How Analytics Makes The Drive Better


If there was ever a battle cry for hiring analytics professionals, it would certainly come from the researchers behind autonomous vehicles, as the resulting data generates tons of data that need inspection.

Credit: iStock
Credit: iStock

I learned of the challenges that can develop from a presentation on data and autonomous vehicles, called Smart Cars: Perception-Driven Autonomous Vehicles, hosted by the Chicago City Data Group, a casual gathering led by the Microsoft Chicago team. The group invited Matthew Walter, a former PhD and Research Scientist at the MIT’s Artificial Intelligence Lab and now an assistant professor at Toyota Technological Institute, an independent research team on the University of Chicago campus.

Walter’s presentation covered how the MIT entry into the Defense Advanced Research Projects Agency (DARPA) Urban Challenge came to be. Driven by the Iraq war, the military sought to reduce ground combat troop death from attacks while driving supplies in urban area. Thus began the DARPA Urban Challenge, a university research competition to create autonomous vehicles that could carry equipment in difficult urban environments.

The autonomous car Walter developed with the team finished in the Top 5 in the 2007 competition, which put Walter on the development path for autonomous vehicles. I recorded his Chicago City Data Group presentation; You can view the hour long presentation here.

The competition faced dynamic obstacles and decisions to pass cars, all while obeying traffic laws and staying below 30 miles per hour. Each team received two files that outlined the topology of the roads and a list of places to visit.

The competing vehicles had to incorporate technology that addressed three general questions while in a given environment:

  • Where is the road?
  • What objects are static?
  • How are other vehicles recognized?


What it involves
Walter explained how care was taken to equip the vehicle, a Land Rover LR3. The team chose to equip it with five cameras for lane detection, 16 radars, a custom built Velodyne 3D sensor, and 12 SICK sensors.

A computer rig was installed in the trunk, complete with 40 GB of RAM and Ethernet to crunch the real time sensor data locally.

Furthermore, a 6kW generator was added, as was a 2kW air conditioner on the roof to keep the computing equipment cool. Drive by wire also was installed.

Walter explained the team chose to “overmeasure” with having multiple sensors, saying, "It was better to have data and not need it rather than need data that does not exist.” Positioning a sensor has to be planned based the sensor's range and field of view. The SICK sensors were positioned at different levels to view ground obstacles, such as distinguishing a grade in the road from a speed bump or curb. Walter showed a real-time scan, which displays data by height -- blue being close to the ground and red to interpret tall objects in the environment.

Much of debate centered on how objects were interpreted. “Sensor noise can suggest something is moving, but it is hard to distinguish,” Walter reveals. “So we had this threshold for determining moving objects, nothing slower than 1.5 meters/sec.”

The amount of data generated from these studies has created an opportunity for professionals to develop better environmental models. This means real-time data from autonomous vehicles offer an opportunity to explore environmental uncertainties in predictive analytics. Imagine machine learning techniques that lead to better distinguishing other nearby vehicles from obstacles, and their intent.

“Our machine involved little machine learning, but we have 1.4 million miles driven,” according to Walter. “That’s about 50GB per second of data.”


But not so fast
Major concerns remain about sensor guidance for autonomous vehicles. The first most significant is all-weather capability. Walter noted in his presentation that sensors still rely on dry conditions and have not mastered reading roads in poor weather conditions such as heavy snow.

In fact, safety advocates have asked the National Highway and Traffic Safety Administration to consider a more gradual implementation schedule of autonomous vehicle tech than one announced in January.

Another concern for experts is the large cost for improving infrastructure. Harvard Business Review outlined how e-commerce is impacted by the poor investment of road improvement in the US. The upgrade backlog is estimated at a mind-numbing $3.6 trillion.

Any investment in infrastructure should also extend to budgets that establish advanced predictive analytics. There’s already talk of a smart environment being built. MIT released a study on a smart city traffic grid, built to guide urban traffic by sensors rather than traffic signals.

Analysis can guide a framework for best practice parameters. The ultimate results are not just better sensors and better algorithms, but a better technology stack that can keep the public safe in the transition to an autonomous vehicular society.

The march of the autonomous cars is coming, and they must bring a renewed value in analytics along for the ride.

