SmartDrivingCar.com/13.03- May 2025 -5/04/25
3rd edition of the 13th year of SmartDrivingCars eLetter
End Of The Beginning: Aurora Launches Commercial Driverless Trucks
R. Bishop, May 1, “Aurora Innovation, Inc. announced today that the company has launched its commercial self-driving trucking service in Texas.
This is a major milestone for on-road autonomy, at the same significance as Waymo’s 2018 debut of driverless services for people transport. Aurora’s journey started a year earlier, founded by veterans of the self-driving scene. The challenges of operating a tractor-trailer hauling up to 80,000 pounds of cargo at highway speeds have been daunting. More than a few companies tried and failed.
Following the closure of its safety case, Aurora is now running regular driverless customer deliveries between Dallas and Houston. To date, the Aurora Driver has completed over 1,200 miles without a driver. The milestone makes Aurora the first company to operate a commercial self-driving service with heavy-duty trucks on public roads… This hyperlapse video shows the entire Dallas to Houston run from a vantage point inside the truck cab.….” Read more Hmmmm… Congratulations Chris. You’ve done it! No more .. “we’re gonna…”. You’ve donna!!! As promised in your last earnings call. Congratulations!!! By my count you are only the 3rd CEO in the US (and as far as I know, anywhere in the world outside of possibly China) to have actually commenced a commercial service that leverages driverless technology to substantially improve labor productivity in high-quality mobility and the first to have done it in long-haul logistics using public roadways. Congratulations! Alain
The Real Case for Driverless Mobility
Narrated by Fred Fishkin, Available nowg
Published in 2024 (but still relevant)!!! Go to Amazon.com…
SmartDrivingCars ZoomCast 388 / PodCast 388 – Aurora, Waymo, NHTSA & more
F. Fishkin, May 4 “Commercial driverless trucks are on the road in Texas. A big accomplishment for Aurora! Plus.. a DOT research grant gets terminated, Waymo’s safety study and partnership with Toyota and NHTSA amends ADAS reporting rules. Join Princeton’s Alain Kornhauser and co-host Fred Fishkin for episode 388 of Smart Driving Cars.
0:00 open
0:30 Aurora launches commercial driverless trucks
6:05 DOT cancels grant to Research Foundation of CUNY
7:50 Waymo releases study showing reduction in serious crashes and improved safety
13:45 Waymo partnering with Toyota
16:12 NHTSA amends order for ADAS reporting
19:40 Star Base now an official city in Texas
21:50 Alain wrapping up another semester at Princeton
M. Lefevre, May 2, “…At the time your grant was issued, the grant agreement and applicable regulations authorized termination by “the Federal awarding agency or pass-through entity, to the greatest extent authorized by law, if an award no longer effectuates the program goals or agency priorities.” 2 CFR §200.340(a)(2). DOT’s priorities presently include:
• promoting traditional forms of energy and natural resources to the greatest extent possible,
• ensuring that taxpayer dollars are used efficiently in ways that maximally benefit the American people and improve their quality of life, and
• ceasing to promote divisive diversity, equity, and inclusion initiatives that discriminate on the basis of race, national origin, or another protected characteristic….” Read more Hmmmm… Totally unwarranted! Alain
New Study: Waymo is reducing serious crashes and making streets safer for those most at risk
Waymo Team, May 1, “The path to Vision Zero requires reducing severe crashes and improving the safety of those most at risk. Our latest research paper shows that the Waymo Driver is making significant strides in both areas. By reducing the most dangerous crashes and providing better protection for pedestrians, cyclists, and other vulnerable road users, Waymo is making streets safer in cities where it operates.
The paper, accepted to be published in the Traffic Injury Prevention Journal, expands on our Safety Impact Hub research, providing a deeper analysis of Waymo’s performance across 11 different crash types compared to human drivers. It also offers new insights into Waymo’s positive impact on serious injury crash rates…” Read more Hmmmm… Congratulations Waymo!! This is a major achievement. Thank you for being exceedingly careful and responsible in your deployment. Alain
P. Simshauser, April 24, “This Third Amended Standing General Order 2021-01 (General Order) is issued by the National Highway Traffic Safety Administration (NHTSA or the agency), an Operating Administration of the United States Department of Transportation, pursuant to 49 U.S.C. § 30166(g)(l)(A) and 49 CFR § 510.7.1. This General Order takes effect on June 16, 2025, and, as of that date, supersedes NHTSA’s April 5, 2023 Second Amended Standing General Order 2021-01.2… “Read more Hmmmm… Please read carefully. Since many new cars have ADAS systems, it may well be that this reporting requirement will need to become the standard reporting requirement for any incident; else, under-reporting will be rampant. Alain
Automated Vehicle (AV) Framework.
