TuSimple, once a buzzy startup considered a leader in self-driving trucks, is trying to move its assets to China to fund a new AI-generated animation and video game business. The pivot has not only puzzled and enraged several shareholders, but also threatens to pull the company back into a legal morass mere weeks after reaching […]
© 2024 TechCrunch. All rights reserved. For personal use only.
Uber users in Austin and Atlanta will be able to hail Waymo robotaxis through the app in early 2025 as part of a partnership between the two companies.
© 2024 TechCrunch. All rights reserved. For personal use only.
After multiple rounds of layoffs in 2022 and 2023, Nuro is pivoting its business strategy to focus more on the startup’s core autonomous driving technology instead of owning and operating a fleet of low-speed, on-road delivery bots. The company said on Wednesday it would start licensing its autonomous vehicle technology to automakers and mobility providers, […]
© 2024 TechCrunch. All rights reserved. For personal use only.
Autonomous vehicles have been highly anticipated because of the possibility that they will greatly reduce or perhaps eliminate the collisions that cause more than a million deaths each year. But safety isn’t the only potential benefit self-driving cars can offer: Teams of researchers around the world are showing that autonomous vehicles can also drive more efficiently than humans can. A U.S. Department of Energy program called NEXTCAR (Next-Generation Energy Technologies for Connected and Automated On-Road Vehicles), for example, is betting that a mix of new smart-vehicle technologies can boost fuel efficiency by as much as 30 percent.
As part of the NEXTCAR program, San Antonio, Texas–based Southwest Research Institute (SwRI) showcased advances in autonomous vehicle technology that will improve vehicles’ fuel economy—including the fuel efficiency of nonautonomous automobiles that just so happen to be in traffic with autonomous ones. The demonstration was held at the ARPA-E Energy Inovation Summit in Dallas in late May.
The SwRI team retrofitted a 2021 Honda Clarity hybrid with basic autonomous features such as perception and localization. On the day of the summit, they drove the vehicle along a route encircling the parking lot of the convention center where the summit was held. SWRI’s Ranger localization system, which the researchers installed on the Honda, has a downward-facing camera that captures images of the ground. By initially mapping the driving surface, Ranger can later localize the vehicle with centimeter-level accuracy, using the ground’s unique “fingerprint” combined with GPS data. This precision ensures the vehicle drives with exceptional control.
“It’s almost like riding on rails,” says Stas Gankov, a researcher in SwRI’s power-train engineering group. For this project, his group collaborated with other divisions at the institute, such as the intelligence-systems division, which developed the autonomy software stack added to the Honda Clarity.
Just as important, however, was the addition of an ecodriving module, a key innovation by SwRI. The ecomode determines the most economical driving speed by considering various factors such as traffic lights and surrounding vehicles. This system employs predictive control algorithms to help solve a tricky optimization problem: How can cars minimize energy consumption while maintaining efficient traffic flow? SwRI’s ecomode aims to reduce unnecessary acceleration and deceleration in order to optimize energy usage without impeding other vehicles.
“Autonomous vehicles operating in ecomode influence the driving behavior of all the cars behind them.” —Stas Gankov, Southwest Research Institute
To illustrate how the technology works, the team installed a traffic signal along the demonstration pathway. Gankov says an actual traffic-light timer from a traffic-signal cabinet was connected to a TV screen, providing a visual for attendees. A dedicated short range communications (DRSC) radio was also attached, broadcasting the signal’s phase and timing information to the vehicle. This setup enabled the vehicle to anticipate the traffic light’s actions far more accurately than a human driver could.
For instance, Gankov says, if the Honda Clarity was approaching a red light that was about to turn green, it would know the light was due to change and so avoid wasting energy by braking and then accelerating again. Conversely, if the car was approaching the signal as it was about to turn from green to yellow to red, the vehicle would release the accelerator and let friction slow it to a crawl, avoiding unnecessary acceleration in an attempt to beat the light.
