Tag: Indy Autonomous Challenge

Racing to an autonomous finish
Photo: Penske Entertainment / Walt Kuhn

Flipping the traditional scenario, in which car racers risk their lives on a racetrack, the Indy Autonomous Challenge (IAC) aimed to help save lives by improving collision avoidance systems, train future automotive engineers, and make the public more comfortable with autonomous cars. Held Oct. 23 at the Indianapolis Motor Speedway and organized by Energy Systems Network, the race saw 21 universities from nine countries forming nine teams to compete for a $1 million grand prize. Following in the footsteps of the DARPA Grand Challenge, first held in 2004 and later renamed the DARPA Urban Challenge, the IAC was the world’s first high-speed autonomous race. The winning team was TUM Autonomous Motorsport from the Technical University of Munich, Germany.

All competing teams were given the same identical vehicle to work with, a Dallara AV-21, modified to carry no one in the cockpit and equipped with two Hexagon | NovAtel PwrPak7-Ds multi-frequency, multi-constellation GNSS receivers, six cameras (two of which faced backward), three lidar scanners and four radars. Each team had to develop its own autonomy-enabling software stack, including the algorithms and neural networks. All the components, except the computer, had to be commercial-off-the-shelf, available on the market. No sensors could be custom-made.

Since 2001, Dallara has been the sole supplier of the Indy Lights series, a championship to prepare drivers for the NTT IndyCar Series. The Dallara AV-21 is a collaboration between Dallara’s Italian headquarters in Varano Melegari (Parma) and Dallara IndyCar Factory in Speedway, Indiana. The new car offers a modern, stylish appearance and provides the proper training required for drivers as the final step on the ladder to the NTT IndyCar Series.

The process by which the automated vehicle sensors and computers were fused into a singular package and integrated into the AV-21 was led by Clemson University’s International Center for Automotive Research’s Deep Orange 12 (DO12) project. The Deep Orange process mirrors that of automotive original equipment manufacturers (OEMs), and the DO12 project scope allowed for engineering and innovation across multiple subsystems. Student groups within the DO12 team explored solutions within and across multiple subsystems, including:
- vehicle-to-vehicle communications
- perception systems
- onboard computing
- drive-by-wire chassis control systems
- vehicle dynamics
- vehicle-to-infrastructure communications
- powertrain design and integration
- vehicle demonstration based on high precision GPS.
Hexagon’s Autonomy & Positioning division provided GNSS receivers and subject-matter experts to the Deep Orange 12 team. The team architected the sensor kit for the Dallara reference vehicle, which AutonomousStuff then replicated 10 times. The team did not compete in the IAC to avoid a conflict of interest and allow students to work closely with competitor teams from universities around the world. The PwrPak7-E1 contains a MEMS IMU to deliver Hexagon | NovAtel’s SPAN technology, a deeply coupled GNSS + inertial engine in a single-box solution. Each GNSS receiver has two antennas to provide heading. The Deep Orange 12 team used HxGN SmartNet RTK corrections, which brought the accuracy down to a few centimeters.

Without developing a driverless decision-making algorithm, Clemson students tested the vehicle with the help of a high-precision positioning system. They developed a control algorithm that can track the optimal line around the Indianapolis Motor Speedway such that all vehicle systems could be validated in a simulated racing environment. Data from these tests were shared with the competition teams to aid in their development of driverless algorithms.

Energy Systems Network will host a head-to-head, high-speed autonomous racecar passing competition at the Las Vegas Motor Speedway on Jan. 7, 2022, during the Consumer Electronics Show. Several of the teams that competed in the IAC, including the winner and finalists, will participate. The primary goal is to advance technology to speed commercialization of fully autonomous vehicles and deployments of advanced driver-assistance systems.
December 28, 2021
TUM Autonomous Motorsport wins Indy Autonomous Challenge

TUM Autonomous Motorsport preps its autonomous vehicle. (Photo: Indy Autonomous Challenge)

TUM Autonomous Motorsport from the Technische Universität München (TUM) won on Saturday the Indy Autonomous Challenge Powered by Cisco, the first autonomous racecar competition at the Indianapolis Motor Speedway.

TUM competed in a field of nine teams from 21 universities to win the $1 million grand prize.

Rules of the IAC competition required each team to compete in a fastest-lap competition that included an obstacle avoidance component. The winning team recorded the fastest two-lap average speed of 135.944 mph on the famed oval track.

