Advanced Mobility Institute Articles

Florida Poly publishes extensive database of autonomous vehicle test tracks

By: Dr. Rahul Razdan
With the active work ongoing with test tracks and proving grounds,  we thought building a database of this information would be useful to the broader Autonomous Vehicle community.  The database can be accessed with read privileges here.

Florida Poly holds AV CEO summit

Autonomous vehicle (AV) technology has the potential to make as significant an impact as the internal combustion engine had for the industrial revolution. AV technology will not only impact the passenger car market, but Florida industries ranging from public transportation to planned communities.  With this in mind, on Oct. 27, 2017[KPM1] , Florida Polytechnic University held a CEO conference on ways Florida Poly can influence and grow [KPM2] four Florida industries absorb and build differentiation based on this disruptive technology. This invitation only event drew over 30 representatives from four sectors — Agriculture, Freight/Logistics, Planned Communities and Public Transportation —to share problems, challenges, opportunities and ideas.

Florida Poly President Dr. Randy K. Avent kicked off the event with a brief overview of the state of the University and its commitment to the application of STEM education in the economic development of the region.  He then introduced the plenary session and keynote speaker, Dianne Gutierrez-Scaccetti, executive director and CEO of Florida’s Turnpike Enterprise, the developer of SUNTRAX. [link to slides].

The session’s participants then moved into break-out sessions.  Each session was chaired by a professional in the sector: Rick Montney, CEO and president of Pro Pak Software in the Agriculture Track; Ken Armstrong, CEO and president of the Florida Trucking Association in the Freight/Logistics Track; Bud Strang, CEO of Six/Ten Corporation in the Planned Communities Track; and Ananth Prasad senior vice president, HNTB, in the Public Transportation Track.  Participating faculty members included Dr. Dean Bushey, Dr. Mustapha Akbas, Dr. Harish Chintakunta, Dr. Shahram Taj and Dr. Melissa Morris.

The critical takeaways from the meeting were:

  1. AV-related technologies are influencing economic developments in each track. For[KPM3]  tracks like public transportation,  the timeframes are immediate, and for others such as planned communities, the impact is more likely in the future.
  2. Florida Poly has a critical role in becoming a repository of unbiased knowledge that Florida industries can use, and as a networking hub for industry as they grapple with the challenges of this technology.  There was also some discussion on funding a center at Florida Poly to execute this function.

The conclusion was for Florida Poly to develop a proposal for consideration by the group.

Florida Poly president testifies at US senate on autonomous vehicle safety

Oral Testimony of Dr. Randy Avent. Senate Committee on Commerce, Science and Transportation Field Hearing. January 24, 2018, 10:00 a.m. Walter E. Washington Convention Center Washington, D.C.

Mr. Chairman, ranking member Senator Nelson and members of the subcommittee, thank you for the opportunity to address you today on this very important topic.

As many of you know the vision of driverless cars has been around for well over 50 years, but little progress was made until 2004 when DARPA created a prized competition called the DARPA Grand Challenge.  Since then, there has been an exponential growth in the underlying AV technology that mirrors the development trajectories in other disruptive markets like computing, networking and DNA sequencing.

Today I’d like to briefly touch on three dimensions of Connected and Autonomous Vehicles: market impact, technical and regulatory challenges and the potential role of the federal government.

Numerous papers abound outlining the promises of autonomous vehicles.  Developed and implemented correctly, the primary advantage of autonomous vehicles centers on significantly lowering driver related deaths.  Last year alone, there were over 40K fatalities in the US at a cost of over $410B – and more than 90% of those were due to human error.  But there are many secondary advantages that are also significantly important.  For instance, Autonomous Vehicles can improve access for the elderly, children and poor and can make public transportation more effective by solving the “last mile” problem.  It can significantly increase the utilization of automobiles, which is less than 5% now, and with higher utilization of fewer cars, the capacity of our transportation infrastructure would naturally rise.  Beyond the transportation sector impact, core technologies underlying autonomy will impact other large markets such as agriculture, logistics, national defense and manufacturing.  In fact, it would be hard to find any technology with a more disruptive impact on both the US and global economy than Connected and Autonomous Vehicles.  Piston powered vehicles driven by people and built by traditional car manufacturers may be soon replaced by interconnected computers on wheels scheduled and controlled by autonomous algorithms developed by IT companies.  US car manufacturers will need to look more like IT companies.  Insurance markets, law enforcement, hotels, real estate, lawyers, auto repair and health care will all be affected, just to name a few.