These autonomous driving strategies can lead to significant energy savings, benefiting not just the autonomous vehicles themselves, but also the entire traffic ecosystem.
“In a regular traffic situation, autonomous vehicles operating in ecomode influence the driving behavior of all the cars behind them,” says Gankov. “The result is that even vehicles with Level 0 autonomy use fuel more sparingly.”
SwRI has been a participant in the NEXTCAR initiative since 2017. The program’s initial phase involved 11 teams, including SwRI, Michigan Technological University, Ohio State University, and the University of California, Berkeley. SwRI, in collaboration with the University of Michigan, focused on optimizing a Toyota Prius Prime, already known for its fuel efficiency, to achieve a 20 percent improvement in energy usage through optimization algorithms and wireless communicating with its surroundings. This was accomplished without modifying the Toyota’s power train or compromising its emissions. The team utilized power split optimization, balancing the use of the gas engine and battery-propulsion system for maximum efficiency.
Building on the success of NEXTCAR’s first phase, the program entered its second phase in 2021, with just SwRI, Michigan Tech, Ohio State, and UC Berkeley remaining. The focus of NEXTCAR 2 has been determining how much automation could further enhance energy efficiency. Gankov explains that while the first phase demonstrated a 20 percent energy-efficiency improvement over a baseline 2016 or 2017 model-year vehicle with no autonomous driving capabilities, through the addition of vehicle-to-everything connectivity alone, the second phase is exploring the potential for an additional 10 percent improvement by incorporating autonomous features.
Gankov says SwRI initially intended to partner with Honda for NEXTCAR’s second phase, but when contracting issues arose, the nonprofit proceeded independently. Utilizing an autonomy platform developed by SwRI’s intelligence-systems division, the NEXTCAR team equipped the Honda Clarity with what amounted to Level 4 autonomy in a box. This autonomy system features a drive-by-wire system, allowing the vehicle to automatically adjust its speed and steering based on inputs from the autonomy software stack and the ecodriving module. This ensures the vehicle prioritizes safety while optimizing for energy efficiency.
Employing techniques like efficient highway merging were key strategies in their approach to making the most of each tank of fuel or battery charge. “For example, in heavy traffic on the highway, calculating the most optimal way to merge onto the highway without negatively affecting the energy efficiency of the vehicles already on the highway is crucial,” Gankov noted.
As NEXTCAR 2 enters its final year, the demonstration at the ARPA-E Summit served as a testament to the progress made in autonomous-vehicle technology and its potential to dramatically improve energy efficiency in transportation.
Autonomous vehicles (AVs) have made headlines in recent months, though often for all the wrong reasons. Cruise, Waymo, and Tesla are all under U.S. federal investigation for a variety of accidents, some of which caused serious injury or death.
A new paper published in Nature puts numbers to the problem. Its authors analyzed over 37,000 accidents involving autonomous and human-driven vehicles to gauge risk across several accident scenarios. The paper reports AVs were generally less prone to accidents than those driven by humans, but significantly underperformed humans in some situations.
“The conclusion may not be surprising given the technological context,” said Shengxuan Ding, an author on the paper. “However, challenges remain under specific conditions, necessitating advanced algorithms and sensors and updates to infrastructure to effectively support AV technology.”
The paper, authored by two researchers at the University of Central Florida, analyzed data from 2,100 accidents involving advanced driving systems (SAE Level 4) and advanced driver-assistance systems (SAE Level 2) alongside 35,113 accidents involving human-driven vehicles. The study pulled from publicly available data on human-driven vehicle accidents in the state of California and the AVOID autonomous vehicle operation incident dataset, which the authors made public last year.
While the breadth of the paper’s data is significant, the paper’s “matched case-control analysis” is what sets it apart. Autonomous and human-driven vehicles tend to encounter different roads in different conditions, which can skew accident data. The paper categorizes risks by the variables surrounding the accident, such as whether the vehicle was moving straight or turning, and the conditions of the road and weather.