Pierre DeBois, Founder, Zimana

Pierre DeBois is the founder of Zimana, a small business analytics consultancy that reviews data from Web analytics and social media dashboard solutions, then provides recommendations and Web development action that improves marketing strategy and business profitability. He has conducted analysis for various small businesses and has also provided his business and engineering acumen at various corporations such as Ford Motor Co. He writes analytics articles for AllBusiness.com and Pitney Bowes Smart Essentials and contributes business book reviews for Small Business Trends. Pierre looks forward to providing All Analytics readers tips and insights tailored to small businesses as well as new insights from Web analytics practitioners around the world.

Analytics Career Journey: Making Business, Lives Better

Technology skills can take you through multiple careers that make lives, businesses, and communities better. Here's the story of one such career journey.

How Third Parties Can Hurt Your Marketing Analytics

Are your digital marketers creating gaps in customer privacy? They could be unless they vet tags and third-party app access. Here's how to do the vetting.


Re: Gorillas want to shift liability to consumers
  • 6/2/2016 12:18:45 PM
NO RATINGS

More to the point, an actual flaw in the actual product itself (and we're not talking negligent consideration of AI vs. human intelligence and when each should be applied) that results in damage could bring on product liability lawsuits -- which do not require a showing of neligence.

Re: Gorillas want to shift liability to consumers
  • 5/13/2016 3:45:24 PM
NO RATINGS

..

Jim writes


For drivers making the shift to autonomous cars there is unlikely to be that type of understanding or acceptance of risk, particularly if we reach the point that autonomous vehicle become required, or even if driver of a car with controls is struck by a driverless car. If that autonomous car has a flaw in the braking or nav system the manufacturer should be eligible for liability. Whether the owner of that vehicle did proper maintenance should be something that could be argued in court (just like it would be today with a car with a driver).


 

I continue to anticipate that the coming proliferation of driverless cars will open a Pandora's box of liability mayhem. Basically I expect that a plaintiff suffering harm (injury, death, property damage, whatever) from a driverless car is going to claim:

• If the car was under robot control, it should have been under human control

• If the car was under human control, it should have been under robot control

In either case, one can expect that the driver, the car manufacturer, and probably the robotic software developer will all be targets of litigation in almost every incident. Can the court system handle a new tsunami of lawsuits? This will be fascinating...

 

Re: Gorillas want to shift liability to consumers
  • 5/12/2016 11:48:07 AM
NO RATINGS

Good point about the autonomous car compensating for it's own failures, including failures that we might notice today as we drive. In addition, even if something like failing brakes can be noticed in that autonomous car the "operator" who is spending their commute on the phone or watching a video won't be paying a attention.

Re: Gorillas want to shift liability to consumers
  • 5/12/2016 8:38:27 AM
NO RATINGS

@James: Your comment raises an interesting point.  When you're driving a car yourself, you can sometimes "feel" when something is wrong (when the brakes are "less squishy," for example).  Plus, a well-programmed automated car may begin to compensate for its own faults (like the brakes reacting more slowly/taking a longer time).  With self-driving cars, you may have no idea that there is a serious problem with your car until it's too late.

Re: Gorillas want to shift liability to consumers
  • 5/12/2016 8:35:31 AM
NO RATINGS

@Lyndon: Well, that's the American Dream, right?  With enough money, you can do just about anything.  ;)

Re: Gorillas want to shift liability to consumers
  • 5/10/2016 4:21:25 PM
NO RATINGS

@kq4ym. Of course aviation and maritime play by their own rules and those who get licensed understand those rules. For drivers making the shift to autonomous cars there is unlikely to be that type of understanding or acceptance of risk, particularly if we reach the point that autonomous vehicle become required, or even if driver of a car with controls is struck by a driverless car. If that autonomous car has a flaw in the braking or nav system the manufacturer should be eligible for liability. Whether the owner of that vehicle did proper maintenance should be something that could be argued in court (just like it would be today with a car with a driver).

Re: Gorillas want to shift liability to consumers
  • 5/10/2016 1:40:44 PM
NO RATINGS

In the general aviation business it's always been the pilot who generally is at fault in any accident, not matter what automation or auto-pilot equipment is aboard. And the aircraft manufacturers are now not held liable for any manufacturing defects on older aircraft. That might be an interesting twist if auto manufacturers are held harmless for autos built before a certain year under the premise that are are not as safe as newer models and can't control the repairability and maintenance of older vehicles.