“Participating in the Indy Autonomous Challenge allowed our team to advance autonomous driving technologies, and being able to take first place after two years of hard work acknowledges that we had an outstanding team,” said Alex Wischnewski, team leader of TUM Autonomous Motorsport. “Our next goal is to win a high-speed autonomous head-to-head race.”

Organized by Energy Systems Network and the Indianapolis Motor Speedway, the primary goal of the IAC is to advance technology that can speed the commercialization of fully autonomous vehicles and deployments of advanced driver-assistance systems (ADAS).

These enhancements will lead to increased safety and performance in motorsports, as well as all modes of commercial transportation. The competition also serves as a platform for students to excel in science, technology, engineering and math (STEM) and inspire the next generation of innovators.

In addition to thousands of attendees at the IMS, and more than 20,000 viewers on the AWS livestream, the IAC hosted 350 high school STEM students representing more than 50 urban, rural and suburban school districts across Indiana.

October 25, 2021
Use of autonomous vehicles in mining and farming touted at CES 2021
After years of testing and hype, not a lot of companies can say there are real applications for autonomous technology. However, at this year’s virtual CES 2021 trade show, both Caterpillar and John Deere, two companies known for their tractors and heavy equipment, showcased autonomous machines that are being used worldwide in farming and mining projects.

Photo: Caterpillar

Deerfield, Ill.-based Caterpillar, a first-time exhibitor at CES this year, said it has been involved in autonomy and use of GPS for more than two decades. “We were an early adopter of GPS when there were few satellites in the sky,” said Denise Johnson, company group president, resource industries. “We have 350 autonomous trucks operating 24-7 on three continents.”

The company’s autonomous vehicles, in addition to other technology, are being used around the clock in the Kearl Oil Sands project in Alberta, Canada.

“We are using autonomy primarily in mining operations in harsh environments. These [vehicles] are operating 24-7, with no loss time incidents,” said Bill Dears, Caterpillar worldwide sales and marketing manager. “We also track people underground with cameras and radar.”

In addition to production enhancement, safety is a factor in mining operations because of operator fatigue — something that is precluded by autonomous mining equipment, Dears said.

Agriculture uses variety of sensors, including GNSS

To Moline, Ill.-based John Deere, exhibiting at the trade show for the third time, agriculture is a high-tech industry that uses GPS, self-driving tractors, artificial intelligence and a multitude of sensors. The company rolled out its first self-driving tractors nearly 20 years ago, said Jahmy Hindman, John Deere CTO.

Photo: John Deere

The company won the CES Innovation Award for one of its tractor and combine product lines. “Both our planter and tractor have GPS and antennas to know where to drive and where exactly fertilizer [is to be placed],” Hindman said. “These tractors are self-propelled, with accuracy augmented with [real-time kinematic] sub-inch accuracy for the planters in a field.”

Among other requirements, Hindman said that tractors have to drive in a straight line, plant the required amount seeds and position them at the right depth. “When a tractor drives in a very straight line, the burden is off of the farmer. The yields increase—this is the way we see the progression of automation,” he said. “We are excited about 5G and its lower latency and high bandwidth. It opens up a lot of opportunity.”

Organizers roll out Indy Autonomous Challenge race car

At the virtual CES, representatives from the Indy Autonomous Challenge unveiled the Dallara IL-15 race car that will be used in a head-to-head race around the famous Indianapolis Motor Speedway on Oct. 23.

The Indy Autonomous Challenge, organized by Energy Systems Network and Indianapolis Motor Speedway, pits 500 university students, developing autonomous vehicle technology, against each other for a $1.5 million prize.

Logo: Indy Autonomous Challenge

Organizers say the speeds are estimated to be as much as 200 mph around the 2.5-mile track, for 20 laps, which enables researchers to evaluate how autonomous vehicle technology works in extreme conditions. They say that the goal of the race is to advance the implementation of autonomous vehicles and advanced driver-assistance systems (ADAS), much like the 2005 Defense Advanced Research Projects Agency (DARPA) Grand Challenge.

The race track has been the scene of much innovation throughout the years, said Doug Boles, Indianapolis Motor Speedway president. “Firestone tests tire technology there and that data transfers to our cars. One of the first conversations we had with Roger Penske [after Penske Entertainment bought the speedway] was about the autonomous challenge,” he said.

IAC sponsors include ADLINK, Ansys, Aptiv, AutonomouStuff, Bridgestone, CU-ICAR, Dallara, Indiana Economic Development Corp., Microsoft, New Eagle, PWR, RTI, Schaeffler and Valvoline.

