- 53
- 730 991
DRIVEN
Приєднався 16 чер 2023
Podcast about AI, robotics, autonomous vehicles, and more with host Paul Perrone. Visit us at www.driven.show
Predicting Autonomous Vehicle Timelines Mathematically - DRIVEN Podcast Ep. 28 #autonomousvehicles
In this groundbreaking episode of DRIVEN, host Paul Perrone takes you on an exclusive deep dive into the cutting-edge research behind his latest paper, "A Comprehensive Mathematical and System-Level Analysis of Autonomous Vehicle Timelines." For the first time, Paul unveils never-before-presented mathematical foundations that challenge conventional wisdom about the timeline predictions for autonomous vehicle (AV) deployment.
Key highlights include:
* Surprising Results: Discover why some AV categories, like consumer vehicles and robo-taxis, face decades-long horizons, while industrial and defense applications may achieve full autonomy within just a few years.
* The Mathematics of Complexity: Learn how NP-hard multi-agent path planning and computational constraints, combined with reliability growth modeling, redefine the AV roadmap.
* Revealing Insights into Operational Design Domains (ODDs): Discover how factors like weather, traffic density, and speed dramatically alter the testing and deployment timelines for Level 5 autonomy.
* Shattering Myths: This episode reveals why ambitious claims of near-term universal driverless cars are mathematically and systematically implausible-and what breakthroughs could accelerate the journey.
Listen in as Paul uncovers the intricate interplay of computational challenges, safety validation requirements, and regulatory hurdles. Whether you're an AV enthusiast, industry insider, or tech visionary, this episode promises to transform your perspective on the future of autonomous vehicles.
www.driven.show
From: Paul Perrone (DRIVEN Host, Perrone Robotics CEO/Founder)
Download Paper: www.perronerobotics.com/papers/av-timelines
Key highlights include:
* Surprising Results: Discover why some AV categories, like consumer vehicles and robo-taxis, face decades-long horizons, while industrial and defense applications may achieve full autonomy within just a few years.
* The Mathematics of Complexity: Learn how NP-hard multi-agent path planning and computational constraints, combined with reliability growth modeling, redefine the AV roadmap.
* Revealing Insights into Operational Design Domains (ODDs): Discover how factors like weather, traffic density, and speed dramatically alter the testing and deployment timelines for Level 5 autonomy.
* Shattering Myths: This episode reveals why ambitious claims of near-term universal driverless cars are mathematically and systematically implausible-and what breakthroughs could accelerate the journey.
Listen in as Paul uncovers the intricate interplay of computational challenges, safety validation requirements, and regulatory hurdles. Whether you're an AV enthusiast, industry insider, or tech visionary, this episode promises to transform your perspective on the future of autonomous vehicles.
www.driven.show
From: Paul Perrone (DRIVEN Host, Perrone Robotics CEO/Founder)
Download Paper: www.perronerobotics.com/papers/av-timelines
Переглядів: 25 176
Відео
Autonomous Racing: How AI Powers Cars at 184 MPH | DRIVEN Ep. 27 - Conversation with Madhur Behl
Переглядів 87 тис.2 місяці тому
In this thrilling episode of DRIVEN, Paul Perrone sits down with Madhur Behl, computer science professor at the University of Virginia and an expert in autonomous racing technology, to explore the cutting-edge world of high-speed self-driving race cars. Discover how artificial intelligence and engineering brilliance combine to control vehicles moving at nearly 200 mph, all without a human drive...
Luis Dussan Conversation - Ep. 26 - #ai #autonomousvehicles #lidar #perception #generativeai #adas
Переглядів 58 тис.3 місяці тому
Episode 26: Luis Dussan - DRIVEN In this episode, Paul Perrone sits down with Luis Dussan, founder of AEye and co-founder of a stealth-mode startup, to explore his groundbreaking innovations in perception technology for autonomous vehicles. From his early days at NASA’s Deep Space Network to leading advancements in ISR tech at Lockheed Martin and Northrop Grumman, Luis shares how his journey sh...
Michael Prichard Conversation - Ep. 25 - Generative AI & Cars
Переглядів 56 тис.4 місяці тому
Exploring the Future of Generative AI with Michael Prichard | DRIVEN Podcast Episode 25 In this captivating episode of the DRIVEN Podcast, host Paul Perrone sits down with Michael Prichard, the Co-Founder and CTO of Multiply AI, to delve deep into the transformative world of generative AI, artificial intelligence, and the exciting intersection with the automotive industry. What's Inside: - Mich...
Safety Assurance for Autonomous Vehicles - DRIVEN Podcast Ep. 24: Safety Watchdog
Переглядів 81 тис.4 місяці тому
In this episode, Paul explores a critical subsystem for autonomous vehicles that acts as a safety watchdog, constantly monitoring the Autonomous Drive System (ADS) for errors. When safety-critical failures are detected, the watchdog triggers fail-safe reactions to protect both the vehicle and its passengers. Key topics of interest include: * How simple, verifiable, and validateable watchdogs pr...