Re: Gorillas want to shift liability to consumers
  • 5/10/2016 10:23:24 AM
NO RATINGS

I hope the citizenry and Congress are skeptical of any attempt by self-driving car manufacturers and their suppliers (nav systems, etc.) to exempt them from liability in the case of any (inevitable) death or injury.

The "not my job" attitude when it comes to safety is a bad way to drive technology forward. Those car makers can't be held liable for everything that happens on the road, but there are going to be situations where they are held responsible. I don't think the public or the courts will stand for such an exemption. We're already seeing judges "rethinking" the exemption that gun makers were given for the use of guns in crime.

An approach that says "use this at your own risk" might be fine for recreational equipment like boats and ATVs, but not for something that people use every day to go about their normal lives. This is a case where the consumer has to trust the manufacturer, and if that trust is violated by negligence, the manufacturer should pay.

Gorillas want to shift liability to consumers
  • 5/9/2016 4:48:38 PM
NO RATINGS

..

Joe writes


Let's also bear in mind that we can ultimately trust automated drivers no more than human drivers for our livery purposes.  There are many unscrupulous taxi/Uber/Lyft/etc. drivers who will "take us for a ride" by going a long, circuitous route with more traffic.  Automated drivers could be programmed to do that as well ....


 

Speaking of the "sharing economy" taxi companies Uber/Lyft as well as robot car developers, there may be reason for even broader suspicion of where all these guys are going in terms of influencing official policies in regard to driverless car technology.

Some of this is revealed in an April 26th article by the British paper/website Guardian, titled Uber, Google and others form self-driving car lobby to shape US policy.

According to this report, Google, Uber, Lyft, Ford, and Volvo, "all of which are working on self-driving car technology, will lobby as the Self-Driving Coalition for Safer Streets to bring autonomous vehicles to the road across the US." OK, but it goes on to reveal that one of their central policy targets is to shift liability away from the big companies (i.e., the technology developers) and more onto individual vehicle owners. Here are some key excerpts from the article:


Tech companies making self-driving cars could become better protected under the law than those car's owners, experts warn, as the announcement came of a powerful new coalition of automakers and big tech companies forming to take on US government regulations around self-driving vehicles.

Heading it up will be David Strickland, the former administrator of the National Highway Traffic Administration, the same group he will now be working to influence. ...

The first task for the lobbying group will be just rolling out self-driving cars.

But the liability issues will be thorny. A powerful corporate lobbying force may pose a new challenge for personal injury lawyers, who are already wary of the technology, while some safety researchers and accident lawyers worry that the lobbying group could unfairly protect tech companies and app makers over their human car owners.

"I'm worried a lobbying group would try to shield manufacturers and app designers over drivers," said Daniel Vega, an accident and personal injury lawyer based in San Francisco. "When these programs fail, who's responsible?"


 

The Guardian article also highlights the increased risk factors associated with the emerging self-driving technology.


Statistician Susan Paddock said the only way to get self-driving cars out on the road was if consumers become comfortable with a great deal of uncertainty.

"It's very challenging to test drive these vehicles as far and as long as they need to be in order to statistically know their performance," Pollock said. "Even if autonomous vehicle fleets are driven 10m miles, one still would not be able to draw statistical conclusions about safety and reliability."

"Uncertainty remains," she added. "I don't know how the general public will respond to it."


 

So basically, while self-driving cars may offer the potential for higher safety, they also bring an awful lot of new additional risk into the mobility environment. This may make the general public kind of uncomfortable, but the big tech developers seem to be intent on sewing up the policy package to ensure liability exposure is resolved more in their favor.

 

Re: Data analysts to the rescue?
  • 5/9/2016 12:29:12 PM
NO RATINGS

Or maybe throw a Michigan road in there somewhere to make the bumpy road a complete set.

Page 1 / 6   >   >>
INFORMATION RESOURCES
ANALYTICS IN ACTION
CARTERTOONS
VIEW ALL +
QUICK POLL
VIEW ALL +