Mobileye plans to test autonomous fleets in four cities

Intel subsidiary Mobileye plans to launch autonomous vehicle fleet testing in Detroit, Paris, Shanghai and Toyko. The announcement, made at CES by CEO Amnon Shashua, said that the company also plans to test in New York City, pending regulatory approval.

The company also plans to use in-house-built lidar sensors, while continuing to champion its camera-based testing. “We are using crowd-sourced data through the Cloud to build high-definition maps at scale,” Shashua said. “Thousands of product vehicles are sending us data.”

Shashua addressed a moderator’s question that cameras alone cannot be the technology of choice for autonomous vehicles. “The camera first is crucial from a technology and business point of view. We have to find out what is acceptable failure for Level 4 autonomy. Camera-only is ideal, but pushing the envelope for driver-assistance systems,” he said. “Consumer AV will take place in the 2025 timeframe. [Eventually], we can build lidar and radar to the same performance levels as camera systems. Lidar and radar can be added later for redundancy, but only for Level 4.”

Shashua said getting to Level 4 could take a decade, but that would be unsustainable unless there are government-funded projects to keep companies afloat. “By 2025, a subsystem will be good enough for consumers. Regulation is critical and sometimes it’s difficult to leap to a consumer level,” he said.

Not everyone believes what Mobileye is testing constitutes “driverless” status. To Alain Kornhauser Princeton University professor and transportation program director, who was head of the university’s team during the 2005 DARPA Challenge, not many companies are capable of full driverless capability.

“Unfortunately, I still see all of this as simply ‘eye candy’ to sell something that actually has no intention of delivering what it is implying. I still claim that the business case is zero, doesn’t exist, for personally-owned autonomous vehicles,” Kornhauser said in his Smart Driving Cars weekly newsletter. “Mobileye is nowhere close to being able to operate safely on most roads, let alone all roads. Thus, the consumer market has zero opportunity to scale.”

Kornhauser said that driverless testing is being conducted only in one place, Phoenix, by Waymo. “Neither Tesla nor Mobileye are driverless anywhere. They both require on-board human driver supervision,” he said. “That’s why they are only self-driving [tests].”

In other CES news:
- GM CEO Mary Barra unveiled a single-seat electric vertical takeoff and landing (eVTOL) concept aircraft. The aircraft will be developed for future use as an air taxi. Barra briefly mentioned that the company’s Super Cruise self-driving technology will be integrated into 22 car models in a few years. The company also rolled out an electric vehicle for deliveries that can travel 250 miles on a charge and a motorized pallet for deliveries that can be tracked.
- The Mercedes-Benz’ MBUX Hyperscreen, rolled out at CES, evaluates map data, surroundings and provides information about landmarks along a route, said Sajjad Khan, company CTO and member of the board of management. The new map feature, called Mercedes Travel Knowledge, allows a passenger or driver to ask a question as they drive by a landmark (“hey, Mercedes, what can you tell me about this building?”). The MBUX Hyperscreen is available in the new S-Class cars.
- HERE Technologies introduced a mapping-as-a-service platform at CES. The platform is targeted to businesses wanting to create custom map datasets for advanced analytics and services, the company said. Some use cases include industrial yard mapping, leveraging probe data from private vehicle fleets in order to create or update a map.• A virtual CES is hard to get used to. After more than 20 years of covering the massive trade show in person, covering press conferences and conducting interviews online was sometimes a challenge. Sometimes the press conferences did not have question-and-answer sessions, or canned answers given to executives by public relations people. This doesn’t happen much during an in-person interview. In addition, trying to chat with “booth” personnel online was cumbersome and often those requests for information were ignored.
January 20, 2021
Universities compete in new autonomous race
By Kevin Dennehy
GPS World Contributor

University teams will go head-to-head in a two-year autonomous race car competition to test new software and other self-driving technologies at Indianapolis Motor Speedway.

The competition, called the Indy Autonomous Challenge, culminates in a high-speed autonomous vehicle race, scheduled for Oct. 23, 2021, on the speedway’s famed 2.5-mile oval track that is home to the annual Indianapolis 500.

The competition was inspired by the 2005 Defense Advanced Research Projects Agency (DARPA) Grand Challenge, which pitted university teams against each other and spurred commercial development of autonomous vehicles.

“The idea for the Indy Autonomous Challenge originated with DARPA’s winning team captain, [Stanford University’s] Sebastian Thrun. Sebastian joined us at the 2018 Indy 500, where he reflected on the inspiration and excitement that came from participating in the DARPA challenge, and how a high-speed automated vehicle race at the Indianapolis Motor Speedway had the potential to be on par with that experience with today’s teams,” said Matt Peak, Energy Systems Network director of mobility.