Movement Planning in Autonomous Vehicles - DRIVEN Podcast Ep. 23
Переглядів 35 тис.5 місяців тому
In this captivating episode of DRIVEN, host Paul Perrone dives into the intricacies of movement planning in autonomous vehicles. Discover how these vehicles intelligently maneuver and navigate through complex environments, interacting with other vehicles, pedestrians, cyclists, and more. From autonomous maneuvers like pacing, collision avoidance, and parking, to the nuanced decision-making proc...
Sensor Fusion in Autonomous Vehicles - DRIVEN Podcast Ep. 22
Переглядів 33 тис.6 місяців тому
Episode 22: Sensor Fusion in Autonomous Vehicles In this informational episode of DRIVEN, hosted by Paul Perrone, we delve into the intricate process of sensor fusion in autonomous vehicles. Sensor fusion involves resolving whether objects detected by different sensors, or the same sensor over time, are the same or distinct. This episode provides a comprehensive overview of how autonomous vehic...
Dr. Bharat Balasubramanian (Dr. B) Conversation - DRIVEN Podcast Ep. 0021 - #adas #autonomous
Переглядів 30 тис.6 місяців тому
Dr. Bharat Balasubramanian (Dr. B) Conversation - DRIVEN Podcast Ep. 0021 - #adas #autonomous
Nolan Bushnell DRIVEN Interview (Ep. 0001) #gaming #ai #robot #autonomousvehicles
Переглядів 9 тис.6 місяців тому
Nolan Bushnell DRIVEN Interview (Ep. 0001) #gaming #ai #robot #autonomousvehicles
LiDAR Perception - DRIVEN Ep. 0020 (#LiDAR, #autonomous, #perception)
Переглядів 38 тис.7 місяців тому
LiDAR Perception - DRIVEN Ep. 0020 (#LiDAR, #autonomous, #perception)
Autonomous Navigation - DRIVEN Ep. 0019 (#autonomousvehicles #selfdriving)
Переглядів 28 тис.7 місяців тому
Autonomous Navigation - DRIVEN Ep. 0019 (#autonomousvehicles #selfdriving)
AV Localization - DRIVEN Ep. 0018 (#autonomousvehicles #slam #gps #localization )
Переглядів 72 тис.8 місяців тому
AV Localization - DRIVEN Ep. 0018 (#autonomousvehicles #slam #gps #localization )
James Gosling Conversation - DRIVEN Ep. 17 (#java #iot #ai #robotics)
Переглядів 68 тис.9 місяців тому
James Gosling Conversation - DRIVEN Ep. 17 (#java #iot #ai #robotics)
Autonomous Vehicles: The World's Most Complicated Technical Problem - DRIVEN Ep. 0016 #autonomous
Переглядів 4,3 тис.9 місяців тому
Autonomous Vehicles: The World's Most Complicated Technical Problem - DRIVEN Ep. 0016 #autonomous
Conversation with Jon Snoddy - DRIVEN Ep. 15 (#disney #lucasfilm #vr #gaming #storytelling #AI)
Переглядів 75 тис.9 місяців тому
Conversation with Jon Snoddy - DRIVEN Ep. 15 (#disney #lucasfilm #vr #gaming #storytelling #AI)
Conversation with Bill Frazer - DRIVEN Ep. 0014 #delorean #electricvehicle #brewing #autonomous
Переглядів 4,6 тис.10 місяців тому
Conversation with Bill Frazer - DRIVEN Ep. 0014 #delorean #electricvehicle #brewing #autonomous
Conversation with Robin Murphy - DRIVEN Ep. 0013 #ai #robotics #sciencefiction
Переглядів 27 тис.10 місяців тому
Conversation with Robin Murphy - DRIVEN Ep. 0013 #ai #robotics #sciencefiction
Conversation with Sandra Kublik - DRIVEN Ep. 0012
Переглядів 5 тис.10 місяців тому
Conversation with Sandra Kublik - DRIVEN Ep. 0012
Conversation with Corey Clothier - DRIVEN Ep. 0011
Переглядів 2,1 тис.11 місяців тому
Conversation with Corey Clothier - DRIVEN Ep. 0011
How an AV Plans its Mission - DRIVEN Ep. 0010
Переглядів 4311 місяців тому
How an AV Plans its Mission - DRIVEN Ep. 0010
Conversation with Ray Russell - DRIVEN Ep. 0009
Переглядів 171Рік тому
Conversation with Ray Russell - DRIVEN Ep. 0009
Conversation with Chunka Mui - DRIVEN Ep. 0008
Переглядів 843Рік тому
Conversation with Chunka Mui - DRIVEN Ep. 0008
Conversation with Doug Szajda - DRIVEN Ep. 0007
Переглядів 256Рік тому
Conversation with Doug Szajda - DRIVEN Ep. 0007
The Cruise AV Pedestrian Incident - DRIVEN Ep. 0005
Переглядів 516Рік тому
The Cruise AV Pedestrian Incident - DRIVEN Ep. 0005
How does an Autonomous Vehicle work? - DRIVEN Ep. 0004
Переглядів 614Рік тому
How does an Autonomous Vehicle work? - DRIVEN Ep. 0004
What's Inside an Autonomous Vehicle? - DRIVEN Ep. 0003
Переглядів 473Рік тому
What's Inside an Autonomous Vehicle? - DRIVEN Ep. 0003
What Really is an Autonomous Vehicle? - DRIVEN Ep. 0002
Переглядів 379Рік тому
What Really is an Autonomous Vehicle? - DRIVEN Ep. 0002
Nolan Bushnell Conversation (6of7) - DRIVEN Ep. 0001 (Part 6: Frameworks, AV Industry, Grit)
Переглядів 66Рік тому
Nolan Bushnell Conversation (6of7) - DRIVEN Ep. 0001 (Part 6: Frameworks, AV Industry, Grit)
Nolan Bushnell Conversation (7of7) - DRIVEN Ep. 0001 (Part 7: Creativity, Reflections, Future)
Переглядів 45Рік тому
Nolan Bushnell Conversation (7of7) - DRIVEN Ep. 0001 (Part 7: Creativity, Reflections, Future)
This was a lot of fun, Thanks Paul.