Level 4 self-driving vehicles were roughly 36 percent less likely to be involved in moderate injury accidents and 90 percent less likely to be involved in a fatal accident.
SAE Level 4 self-driving vehicles (those capable of full self-driving without a human at the wheel) performed especially well by several metrics. They were roughly 36 percent less likely to be involved in moderate injury accidents and 90 percent less likely to be involved in a fatal accident. Compared to human-driven vehicles, the risk of rear-end collision was roughly halved, and the risk of a broadside collision was roughly one-fifth. Level 4 AVs were close to one-fifthtieth as likely to run off the road.
The paper’s findings are generally favorable for level 4 AVs, but they perform worse in turns, and at dawn and dusk.Nature
These figures look good for AVs. However, Missy Cummings, director of George Mason University’s Autonomy and Robotics Center and former safety advisor for the National Highway Traffic Safety Administration, was skeptical of the findings.
“The ground rules should be that when you analyze AV accidents, you cannot combine accidents with self-driving cars [SAE Level 4] with the accidents of Teslas [SAE Level 2],” said Cummings. She took issue with discussing them in tandem and points out these categories of vehicles operate differently—so much so that Level 4 AVs aren’t legal in every state, while Level 2 AVs are.
Mohamed Abdel-Aty, an author on the paper and director of the Smart & Safe Transportation Lab at the University of Central Florida, said that while the paper touches on both levels of autonomy, the focus was on Level 4 autonomy. “The model which is the main contribution to this research compared only level 4 to human-driven vehicles,” he said.
And while many findings were generally positive, the authors highlighted two significant negative outcomes for level 4 AVs. It found they were over five times more likely to be involved in an accident at dawn and dusk. They were relatively bad at navigating turns as well, with the odds of an accident during a turn almost doubled compared to those for human-driven vehicles.
The study’s finding of higher accident rates during turns and in unusual lighting conditions highlight two major categories of challenges facing self-driving vehicles: intelligence and data.
J. Christian Gerdes, codirector of the Center for Automotive Research at Stanford University, said turning through traffic is among the most demanding situations for an AV’s artificial intelligence. “That decision is based a lot on the actions of other road users around you, and you’re going to make the choice based on what you predict.”
Cummings agreed with Gerdes. “Any time uncertainty increases [for an AV], you’re going to see an increased risk of accident. Just by the fact you’re turning, that increases uncertainty, and increases risk.”
AVs’ dramatically higher risk of accidents at dawn and dusk, on the other hand, points towards issues with the data captured by a vehicle’s sensors. Most AVs use a combination of radar and visual sensor systems, and the latter is prone to error in difficult lighting.
It’s not all bad news for sensors, though. Level 4 AVs were drastically better in rain and fog, which suggests that the presence of radar and lidar systems gives AVs an advantage in weather conditions that reduce visibility. Gerdes also said AVs, unlike humans, don’t tire or become distracted when driving through weather that requires more vigilance.
While the paper found AVs have a lower risk of accident overall, that doesn’t mean they’ve passed the checkered flag. Gerdes said poor performance in specific scenarios is meaningful and should rightfully make human passengers uncomfortable.
“It’s hard to make the argument that [AVs] are so much safer driving straight, but if [they] get into other situations, they don’t do as well. People will not find that reassuring,” said Gerdes.
The relative lack of data for Level 4 systems is another barrier. Level 4 AVs make up a tiny fraction of all vehicles on the road and only operate in specific areas. AVs are also packed with sensors and driven by an AI system that may make decisions for a variety of reasons that remain opaque in accident data.
While the paper accounts for the low total number of accidents in its statistical analysis, the authors acknowledge more data is necessary to determine the precise cause of accidents, and hope their findings will encourage others to assist. “I believe one of the benefits of this study is to draw the attention of authorities to the need for better data,” said Ding.
On that, Cummings agreed. “We do not have enough information to make sweeping statements,” she said.
Login