cases, and Koosha Kaveh at driverless car rental service Imperium Drive envisions the supervisors becoming "air traffic controllers" for fleets of AVs.

Plunging capital for AVs also is pushing developers to address edge cases and slash costs, while consultant Chris Borroni-Bird is worried "that AV companies will rush to market without proving the safety is better than human-driven vehicles.

From Reuters, Full Text.   

Update on Autonomous Cars

Still waiting ...

Where Are The Autonomous Cars?

By Semiconductor Engineering, August 9, 2022

Level 5 vehicles, which are self-driving in all road situations, do not yet exist. Moreover, it’s not clear when that will change.

Are we there yet? Governments, consumers, and engineers alike want to know how close the automotive world is to producing a fully autonomous Level 5 vehicle.

While some experts say such vehicles could hit the road in the next few years, they're a shrinking minority. Most forecasts say a truly self-driving car is at least a decade away — and maybe much longer, because it requires disruptive technology that has yet to be invented.

At stake are billions of dollars-worth of automotive and tech industry profits, as well as an untold number of human lives. More than a million people around the world die each year in road deaths according to the World Health Organization, though the extent to which such deaths are fully attributable to driver error and could be prevented by high-tech cars is up for debate. Still, the European Union is reportedly planning to approve the sale of Level 4 vehicles — those that are fully autonomous within a specific geographic area or set of circumstances — as part of its attempt to reach zero road deaths by 2050.

There are currently no such cars on the market. Level 4 technology is employed in Waymo ridesharing, a taxi service by the General Motors subsidiary Cruise, and a handful of other projects, but not in consumer vehicles. Level 3, which requires the driver to take over when the system encounters a problem, currently can be found in select Mercedes models in Germany and a small number of Honda Legends in Japan. Advanced driver assistance systems (ADAS) in Teslas and other high-tech cars available to consumers typically are classified as Level 2.

From semiconductor Engineering

View Full Article   

Still Waiting for Fully Self-Driving Cars

What's the real status Among the real players?    Here is quite a lot of data to use.

Still Waiting for Self-Driving Cars

By Keith Kirkpatrick

Communications of the ACM, April 2022, Vol. 65 No. 4, Pages 12-14  10.1145/3516517

Over the past decade, technology and automotive pundits have predicted the "imminent" arrival of fully autonomous vehicles that can drive on public roads without any active monitoring or input from a human driver. Elon Musk has predicted his company Tesla would deliver fully autonomous vehicles by the end of 2021, but he made similar predictions in 2020, 2019, and 2017. Each prediction has fallen flat, largely due to real-world safety concerns, particularly related to how self-driving cars perform in adverse conditions or situations.

The State of Self-Driving Cars Today

Despite such proclamations from Tesla, which released its optimistically named Full Self Driving capability for AutoPilot in October 2021, fully automated self-driving cars have not yet arrived. Instead, most manufacturers are offering systems that feature capabilities that generally fall within the first three of the six levels of autonomy defined by the Society of Automotive Engineering (SAE), which range from Level 0 (no driving automation) to Level 5 (full self-driving capabilities under all conditions).

Most new cars today feature some Level 1 driver assistance technology, including automatic braking, lane-keeping assist, and adaptive cruise control. More advanced systems like Tesla's Autopilot or General Motors' Super Cruise, fall into the Level 2 classification indicating the car can autonomously manage its speed and steering, but requires the driver to remain focused and able to take control in the event of an adverse event. Other manufacturers, such as Honda and Audi, are focusing on Level 3 autonomous systems that allow the car to take complete control, but only under very specific conditions, such as low-speed driving in traffic, in good weather, and only on preapproved roads.

"I'm sure a lot of manufacturers would like to spring over Level 2 and Level 3, to the greatest extent possible," says Peter Hancock, a Pegasus Professor and Provost Distinguished Research Professor in the Department of Psychology and the Institute for Simulation and Training at the University of Central Florida.

However, the most likely scenario under which Level 4-capable vehicles will arrive may be through the deployment of autonomous long-haul trucks. Hancock says that due to global truck driver shortages, there likely will be a stronger push to develop autonomous trucks, at least across interstate highways in the U.S., which are constructed to a specific design standard, are usually in good physical condition, and feature physical barriers between oncoming traffic.

Indeed, Aurora Innovation announced it is building a Level 4 autonomous system and plans to launch its autonomous trucking business in 2023, followed by our autonomous ride-hailing business in 2024. The company told Communications it has partnered with FedEx, Uber, Toyota, and truck OEMs (Volvo and PACCAR) to develop a partnership ecosystem focused on bringing self-driving technology to market. ... '

Regulatory Hurdles for AI Autonomous Cars

 Good piece.