But while the promise of AV technology is noteworthy, there are still substantial barriers to its widespread adoption.  For one, the AV technology core relies on what I call the “Sensor and Signal Processing chain” and there’s still significant work that needs to be done on the edge cases to improve performance.  A strong regulatory framework is paramount to safety and consumer acceptance, but an overregulated market is likely to stifle innovation and give our global competitors an advantage.  To this end, we need a science-based, data-driven approach to creating policies and legislation that’s modeled after successful verification or certification approaches in other industries. This framework must integrate the full spectrum of testing approaches ranging from digital simulation and hardware-in-the-loop emulation, to closed-circuit and public open road testing in urban areas.  Lastly, as the fundamental technology transitions away from automotive and civil engineering, there will need to be a rapid shift in the transportation industry and their regulatory partners towards computer science, electrical engineering and analytics.

States such as Florida have taken a leadership role in enabling this market.  The federal government can have a very constructive role in enabling this transformative technology through research funding, through safety consortiums that investigate and provide factual data around AV accidents much like the NTSB role in aviation accidents, and through creating quasi-governmental organizations much like the Department of Energy (DOE) and the Department of Defense’s (DoD’s) Federally Funded Research and Development Centers (FFRDCs) and University Affiliated Research Centers (UARCs) that conduct applied research and provide unbiased technology expertise to the government.

Finally, Florida Poly is working with its partners to research solutions to these challenges.  This includes a deep partnership with the Florida Turnpike Enterprise’s world-class AV test track called SunTrax, and a partnership with the Orlando Smart City initiative that provides open road testing in an urban setting.  These two test complexes, combined with Florida Poly’s new Advanced Mobility Institute, is focused on addressing many of these vexing challenges.

Thank you for your time.

Link to written testimony here.

jonathan_and_max_with_cars-516a31aa1155f78272699f190b803732

A “Game-Changer:” Florida Poly’s new course on self-driving cars

Florida has become a hotbed for driverless car technology. The self-driving vehicle is moving from the Jetsons to a road near you, and things are moving fast. At Florida Polytechnic University in Lakeland, students are just starting a brand new class that teaches the basics of building an autonomous vehicle.  More information here.

 

 

DOT announces central Florida (with Florida Poly) as one of ten proving grounds

The U.S. Department of Transportation announced Thursday that Central Florida has been selected to provide a proving ground pilot site to test new automated vehicle technologies. More information here.
suntrax testing center

FDOT announces partnership with Florida Polytechnic University to develop SunTrax test facility

Tallahassee Florida Department of Transportation (FDOT) Secretary Jim Boxold announced a long-term partnership between FDOT and Florida Polytechnic University to construct the new, state-of-the-art transportation technology testing facility, SunTrax. The creation of this facility will establish Florida as a transportation technology leader and create a high-tech hub for the research, development and testing of emerging transportation technologies related to tolling, intelligent transportation systems (ITS) and automated and connected vehicles. For more information visit Florida Trend here.
For more information on Suntrax.

The dangers of inferior simulation for autonomous vehicles

First – it is stellar that folks like Waymo and Uber say they are now using more simulation. That the University of Michigan did a study saying it can be used instead of public shadow driving. And that MCity has said that the use of simulation with data and the Monte Carlo process you can cull the work down by over 99%
For More Information: here.

Autonomous vehicle technology and planned communities

By: Jake Polumbo

A recent article in Realtor Magazine highlights the excitement around the impact AV technology  will have on planned communities.