Press release, April 24, “The Department of Transportation’s National Highway Traffic Safety Administration has unveiled the National Highway Traffic Safety Administration’s (NHTSA) new Automated Vehicle (AV) Framework. The new framework will unleash American ingenuity, maintain key safety standards, and prevent a harmful patchwork of state laws and regulations. See video” Read more Hmmmm… Details matter. Alain
Self-Driving Cars Have New Rules in the U.S. Here’s Why That Matters
Deni Bechard, May 4, “… On April 24, with a brief video and a few dozen pages, the U.S.’s driverless car rulebook got a reboot. In the video, Secretary of Transportation Sean Duffy, … The order for the rule change, also dated to April 24, was released by the National Highway Transportation Security Administration (NHTSA) and will take effect on June 16. It will affect four vehicle automation levels (listed at the bottom of this article): Level 2, which requires driver intervention, and Levels 3 to 5, which use an automated driving system (ADS) that require little or no such intervention….
According to the order, this will trim the “unnecessary burdens” on companies, reducing expenses while keeping “safety benefits.” But critics argue…” Read more Hmmmm… My head is spinning. No comment. Alain
Waymo says its robotaxis are up to 25x safer for pedestrians and cyclists
J. Dow, “Waymo has released new research saying that its driverless robotaxis reduce pedestrian- and cyclist-involved collisions by 82%-92%, and crashes that involve an injury by 96%, when compared to the average driver.
Waymo has been operating its autonomous, driverless Level 4 robotaxis for several years now, and is continuing to (slowly) roll them out to more metro areas in the US. They’ve been operating in Phoenix since 2019 in some capacity, and entered San Francisco in 2022, Los Angeles in 2023, and Austin, Texas in 2024, plus they’ve just started testing in Atlanta, Georgia. In that time, the company has racked up 56.7 million miles of operation, allowing it to have a big enough sample to start understanding how its driving capabilities compare to the overall vehicle fleet.
Today it released a research paper that it has published, suggesting that its vehicles are indeed quite a lot safer, especially when it comes to “vulnerable road users” like pedestrians, cyclists and motorcyclists. Read more Hmmmm… one way to report on Waymo’s post. Alain
Waymo is still good at avoiding serious distraction and death after 56.7 million miles Andrew Hawkins, May 1, “Waymo released a new study today that it says shows its fully driverless vehicles continuing to outperform human drivers after 56.7 million miles.
The peer-reviewed study, which is slated for publication in Traffic Injury Prevention Journal, analyzes Waymo’s performance in 11 different crash scenarios compared to human drivers. In addition, it cites early evidence that the company’s vehicles are adept at preventing the most serious types of injuries during a vehicle crash. The study is the latest from Waymo that aims to bolster its safety case as it slowly introduces its robotaxis to new cities.
Waymo says its fully driverless vehicles have traveled 56.7 million miles across its four major markets — Phoenix, San Francisco, Los Angeles, and Austin — as of January 2025.
After analyzing the data, the company says its vehicles demonstrated a 92 percent drop in pedestrian injuries, an 82 percent decline in cyclist injuries, and an 82 percent decrease in motorcyclist injuries. Waymo also logged 96 percent fewer vehicle-to-vehicle crashes at intersections compared to human drivers, which the company notes is the leading cause of road injury for drivers in the US. …” Read more Hmmmm… Andrew is being very conservative in his reporting above making sure that even this peer-reviewed study is only something “said” by Waymo as opposed to being a statement of fact and that it “slowly” as opposed to “carefully” or “responsibly” “introduces its robotaxis to new cities”. Whatever, at least he reported it.
