Drawback of Machine Learning and Self-Driving Cars

Good piece by Lance Eliot.

Strict Literal Interpretation Is A Hardheaded Drawback Of Machine Learning And Likewise Bad For AI Self-Driving Cars

Lance Eliot Contributor  in Fortune.

ON Transportation

Dr. Lance B. Eliot is a world-renowned expert on Artificial Intelligence (AI) and Machine Learning (ML).

Includes an audio transcript at the link that makes the interesting case that cars taught by machine learning and used in contextually confusing environments make mistakes.     Yes they do, as humans do.

Tracking Human Mobility

A somewhat unusual look at different kinds of mobility and how it relates to pandemic challenges.

App Tracks Human Mobility, COVID-19

University of Miami, Deserae E. del Campo,  June 14, 2021

The COVID-19 vs. Human Mobility Web application can map the coronavirus pandemic's global impact on human movement. The University of Miami's Shouraseni Sen Roy and Christopher Chapin based the interactive app on Apple Maps' dataset on human movement through walking, driving, and public transit; Oxford University's COVID-19 Government Response Tracker, detailing government policies deployed during the pandemic; and Johns Hopkins University's compiled global cases of COVID-19. Users can choose a country, or a U.S. state or county, and compare human mobility and coronavirus cases over time, as well as data on government policies associated with COVID-19's spread. Sen Roy said, "Understanding historic mobility patterns, both under normal circumstances and in response to extreme events like a pandemic or a natural disaster, is surely needed for policymakers to make informed decisions regarding transportation systems and more.”

Electrified Urban Transport

Recall we experimented with Segways in our innovation center,  and observed them being used in locations like the grocery store 'Jungle Jims'.      Here more about typical  human transportation. But do consider that we now expect to be able to carry things with us as well.

SEGWAYS, SCOOTERS, AND SKATEBOARDS: THE NEW ELECTRIFIED URBAN TRANSPORTATION  from Boundmotor.com

March 31, 2021

When Carl Benz applied for a patent for his “vehicle powered by a gas engine” in January 1886, he ignited what would later become a revolution in transportation. Over the centuries, improvements would be made to Benz’s idea, which ultimately led to making privately owned cars and large-scale projects like buses and subway systems central to urban mobility. Popular as they are, the traditional modes of public transportation like privately owned cars, public buses, and subways have their challenges. They are expensive to establish and maintain, result in gridlocks, pollution, and a shortage of parking in most major cities. Within the context of the challenges related to traditional forms of mass transportation, the Segway’s introduction in 2001 started a trend of replacing large-scale public infrastructure with small, one-person electric vehicles. McKinsey & Company, the management consultancy firm, calls this type of transportation micromobility. This article looks at the evolution of one-person electric modes of transport and how they have impacted urban transportation. We start by focusing on the urban transport challenges that have made one-person electric vehicles a growing urban transit option. We then look into the history of these forms of transport and some safety tips for people using them.

CHALLENGES OF TRADITIONAL PUBLIC AND PRIVATE URBAN TRANSPORTATION

The challenges associated with extensive public transportation projects are well documented. An article published by Australia’s University of Melbourne puts these challenges into perspective. It says, “Chronic losses of life on roadways, dangerous deterioration in air quality, and worldwide accumulation of atmospheric carbon can no longer resist the challenges of an increased population and its urbanization.” These challenges are partly responsible for the increasing trend where people prefer to use one-person electric vehicles.  ... "    (Much more) 

Predicting Railway Delays

 Interesting application.  Consider data availability, accuracy and variability of prediction.

Predicting British railway delays using artificial intelligence  by University of Illinois at Urbana-Champaign

Over the past 20 years, the number of passengers traveling on British train networks has almost doubled to 1.7 billion annually. With numbers like that it's clear how much people rely on rail service in Great Britain, and how many disgruntled patrons there would be when delays occur. A recent study from the University of Illinois Urbana-Champaign used real British Railway data and an artificial intelligence model to improve the ability to predict delays in railway networks.

"We wanted to explore this problem using our experience with graph neural networks," said Huy Tran, an aerospace engineering faculty member at UIUC. "These are a specific class of artificial intelligence models that focus on data modeled as a graph, where a set of nodes are connected by edges."  ... " 

Hitchhiking Drones

And had mentioned this novel idea as well in a recent post.  Also covered in considerable detail in IEEE Spectrum.  As noted will require some considerable design changes for public Transportation.

Delivery Drones Could Hitchhike on Public Transit to Massively Expand Their Range.  Riding on the top of public buses could make drone delivery much more efficient .... "

By Evan Ackerman in IEEE Spectrum.  ... 

Delivery Drones will be taking the Bus?

Clever proposal for integrating transport, lowering energy costs.  Adds complexity to bus capabilities.