The Key Regulatory Hurdles Facing AI Autonomous Cars 

By Lance Eliot, the AI Trends Insider   

You might be surprised to learn that there is a regulatory enigma of sorts that surrounds and engulfs the advent of AI-based self-driving cars.   

How so?   

Nobody is quite sure what to make of the beast, as it were, in terms of what size and shape of regulatory rules and legal oversight is best warranted for the emergence of self-driving cars.   

Some emphatically insist that we should live and let live, meaning that the marketplace should decide how, where, when, why, and other crucial elements about the deployment of self-driving cars. Others exhort that this is a high-tech innovation that abundantly needs and altogether requires demonstrative legislative controls and strict guidance (it is, after all, akin to a computer on wheels).   

Some reside at nearly polar opposites of what should be done. 

In addition, some sit somewhere in between and are trying to find some agreeable middle ground. One thing that most everyone acknowledges is that self-driving cars are important, and they are especially notable since they involve clear-cut life-or-death kinds of considerations.   

Cars by their very nature are intertwined with life and death.   

We ought to acknowledge that right upfront. We make use of cars on our public roadways. They are an essential form of transportation. Plus, our society has culturally ingrained itself into cars as more than simply a transit option. Car driving is depicted in our movies and TV shows. People discuss cars and the driving of cars as regularly and routinely as they discuss the clothes they wear or what kind of food they eat.   

Teenagers see the driving of a car as a key step toward adulthood and bask in the freedom they can inure by being able to drive a car.  For teens, possessing a driver’s license is a huge source of personal identity and illuminates their rites of passage into the world as independent beings. There has been a tad bit of waning on this heretofore life monumental heralding as some newbie drivers decide to wait to drive, but the preponderance is still in effect.   ....'

Waymo Is 99% of the Way to Self-Driving Cars. The Last 1% Is the Hardest

 Odd illogical example given. Could such an example be solved by freezing and towing the car away?  Can't be that easy. 

Waymo Is 99% of the Way to Self-Driving Cars. The Last 1% Is the Hardest   By Bloomberg Businessweek, August 24, 2021

Despite years of research and billions of dollars in investments, the technology behind self-driving vehicles still has flaws.

Joel Johnson laughs nervously from the backseat when his self-driving taxi stops in the middle of a busy road in suburban Phoenix. The car, operated by autonomous vehicle pioneer Waymo, has encountered a row of traffic cones in a construction zone, and won't move. "Go around, man," Johnson says as he gestures to the drivers honking behind him.

After the vehicle has spent 14 mostly motionless minutes obstructing traffic, a Waymo technician tries to approach—but the car unexpectedly rolls forward, away from him. "It definitely seemed like a dangerous situation," Johnson recalls.

Incidents like this one, which Johnson posted to his YouTube channel in May, are embarrassing for Waymo—a company that's having its own problems moving forward. A unit of Alphabet Inc., Waymo hasn't expanded its robo-taxi service beyond Phoenix after years of careful testing. The company has floated moves into other areas—trucking, logistics, personal vehicles—but the businesses are in early stages. And its production process for adding cars to its driverless fleet has been painfully slow.

From Bloomberg BusinessWeek  

Is the Dream of Self-Driving Car Over?

Are we slipping on compete autonomy?  I don't think so.  It may take longer than expected, but it will be here.   It has too many long range benefits to ignore.    It will also be delivered overseas and the pressure to catch up will be large. 

Why Self-Driving Cars Could be Going the Way of the Jetpack By New Scientist, July 29, 2021

As revolutions go, this one has been rather lacking in revs. For the past decade or so, there have been confident predictions that gas-guzzling cars driven by accident-prone humans would soon be on the slip road to oblivion. The future of mobility was to be all-electric – and all-autonomous.

Electric cars are already on the move, although we must go much further and faster if we are to meet climate goals. Meanwhile, however, the "autonomous" bit seems to be stuttering, to say the least.

To be sure, some of the latest commercially available cars come with ever more computing smarts, such as adaptive cruise control, which allows for occasional hands-free use in very specific road conditions. But beyond a few small-scale tests of truly autonomous vehicles, drivers must keep their eyes and minds on the road at all times. A future where the average motorist can sit back, relax, even take a nap and let the car's computer get them all the way from home to work and back, say, seems barely on the horizon.

Some observers are now openly saying the dream of full autonomy is a mirage: creating robot vehicles able to tackle any kind of road or traffic situation is just too tough a nut to crack. Are they right? And if so, what exactly is keeping down the self-driving car?  ...

A series of high-profile accidents involving fatalities both inside and outside driverless cars has shaken faith in the idea that they are safer overall.  .... 