People drive really well and safely as long as they don’t mis-behave… as long as they don’t text, don’t drive when impaired, don’t speed excessively, don’t fall asleep and pay attention to the road ahead. However, they claim to their iPhones that they are not driving, they drive when impaired, they speed excessively and they fall asleep. The safety aspects of each of the these mis-behaviors can be substantially addressed without driverless technology:
Your phone knows you are driving. it has front and back cameras and gps. It knows. It doesn’t need to ask.
Your breath tells everyone you’ve been drinking.
Your car and your phone know how fast you are going and if you are driving erratically. Most cars today know if you are tailgating.
Your closed eyes tell your are sleeping.
Each of these mis-behaviors could be mitigated; however, driving is assumed to be a right, not the privileged that it is. Thus, the mis-behavior is tolerated rather than eradicated. Driverless tech provides a mobility alternative that would enable progress in eradicating the toleration of mis-behavior by creating availability of demand responsive affordable rides to those wishing to text, drink, sleep and/or not be engaged in the stress associated with driving. Alain
Samantha Doniger, May 2025, “Accurate and robust object detection is critical for advancing autonomous driving systems. In recent years, transformer-based architectures have shown significant promise in this domain, offering improved performance over previous state-of-the-art technologies, largely due to their ability to handle long-range dependencies. This thesis explores the potential benefits of multimodal sensor fusion in autonomous driving by evaluating three transformer-based architectures for object detection tasks, each trained on the nuScenes dataset. The first model, TransFusion, integrates camera and LiDAR data within a unified transformer framework. The second model is a LiDAR-only variant, adapted from the TransFusion implementation to isolate the contribution from the LiDAR sensors. The third model, FCOS3D, is a camera-only model that isolates the contribution from the camera sensors.
The primary goal of this research is to identify scenarios in which single-modality models (camera-only or LiDAR-only) produce conflicting detections and to analyze how the fusion-based approach handles these discrepancies. By closely examining these instances, the study evaluates whether LiDAR offers critical advantages over camera-only systems in consumer vehicles. Given the higher cost and complexity associated with LiDAR sensors, understanding whether these advantages justify the integration of LiDAR is vital for automotive manufacturers and researchers seeking to optimize safety, reliability, and system efficiency under cost constraints.
Through extensive experimental evaluations, this thesis contributes insights into how multimodal fusion impacts object detection, revealing that while the LiDAR-only variant yields higher overall detection metrics in limited training environments, the camera-only approach excels at identifying near-range objects, and the fusion model effectively refines extraneous predictions. This synergy underscores trade-offs between cost and detection coverage, providing guidance for future sensor design and deployment strategies in the pursuit of a fully autonomous driving system. Read more Hmmmm… This is a really good senior thesis. Alain
An Analysis of MOVES Style Transportation in New York City
Koby Ginder, May 2025, “Today, we stand at a critical moment in the evolution of automotive technology. Driverless technology has made tremendous progress over the past decade, and driver-
less vehicles have begun to permeate our society. The growth of this technology and the path it takes is sure to redefine how we think about mobility. This exploration aims to introduce, simulate and test an innovative transportation style that has only recently been made possible by the strides in automotive driverless technology. This network, known as MOVES style transportation, will be analyzed in America’s city: New York City. This paper will fi rst analyze the current patterns of transportation systems in the city; by inspecting public transportation data it will show the current movement patterns of New Yorkers and visualize it. It will introduce and describe the MOVES style autonomous driving network as it will be implemented in this speci fic use case. It will then model and simulate the performance of this system using specialized software developed by the Princeton Department of Operations Research and Financial Engineering. Financial performance will also be discussed based on the simulated results. Read more Hmmmm… This is a really good senior thesis. Alain
Pardon my French: Assessing the Potential for Data Centers in Rural Quebec with Machine Learning Models