Like the DARPA competition, the Indy Autonomous Challenge focuses on university participation. “I can’t speak for DARPA, but our focus on universities is deliberate,” Peak said. “It was advised by not only Thrun, but other original DARPA competitors such as [Aurora CEO] Chris Urmson, all of whom commented on how participation by universities — their students, faculty, departments, alumni — was a key to DARPA’s success.”

The autonomous racing software developed through the competition could assist in developing commercial self-driving vehicles and enhance existing advanced driver-assistance systems (ADAS). Some of the cornerstone technologies include GNSS and digital maps, which provide the accurate location for fully autonomous vehicles.

As was the case with the original DARPA challenge, spurring new innovations and socially beneficial products and services is a goal of the competition, Peak said. “In our case, we see inspiring teams’ creation of software that can solve for edge cases — those problems or situations that occur only at an extreme operating parameter, such as avoiding unanticipated obstacles at high speeds while maintaining vehicular control,” he said. “This applies not only for highly automated vehicles, but also for vehicles equipped with ADAS that aim to help human drivers avoid obstacles altogether. The notion is, if our university innovators can enable cars to outmaneuver others at 200 mph, they certainly can help enable you to avoid that piece of lumber that fell off the pickup in front of you on the 65-mph highway.”

Peak said that a perfect place to demonstrate these technologies is the famous speedway, which for 100 years has tested automotive technology in a demanding environment. “Tackling automation at 200 mph in a race car is a bit more alluring than with a 20-mph people mover,” he said.

In addition to ESN and Indianapolis Motor Speedway, other challenge partners include race-car manufacturer Dallara Automobili and the Clemson University International Center for Automotive Research (CU-ICAR).

$1.45 Million in Prize Money

During the final race at the speedway, teams will compete for $1 million as the first-place prize. Second- and third-place finishers receive $250,000 and $50,000, respectively.

The five-round competition starts with the submission of a white paper to demonstrate vehicle automation with a video of an existing vehicle or participation in Purdue University’s self-driving go-kart competition at the speedway.

During the initial rounds, teams will use sponsor ANSYS’ driving simulator to develop autonomous vehicle software. ANSYS, which will provide $150,000 in prizes to top finishers of a third-round race, will co-host a hackathon to let teams work with the simulator, the company said. The fourth round allows teams to test their vehicles at the speedway in advance of the final race.

So far, five universities have registered:
- Korea Advanced Institute of Science & Technology (KAIST)
- Texas A&M Transportation Institute (TTI)
- University of Florida
- University of Illinois
- University of Virginia.
Not Everyone Has Championed Autonomous Vehicles…

The new competition is commencing during a time when media reports show that the once-hot autonomous vehicle industry has vocal critics. Recently, Apple pioneer Steve Wozniak, who once headed a GPS-based fleet company called Wheels of Zeus, said he didn’t expect to see a fully autonomous vehicle operating on the streets in his lifetime.
In addition, a few automakers have reined in autonomous vehicle development or have scaled back their technology expectations in recent months.

“Not at all surprising. The traditional OEMs were never going to be disrupters that put driverless mobility-as-a-service cars out there. It isn’t their business model, and it won’t be,” said Alain Kornhauser, Princeton University professor and transportation program director, who was head of the university’s team during the DARPA Challenge, in his Smart Driving Cars weekly newsletter. “Self-driving, I dare say Level 2, is and has always been their sweet spot — it sells cars. Now watch these same companies throw monkey wrenches into those driverless mobility machines to protect their conventional business model.”

Peak says the recent negative press on autonomous vehicles is what happens when any new technology is rolled out. “For any new technology, such as automation, we’re going to see euphoric coverage (automation will solve all of our problems) and pessimistic coverage (automation will never arrive and, if it does, it will make things worse),” he said. “It’s a cycle, it swings back and forth, and we happen to be touching upon the latter, pessimistic end of that cycle.”

Taking a moderate and realistic position about the technology is what the Indy Autonomous Challenge is striving to do, Peak said. “Automated vehicle technologies have a role to play, both in helping humans drive better, and eventually in enabling new markets, such as first/last mile transit solutions. The technologies are light years ahead of where they were a decade ago, and low-level automated technologies are already making a difference and saving lives in today’s vehicles,” he said. “We have a bit of a ways to go before the full potential of automation will be realized, and the Indy Autonomous Challenge will help us address the concerns brought about by the media and others to reach this end goal much sooner than we otherwise would.”

For more, go to www.indyautonomouschallenge.com.
December 4, 2019