“Prime real estate will also be unlocked for new home construction. Places once used for parking lots, auto dealerships, and gas stations will become obsolete with self-driving cars. That may free up prime real estate for housing …Builders will be able to get significantly higher density, and consumers will be buying a home where 100 percent of the square footage is livable,” Rick Palacios, Jr. writes in a Sept. 4 article tiitled “How Driverless Cars will reshape housing?” http://realtormag.realtor.org/daily-news/2017/09/05/how-driverless-cars-will-reshape-housing

Closer to home, Disney World in Orlando is planning for self-driving busses from hotels to theme parks. Epcot Center was originally envisioned by Walt Disney as the first “smart city” and will likely stay on the cutting edge of AV technology, especially with the Florida SunTrax facility so close to the park.

In southwest Florida, Babcock Ranch designers are well along in their planning to use AV technology in a solar-powered town using autonomous shuttle runs to grocery stores and shopping centers;  their plan is to enable residents to use apps on their phones to arrange group trips to the mall or single-person stops at the market.  Their ultimate goal is for residents to realize they don’t need to own a car anymore and to treat “mobility as a service.”

https://www.fastcompany.com/40479135/this-solar-powered-town-is-home-to-americas-first-self-driving-shuttle-network

Recent Articles:

11/13/2017: Smart City in Arizona

11/12/2017: Sustainability in the South Shore of Boston

10/10/2017: Babcock Ranch Self Driving Shuttle Network

Florida Poly publishes extensive database of autonomous vehicle test tracks

By Dr. Rahul Razdan

With the active work ongoing with test tracks and proving grounds,  we thought building a database of this information would be useful to the broader Autonomous Vehicle community.  The database can be accessed with read privileges here.

Florida agriculture embraces autonomous vehicle technology

By William Rhey

It’s tempting to overlook agriculture when discussing AV technology. But there are more applications than you might believe. Commercial drones are already in place, using sensors to assess the need for fertilization, irrigation, crop health, crop maturity and productivity potential.  On the horizon are robots capable of monitoring, cultivating and harvesting crops 24/7, with little or no human labor involvement.

In the short term, sensors and automation hold promise for Florida agricultural industries long dependent upon troublesome labor politics and economics.AV-related technology will allow surveying, planting, maintaining and harvesting of crops at levels of efficiency never before seen.

The dozen[KPM6]  C-level executives attending the Executive Summit were audience to a presentation by Gary Wishnaski, president and CEO of Wishnaski Strawberry Farms in Plant City, Florida.  The company grows, harvests, packs and ships strawberries throughout the United States.

Gary noted that in his industry, harvest labor accounts for 33 percent of total costs.  The industry faces problems of a shrinking labor force, high labor costs, political risks and the perishability of its products.  He also pointed out opportunities realized by the increasing speed of processors and advances in GPS and stereo vision technology.  The result the creation of a strawberry industry consortium, consisting of companies that make up 60% of strawberry production in the US – which has established a start-up robotics company and a cost-effective robotic strawberry picker.[KPM7]

Just a few years ago, the conventional wisdom was that such a device could never be developed.  However, advances in sensor sensitivity and data processing speed (Nvidia’s processor crunches 30 gigabytes of data per second), coupled with GPS and “stereo vision” have enabled the creation of a robotic picker that can harvest strawberries day or night.  After three years of testing on rails, the robotic picker is ready to deploy on wheels in strawberry fields this season.  And it is not the only game in town.  Other initiatives, such as a robotic picker developed by Agrobot – are promising to transform the industry.

Benefits to growers include lower harvesting costs, improved harvest quality, energy savings (berries can be picked at night and need less cooling), 30 percent reduced plastic usage and increased yields of at least 10 percent.   The robot can also be used to scout fields for pests and measure more accurate yields. Gary indicated that the biggest barrier to the development of this device has been money and overcoming resistance to the “it can’t be done” mentality.

Florida Poly’s critical role as the connector and enabler of this technology for Florida agriculture was clear.  This is a university located in the center of a vital agricultural area.  There is a future for the continuous development of technology that will increase agricultural quality and reduce costs of production.