From New Scientist:      

AI of Autonomous Cars also Useful for Conventional Autos

As you might expect, for example automatic lane holding and parking capabilities are already well known.  My guess to is that such autonomous solutions will be useful in many places.  A good related piece: 

AI of Autonomous Cars Finding Its  Way into Conventional Cars, a Big Crossover   By Lance B. Eliot

 "   .... The thing is, a lot of the autonomous tech will also end up in human-driven cars too. This might seem surprising. Many assume that the tech devised to aid AI-based autonomous driving would solely be used by autonomous driving vehicles. But it turns out that there are numerous handy ways in which the tech derived for self-driving cars can be leveraged for human-driven vehicles.   

Not every piece of tech that goes into a self-driving car is necessarily going to find its way into a human-driven vehicle. Some contraptions will; some will not. The tech that gets crossed over into a human-driven car is bound to have other aspects included, recasting the tech and making it more readily accessible or usable by humans versus when the target “user” being an AI driving system (note that I’ve put the word “user” into quotes since I don’t want to suggest or imply that today’s AI is somehow human-like). 

The overarching question is this: Can the advanced tech devised for self-driving cars be leveraged for use in human-driven cars on a crossover or crisscrossing basis?   

Well, I’ve already tipped my hand and propounded my answer, which is a resounding yes, albeit the seemingly outsized affirmation is tempered with the strident precaution to mindfully undertake any such crossovers.    .... " 

Early Warning System for Cars

Learning from real-world case where Humans have taken over. 

AI Recognizes Potentially Critical traffic situations Seven Seconds in Advance

New early warning system for self-driving cars

A team of researchers at the Technical University of Munich (TUM) has developed a new early warning system for vehicles that uses artificial intelligence to learn from thousands of real traffic situations. A study of the system was carried out in cooperation with the BMW Group. The results show that, if used in today’s self-driving vehicles, it can warn seven seconds in advance against potentially critical situations that the cars cannot handle alone – with over 85% accuracy.

To make self-driving cars safe in the future, development efforts often rely on sophisticated models aimed at giving cars the ability to analyze the behavior of all traffic participants. But what happens if the models are not yet capable of handling some complex or unforeseen situations?

A team working with Prof. Eckehard Steinbach, who holds the Chair of Media Technology and is a member of the Board of Directors of the Munich School of Robotics and Machine Intelligence (MSRM) at TUM, is taking a new approach. Thanks to artificial intelligence (AI), their system can learn from past situations where self-driving test vehicles were pushed to their limits in real-world road traffic. Those are situations where a human driver takes over – either because the car signals the need for intervention or because the driver decides to intervene for safety reasons.  ... " 

Explaining AI in Context

Not to say I am using the connection with autonomous cars, but am very much into how we explain with AI in all sorts of contexts.    We built some AI systems in our early days that could have used very precise explanatory capabilities, in order to keep its credibility over many maintenance cycles,  but it could only be crudely done at the time.   Here a nice case study in the here and now.  

The Rocky Road Toward Explainable AI (XAI) For AI Autonomous Cars 

The AI systems doing the piloting of autonomous cars will need to provide explanations to curious passengers about the route being undertaken    By Lance Eliot, the AI Trends Insider  

Our lives are filled with explanations. You go to see your primary physician due to a sore shoulder. The doctor tells you to rest your arm and avoid any heavy lifting. In addition, a prescription is given. You immediately wonder why you would need to take medication and also are undoubtedly interested in knowing what the medical diagnosis and overall prognosis are. 

So, you ask for an explanation. 

In a sense, you have just opened a bit of Pandora’s box, at least in regard to the nature of the explanation that you might get. For example, the medical doctor could rattle a lengthy and jargon-filled indication of shoulder anatomy and dive deeply into the chemical properties of the medication that has been prescribed. That’s probably not the explanation you were seeking.   

It used to be that physicians did not expect patients to ask for explanations. Whatever was said by the doctor was considered sacrosanct. The very nerve of asking for an explanation was tantamount to questioning the veracity of a revered medical opinion. Some doctors would gruffly tell you to simply do as they have instructed (no questions permitted) or might utter something rather insipid like your shoulder needs help and this is the best course of action. Period, end of story.   

Nowadays, medical doctors are aware of the need for viable explanations. There is specialized “bedside” training that takes place in medical schools. Hospitals have their own in-house courses. upcoming medical doctors are graded on how they interact with patients. And so on.   

Though that certainly has opened the door toward improved interaction with patients, it does not necessarily completely solve the explanations issue. 

Knowing how to best provide an explanation is both art and science. You need to consider that there is the explainer that will be providing the explanation, and there is a person that will be the recipient of the explanation.    ... '

Argo LiDAR has 400 Meter Range

How much does it add to effectiveness in context? 