Tyler Barretta, May 2025, “This thesis aims to explore the feasibility of data centers in Northern Quebec using machine learning models to determine feature importance of site selection factors. Specifically, Random Forests are used to learn feature importance on a large, multi-source dataset of hyperscale data centers and corresponding, important features captured across national and regional levels through 2006-2024. SVMs, LASSO regression, and XGBoost models are used to corroborate the feature importance results of the Random Forest. Installed Solar PV Power Capacity and Internet Adoption as the fraction of a country’s population using the internet are determined to be robust predictors for the existence of data centers at a given location in a given year. Quebec and Canada show favorable internet adoption metrics but low solar PV power capacity, when compared to the average metrics across locations with hyperscale data
centers. Thus, the model does not show Canada, and specifically rural northern Quebec, to be a likely site for a hyperscale data center. However, the model does not provide a comprehensive set of feature importance weights, and it has limitations in the simplification of complex features to simple data points, a weakness to collinearity in the determination of feature importance, and a time-stagnant nature which fails to capture an evolving set of optimal feature weights. Qualitative research shows that Canada is well poised to become a data center hub. Read more Hmmmm… This is a really creative senior thesis. Alain
Draft… Orf467F24: Investigation of MOVES-Style Mobility Deployments … Draft
Alain Kornhauser, Dec. 19, “An updated note to the readers of the SDC eLetter: Read more Hmmmm… We had an excellent class this Fall. This is a compilation of their investigations of MOVES-stye mobility opportunities in their “hometowns”. This is a compilation of drafts submitted in lieu of a final exam. The class will make the document more suitable for publication during the January intersession. Alain
***********************
Previous SmartDrivingCars ZoomCast/PodCasts
SmartDrivingCars ZoomCast 387/ PodCast 387– The Last(?)Dispatcher w Michael Sena
F. Fishkin, Feb. 25 “Keeping cars out of cities? The parking meter is turning 90 this year. We learn more about that and more from The Dispatcher publisher Michael Sena. Plus ..self driving cars, AI, the Black Hawk tragedy and more. Join Princeton’s Alain Kornhauser and co-host Fred Fishkin for episode 387 of Smart Driving Cars.
0:00 open
1:10 Michael Sena on parking meters turning 90 and what they are being used for now
8:15 The Pope and a cautionary approach to AI
13:05 For now…at least…the last edition of The Dispatcher
16:57 There’s another book on the way
18:30 Henry Ford…and the road today to driverless mobility
29:35 AI and Deep Research
37:10 the Black Hawk – American Airlines tragedy. What we’re learning.
SmartDrivingCars ZoomCast 386 / PodCast 386 – DeepSeek, HandyRides, Waymo, Tesla & more
F. Fishkin, Feb. 2 “DeepSeek and AI, HandyRides Inc. arrives, women providing taxi rides on motorcycles in Kenya, Waymo expanding to more cities and Tesla bringing front bumper camera to Model Y. Welcome back to Smart Driving Cars! Join Princeton’s Alain Kornhauser and co-host Fred Fishkin for all of that and more on episode 386. And remember to subscribe.
0:00 Open
1:21 AI code editor, DeepSeek and more
6:22 HandyRides Inc. now exists
7:05 From NY Times: Women on motorcycle taxis giving rides in Kenya and a piece on driving in Vietnam
14:36 Timothy Lee piece…speculating DeepSeek not responsible for crashing NVIDIA stock
16:50 Waymo expanding to more cities including Las Vegas and San Diego
19:58 More DeepSeek discussion
25:16 new edition of The Dispatcher out from Michael Sena
26:17 The work that lies ahead to provide mobility to those who need it
29:15 Why are there still rear ending crashes
29:35 New Tesla Model Y will have front bumper camera
SmartDrivingCars ZoomCast 385 / PodCast 385 – w Michael Sena … GM Cancels Cruise, Waymo progresses and NHTSA’s New Rules for Driverless
F. Fishkin, Dec. 22 “With GM putting an end to the Cruise robotaxi venture, Waymo reaching 5 million rides and NHTSA proposing new rules for driverless vehicles, there’s plenty of news to end the year. The Dispatcher publisher Michael Sena joins Princeton’s Alain Kornhauser and co-host Fred Fishkin for a look at those stories and more on episode 385 of Smart Driving Cars! Tune in and subscribe.
0:00 open
1:17 Nobel Prize for Physics awarded to Princeton’s John Hopfield. Alain’s tribute.
1:54 GM shutters Cruise robotaxi venture
13:26 Waymo has now delivered over 5 million driverless rides
26:49 NHTSA proposes new rules for self driving cars
34:55 The Dispatcher Musings…back to Scranton
38:14 Closing out the year with long time friends and kudos to Alain’s students
SmartDrivingCars ZoomCast 384 / 