Stanford Lab Envisions Delivery Drones That Save Energy by Taking the Bus
VentureBeat
By Khari Johnson in ACM

In an effort to redesign urban package delivery, researchers in Stanford University's Intelligent Systems Laboratory and Autonomous Systems Lab developed a methodology that allows delivery drones to access buses or trams, which could reduce traffic congestion and energy consumption while allowing the drones to travel farther. The artificial intelligence network underlying this system, which can accommodate up to 200 drones delivering up to 5,000 packages, was designed for cities with up to 8,000 stops. The approach is aimed at minimizing the time required to complete a delivery, according to the researchers, who added that it “can achieve significant commercial benefits and social impact.”  ... ' 

Transportation Updates

Bottom line, lots of work yet to do in completely autonomous cars.  The number of miles driven in CA seems impressive.

Some excerpts from Wired Transportation.  Worth subscribing to, links to full articles.

At some points three or so years ago, it looked like self-driving cars might appear at your or my door any moment. But now it’s clear the journey to robot cars will be more of a slog. Last week, we gained insight into some important steps necessary before the vehicles really hit the road. For one, the federal government needs to figure out its approach to regulating autonomous vehicles, and to the advanced driver-assistance tech that precedes it. A federal safety board criticized regulators for the approach they’re taking to Tesla Autopilot—even as those same regulators shut down passenger trips on a kind of autonomous shuttle. Companies also need to reach their own internal self-driving benchmarks. We got some insight into how they’re doing that.

Plus, the Air Force gets into flying cars, and Uber gets into ads. Let’s get you caught up.
Headlines .... 

Advertisers should love Uber’s newest plan to make money: placing billboards on top of its drivers’ cars.

Thanks to data released last week, we now know that robot cars in autonomous mode drove almost 2.9 million miles on public California roads last year.  .... "

China increases Biometric Public Transport Scanning

If does seem that while we fret about the possible misuses of tracking data from such passive biometric scanning, other countries are  seeing the efficiency value.  Note the cautious CYA phrase below 'Perhaps too high tech'.

China speeds up its subway with palm scanners and facial recognition in DigitalTrends

While New York attempts to update its public transportation system to run on time and use mobile tickets, commuters over in Beijing are looking at a range of high tech upgrades. In fact, perhaps too high tech. As per a China Daily report, the Chinese capital of Beijing is now considering the introduction of “bio-recognition technology” to its subway station. This technology would include palm scanners and facial recognition scanners, and would purportedly help increase efficiency and decrease gridlock in key stations during rush hour.  ... " 

Charging Moving Vehicles

In Spectrum IEEE

Wireless Power for Moving Electric Vehicles Closer to Reality     By Charles Q. Choi

 Two men stand in front of and beneath a pair of large white wheels trimmed with copper foil. Electronic equipment hangs from the bottom of the wheels and more equipment is on a table behind one wheel.

Wireless charging of moving electric vehicles is one step closer to hitting the road, Stanford University researchers say. Such technology could also help charge mobile devices, medical implants, and factory robots, the scientists add.

Wireless charging via a technique known as magnetic induction is currently used to power electric toothbrushes, power tools, robotic vacuum cleaners, medical implants, and other devices. Inductive charging depends on at least two coils—one in the power transmitter, and one in the power receiver. When the transmitter coil is energized, it generates an electromagnetic field that can transfer energy to the receiver coil. ... " 

Cisco: How Digital is Disrupting Transportation

How Digital is Disrupting Transportation  (13 page PDF)

Context for report

Cisco developed this paper to create a starting point for discussions about the digitisation of transportation, and its downstream impact on cities, regions and economies. The report comprises a range of inputs, including discussions with global experts such as those who attended the Intelligent Transport Systems World Congress in October 2016, as well as contemporary research and insights. Cisco is a global technology company focused on helping organisations prepare for and respond to the impact of digital technologies. By investing in thought leadership, Cisco intends to contribute to the debate and potential solutions, rather than being a passive observer

Purpose of this report

Governments, institutions and companies are experiencing immense disruption. Business and engagement models are being transformed by rising citizen and customer expectations, and fueled by mass connectivity. The transportation sector is poised to move from `human scale’ to machine scale’,

creating a wave of innovation propelled by the ability of humans to connect to machines, or for machines to connect with other machines. The transportation industry is projected to experience more change than most sectors, in large part because it offers solutions to some of the world’s most acute challenges: environmental sustainability and rapid urbanisation.

Digital transportation solutions are forecast to improve safety, energy and operational efficiency, and performance in mass transit, rail, freight and logistics, aviation and road transit. The purpose of this report is to investigate emerging trends in transportation. It is intended to stimulate thought, provoke discussion and raise awareness of the opportunities presented by digital and how to capitalise on those opportunities. The report concludes with the role of digital infrastructure in creating a robust, secure and future-proofed platform for innovation. ... " 

Robot has a Tail

In IEEE Spectrum:  Robot uses actuator tail for transport.