 Argo AI says its latest LiDAR sensor has a 400-meter range

The tech could bolster Ford and Volkswagen's self-driving ambitions. In Engadget, Kris Holt @krisholt, May 4th, 2021

Argo AI has made some waves in the autonomous vehicle space over the last few years, with investors Volkswagen and Ford working on cars that use its self-driving tech. The company suggests it's taken a significant step towards bringing autonomous vehicles to roads. Argo created a LiDAR sensor that's said to have a range of 400 meters, which it believes it the longest range of any current LiDAR sensor.   .. "

VW Will Design its own Self-Driving Chips

 Perhaps expected, adds some control, link to driving data

VW will design its own chips for self-driving cars in Engadget

It's borrowing its strategy from Apple and Tesla.

Volkswagen won't settle for off-the-shelf computing power with its self-driving cars. As Reuters (via Autoblog) reports, company chief Herbert Diess told Handelsblatt in an interview that VW will design its own high-performance chips for autonomous vehicles. It was a matter of eking out the best possible hardware, Diess said — much like Apple and Tesla, the move would give VW "higher competence" in defining its processors.  ... ' 

UK Allowing ALKS , Self Driving this Year

 Things continue to move in this space, though lots of issues remain.    But note this appears to be only ALKS (Automateed Lane Keeping) only.  

'Self-driving' cars to be allowed on UK roads this year  By Cristina Criddle In the BBC

"Self-driving" vehicles could be allowed on UK roads by the end of this year, the government has said. The Department for Transport said automated lane-keeping systems (ALKS) would be the first type of hands-free driving legalised.

The technology controls the position and speed of a car in a single lane and it will be limited to 37mph (60km/h)  But insurers have warned the government's definition of ALKS as "self-driving" is misleading.  Previously, the government had said these new laws would be in place by spring this year and told the BBC there was no delay in its suggested timeframes.

Hands-free

Following a consultation last year, the government has now said that vehicles with ALKS technology can be legally defined as self-driving, “as long as they receive GB type approval and that there is no evidence to challenge the vehicle’s ability to self-drive.” The government confirmed that drivers will not be required to monitor the road or keep their hands on the wheel when the vehicle is driving itself.

But the driver will need to stay alert and be able take over when requested by the system within 10 seconds. ..... " 

Wal-Mart Invests in Self-Driving

Somewhat unusual, but Wal-Mart is making a considerable play here.  Cruise is only indicating a self driving Taxi for now.    Possibilities for delivery?

Walmart invests in self-driving startup Cruise

Cruise says it's about two years from commercial launch. We've heard that before.

 By Timothy B. Lee  in ArsTechnica

Walmart invests in self-driving startup Cruise

Walmart is investing in self-driving startup Cruise as part of a massive $2.75 billion investment round in the company—an expansion of the $2 billion round announced in January. That original announcement featured three other big names: GM, Honda, and Microsoft.

Cruise was originally an independent startup but was acquired by GM in 2016. GM has poured billions into the company and has increasingly sought additional financial support from outside investors.

Recently, Cruise has been signaling that it is just a couple of years away from launching its technology commercially. Earlier this week, Cruise announced that it would launch a self-driving taxi service in Dubai in 2023. Cruise CEO Dan Ammann then told Bloomberg that he expected to launch a commercial service in San Francisco prior to launching in Dubai.  ..."

Dubai RoboTaxi Service: GM's Cruise Origin

More self driving, here a taxi service.  More data and experience with the customers and concept.

GM's Cruise will operate a robotaxi service in Dubai  in Engadget

It's the first time the Cruise Origin will serve outside of the US.

Want to hail a Cruise robotaxi as soon as you can? You might want to book a trip to the UAE. The GM-backed brand has struck a deal to operate self-driving taxis and ride-hailing services in Dubai in 2023. It will be Cruise's first commercial self-driving service with its Origin vehicles outside of the US, Dubai said. Only a handful of the autonomous shuttles will be available at first, but the city plans to have as many as 4,000 Origins on streets by 2030.  ... "

Early Warning Systems for Self Driving

Recognizing situations for warnings. Classic AI application.

Early Warning System for Self-Driving Cars

Technical University of Munich (Germany),  March 30, 2021

An early warning system for self-driving vehicles developed by researchers at Germany's Technical University of Munich (TUM) leverages artificial intelligence (AI) to learn from real traffic situations. During tests on public roads, the researchers identified about 2,500 situations that required driver intervention; they found the system issued warnings about potentially critical situations seven seconds in advance with more than 85% accuracy. Using a recurrent neural network, the system recognizes patterns in the data collected by sensors and cameras and will warn drivers if it identifies a situation the control system has had difficulty handling in the past. TUM's Eckehard Steinbach said, "We limit ourselves to the data based on what actually happens and look for patterns. In this way, the AI discovers potentially critical situations that models may not be capable of recognizing, or have yet to discover."  .. '