Recent Articles:

11/23/2017: Global Agriculture Robots Market 2017 [Harvest Automation]

11/23/2017:  Robotics in Indian Agriculture

11/02/2017: Immigration Crackdown Prompts Farm Automation  

Autonomous vehicle technology drives pilot projects

By Dean Bushey, Rahul Razda, and Anand Prasad

Public Transportation has been one of the most active areas for the use of autonomous vehicle (AV) technologies. In fact, one of Florida’s most visible communities (The Villages) just announced the pending availability of autonomous taxi service. Public utilities are viewing AV as a solution to a number of vexing issues such as solving the last mile problem (bus-stop to house) or raising the efficiency of existing fleets or even providing on-demand 24-7 access.

In addition, the pace of pilot projects is accelerating around the world.   Bloomberg Philanthropies keeps these projects up to date on their website.   Some important pilots include Uber’s work with Pittsburgh, and Waymo (Google)’s work in Phoenix.  In Florida, nearly every public authority ranging from JTA to LYNX are considering the use of this technology.

Recent Articles:

11/24/2017: Lyft Gets Approval To Test Self Driving Cars On Public Roads in California

11/23/2017: Waymo Ride Hailing Service Launching Soon Fully Autonomous Cars

11/22/2017: Self Driving Buses Shuttles Tests in Singapore  

Verifying how AVs behave during accidents

Summary: This post talks about the somewhat-unpopular topic of how Autonomous Vehicles should behave during (and directly after) unavoidable accidents, and especially how to verify that.

AV accidents are clearly going to happen: Even the best driver in the world is not guaranteed to never have accidents. This is largely due to, ahem, all the other idiots out there.

I discussed that in my 2106 Stuttgart symposium report, where I said:

For more Information: here.

On mobileye’s formal model of AV safety

Summary: This short post talks about Mobileye’s new paper (regarding a formal approach to Autonomous Vehicles safety). It claims that the paper has several issues, but is nevertheless an important start.

Mobileye came out with a paper titled “On a Formal Model of Safe and Scalable Self-driving Cars” (Bloomberg coveragesummary paperfull pdf). Their main contribution is a thoughtful, detailed, formal description of AV safety – do take a look.

For more information: here.

Autonomous vehicle testing – where is the due diligence?

Is anyone doing or even advocating any minimum level testing? Governments: Creating Test Cases – State and Local governments are waiting on the Fed’s in DoT. Who are clearly doing very little. A couple of weeks ago the GAO completed an audit of the DoT. The GAO stated that the DoT should be far more organized and actually have a plan moving forward. They stated they should also test AVs for minimum capabilities. The DoT’s response was that they cannot put a plan in place or even create the tests until the various technologies involved are settled.

For more information: here.

Corner or edge cases are not most complex or accident scenarios

I am seeing a very disturbing trend. Folks in the autonomous vehicle industry are using the terms “Corner or Edge Cases” to include complex, dangerous and accident scenarios.

Here is the Wiki definition of a Corner Case – “In engineering, a corner case (or pathological case) involves a problem or situation that occurs only outside of normal operating parameters—specifically one that manifests itself when multiple environmental variables or conditions are simultaneously at extreme levels, even though each parameter is within the specified range for that parameter.”

For more information: here.

Autonomous levels 4 and 5 will not happen without simulation vs public shadow driving

By: Michael DeKort

The reason it is not possible to create an autonomous vehicle using that process is that it will take one trillion miles at a cost of over $300B. And those using it will cause thousands of accidents, injuries and casualties when they move from benign scenarios to complex, dangerous and accident scenarios.

For more information: here.

Self-Propelled cars could change the world (Florida Poly in Iceland)

Self-propelled cars could change the world as we know it, says Rahul Razdan, a PhD in computer science. Razdan commented on the issue at a seminar organized by the Engineering Association of Iceland today.

Razdan has worked for the creation of launch companies for decades, currently working at the Florida University of Technology. He says the average utilization of passenger cars is only about 5% today.

For more information visit here.