you didn't make an argument to support your case. you just called it wrong and speculated more deaths. you need to say "why" it's wrong if you believe it is wrong. wrong, silly, dumb, why are we having it...? those are not intelligent points.
Indeed this is a short 60 second clip. The whole episode is a 2 hour conversation but that topic was covered in probably 10 minutes or more. So please check it out and let us know what you think. Episode 26 of DRIVEN.
You’re not addressing the fact that liar is too expensive to have on 100 million cars. It’s not a viable mass production design element. And you made a huge mistake assuming they would use two cameras. In fact, they’re using an array of cameras that generates three-dimensional simulation of the environment around the vehicle. I used FSD last week. 🤯
Indeed this is a short 60 second clip. The whole episode is a 2 hour conversation but that topic was covered in probably 10 minutes or more. So please check it out and let us know what you think. Episode 26 of DRIVEN.
Khup sundar aahe mahiti
Pahilyabaddal khup khup dhanyavad!
👌💚♥️💚♥️💚♥️💚
USA USA USA
Commodore 64 driven car? Wow! Count me in!
Going to need a lot of tape decks!
@@DRIVEN-SHOW Pffft! 5" Floppies for the win!
,
Thanks fot sharing.
Great episode once again, Paul!
The problem with the delivery idea mentioned is nobody will deliver if pay isn't good enough. Currently Walmart has reduced driver pay by 50% and as a result there are delays with deliveries because the pay is so low it sometimes would cost the driver money to make a delivery. A better solution is to make a network of delivery lockers/hubs/dropoff spots. For safety reasons as well because there are numerous reports that Cartel gang members are doing Walmart delivery, DoorDash etc. With Walmart a driver could record a customer's name and address even if they choose not to deliver. Also an easy way for burglars to scope out potential targets in advance.
I disagree with Nolan on his jobs commentary. I've been unemployed for over 3 years now, have 25 years of tech experience and nobody is hiring. How am I supposed to survive? There are tons of other people in the same boat. Government welfare?
he just not made java he made a way for me to earn and build a career 🎉
Thank you for having me, Paul! We covered so much LLM ground in this convo❤ I hope it will be a useful introduction to LLM space for folks. I encourage anyone who is hungry to learn more to check out the podcast with LLM experts I just launched ❤
Sondra is safe in Poland.They have good leadership that wouldn't let the U.N. ruin their country
If we say it… it’ll manifest
Update: Cruise issues recall update to the AV fleet to update the minimal risk response to fail-stop when engaged in a collision. Report linked below. The pedestrian was on the ground after they were propelled in front of the Cruise vehicle after a hit and run incident occurring in the adjacent lane. The Cruise vehicle braked hard and veered to the right when it ran over the pedestrian, registering the collision as a lateral collision versus forward collision. This induced the vehicle to engage in a maneuver to pull over to the side of the road (“fail-op” vs “fail-stop” as outlined in DRIVEn podcast episode 0005). The update will be to make the vehicle fail-stop under such a circumstance. static.nhtsa.gov/odi/rcl/2023/RCLRPT-23E086-7725.PDF
Great visualizations of the accident in San Francisco. I'll see you as the expert witness in court. Also great comments on the role of neural nets (should they be ubiquitous or not?) - Cruise I think was quoted as saying their vehicles are engaged in "continuous learning" which usually means NN. Finally - as we move into this era of automation, the key issue to acknowledge in evaluation of accidents: Such inevitable events won't be the same ones we would see in a universe of all-human drivers ... the question is "are we safer?" The metric is severe injuries and fatalities per year. Looking at any particular accident and saying "well that would not have happened with a human driver" is clearly the wrong standard.
Cruise’s Continuous Learning Machine Predicts the Unpredictable on San Francisco Roads (Cruise): medium.com/cruise/cruise-continuous-learning-machine-30d60f4c691b A Flexible, Verifiable, and Validateable Approach to Autonomous Vehicle Safety (Paul Perrone): www.dependability.org/wg10.4/ivds2021/presentations/perrone-PerroneRobotics-IVDS-21-Flexible%20VandV%20Safety%20Approach.pdf
'Promo sm' 😱
Excellent interview. Thank you.
😆