Model Based Machine Learning

Thinking of the possibilities for analyzing supply chain problems.   Bayesian approaches.   Has anyone examined?  This shows some technical examples using R.    Via DominoDataLab.

This guest post was written by Daniel Emaasit, a Ph.D Student of Transportation Engineering at the University of Nevada, Las Vegas. Daniel’s research interests include the development of probabilistic machine learning methods for high-dimensional data, with applications to urban mobility, transport planning, highway safety, & traffic operations. ....  

This blog post follows my journey from traditional statistical modeling to Machine Learning (ML) and introduces a new paradigm of ML called Model-Based Machine Learning (Bishop, 2013). Model-Based Machine Learning may be of particular interest to statisticians, engineers, or related professionals looking to implement machine learning in their research or practice.

During my Masters in Transportation Engineering (2011-2013), I used traditional statistical modeling in my research to study transportation related problems such as highway crashes. When I started my PhD, I wanted to explore using machine learning because of the powerful academic and industry use cases I had read about. In particular, I wanted to develop methods that learned how people travel within cities, allowing for better planning of transportation infrastructure.  ... " 

Driver Assistance vs Autopilots

Interesting story of varying language being used in describing the idea of 'driver assistance' when using and selling the Tesla.   Our language has to adapt to the physical consequences  And the legal consequences.  In ArsTechnica.

Nissan Lab on the Future of Transportation

In Knowledge@Wharton.   A podcast and transcribed text.

How Nissan Is Preparing for a Future of Self-driving Cars
Nissan Future Lab's Megan Neese discusses a future of transportation that's autonomous, electrified and connected.

In a future where self-driving vehicles may be the norm, will fewer people want to buy a car? Japanese automaker Nissan is looking ahead to this and other scenarios in the future of transportation — and it is doing research on products to position itself well going forward.

Knowledge@Wharton caught up with Megan Neese, senior manager of the Nissan Future Lab, to talk about her group’s goals and projects. She also recently spoke at the ‘Digital Disruption and Empowered End-users’ conference hosted by Wharton’s Mack Institute for Innovation Management. ... "

Watson Driverless Bus

A intriguing combination of Technical trends.  Augmenting ...
Olli is an IBM Watson-powered driverless electric bus.   At least you can ask where you are going ....  The 3D-printed vehicle can seat 12 passengers. .... by Mariella Moon , @mariella_moon

Update on Hyperloop

Update:  High speed, maglev, in-vacuum transportation of people and cargo in relatively narrow pipes. People stacked in a recumbent style of seat.  Windowless, but perhaps with virtual reality displays.

Impressive and futuristic  effort, probably doable in the longer term. Though I wonder about drilling through mountains, earthquakes, security, maintaining near vacuums and more.

This is also most useful at scale for long trips, where the infrastructure needs will be enormous.  And in  the short term, the slower, but very adaptable, competition from self driving vehicles.  I do like the idea of adding cargo potential. Unlike the Mars trip, here I would readily take a test trip.  Invite me. Following.

Analyzing Commuting Habits

In Datanami:  HP and Ford gather data, possible application to commuting efficiency improvement.

UK Virtual Reality Lab for Transport

In Engadget: Don't quite understand the application, but intriguing.  In general we found that VR applications were most useful when they were closely connected to real, or imagined realistic spaces. In other words when they were really augmented reality applications.  When they were navigating in purely abstract spaces the user lost the useful sense of immersion.

Sony Drones for Enterprises

In CIO,   Mobile in three dimensions. Expect a further dimensionalizing of data acquisition. " ... Drones are officially taking over. Not content to cede the market for autonomous vehicles to Amazon and Google, Sony announced today that it is launching a joint venture to design and build drones for enterprise clients.  ... The project is being led by Sony Mobile Communications, Sony’s mobile phone and device subsidiary, in collaboration with ZMP, another Japanese company focused on automotive and robotic design. Sony said it would be taking a controlling stake in the venture, with a 50.005 percent share.

The new company, which will be called Aerosense, will be incorporated next month with 200 million yen ($1.6 million). Aerosense will focus on enterprise solutions using autonomous unmanned aerial vehicles for image capture combined with cloud Relevant Products/Services-based data Relevant Products/Services processing, according to a blog post by Sony Mobile. ... " 

Honda Robotic Chair

Saw this demonstrated in a retail setting.  The Honda Uni-Cub.  But apparently still not available for purchase.  In Engadget.    An example of a one wheeled personal transportation device, but with a seat rather than requiring upright balance. Many pictures at the sites.