All Segments
George Hotz: 3 Problems of Autonomous Driving: Static, Dynamic, Counterfactual | AI Podcast Clips
4 segments available
This is a clip from a conversation with George Hotz on the Artificial Intelligence podcast. You can watch the full conversation here: http://bit.ly/2YLIPom If you enjoy these, consider subscribing, sharing, and commenting below. Full episode: http://bit.ly/2YLIPom Full episodes playlist: http://bit.ly/2EcbaKf Clips playlist: http://bit.ly/2JYkbfZ Podcast website: https://lexfridman.com/ai George Hotz is the founder of Comma.ai, a machine learning based vehicle automation company. He is an outspoken personality in the field of AI and technology in general. He first gained recognition for being the first person to carrier-unlock an iPhone, and since then has done quite a few interesting things at the intersection of hardware and software. Subscribe to this YouTube channel or connect on: - Twitter: https://twitter.com/lexfridman - LinkedIn: https://www.linkedin.com/in/lexfridman - Facebook: https://www.facebook.com/lexfridman - Instagram: https://www.instagram.com/lexfridman - Medium: https://medium.com/@lexfridman - Support on Patreon: https://www.patreon.com/lexfridman
Segments Timeline
The Leapfrog Strategy in Autonomous Driving
George Hotz discusses the concept of leapfrogging in autonomous driving technology, emphasizing the need for innovative approaches that diverge from existing methods. He highlights the potential for breakthroughs in mapping and simulation that could revolutionize the industry, suggesting that current systems are built on outdated frameworks.
"so the way you leapfrog right is you come up with an idea or you take a direction perhaps secretly that the other people aren't taking and so cruise way mo even Aurora no Aurora Zuke's is the same sta..."
Understanding the Static Driving Problem
Hotz explains the static driving problem, which assumes a vehicle is the only one on the road. He argues that while this problem can be solved with mapping and localization, it is not as straightforward as it seems. He critiques existing systems like Tesla's for failing to address the complexities of real-world driving conditions.
"said before about oh they actually get the whole thing well I'll say this about we divide driving into three problems and I actually haven't solved the third yet but I haven't idea how to do it so the..."
Navigating the Dynamic Driving Challenge
In this segment, Hotz delves into the dynamic driving problem, which involves real-time detection and prediction of moving objects, such as other vehicles. He emphasizes the necessity of understanding and modeling the behavior of other drivers to navigate these challenges effectively.
"how could you how do you have a perfect you can build perfect localizers are not that hard to build okay come on now with with wood lighter why don't ya wood lighter okay why don't ya but you use ligh..."
The Counterfactual Dilemma in AI
Hotz introduces the concept of counterfactuals in autonomous driving, referencing his discussions with Judea Pearl. He explains that addressing counterfactual scenarios is crucial for developing robust AI systems, and he proposes using reinforcement learning to tackle this complex problem involving human behavior.
"dynamic problem yeah so you have to deal with this um this involves again like you're gonna need models of other people's behavior do you are you including in that I don't to step on on the third one ..."