George Hotz: Comma.ai, OpenPilot, and Autonomous Vehicles
Aug 5, 2019
auto_awesome
George Hotz, founder of Comma.ai, renowned for jailbreaking the iPhone, dives into the future of autonomous vehicles. He discusses the complexities of programming styles in developing lane-keeping systems and the challenges of perception in self-driving tech. Hotz emphasizes the importance of real data to enhance driver safety and addresses the hurdles of achieving Level 5 autonomy. The conversation also touches on the ethical dilemmas of data access and communication in the tech industry, reflecting on the intersection of innovation and societal impact.
George Hotz emphasizes the importance of accurate and reliable lane keeping systems and effective driver monitoring for autonomous vehicles.
George Hotz discusses the current limitations of open pilot, including challenges in navigation, stop car detection, and the need for continuous driver monitoring.
George Hotz acknowledges the difficulty in achieving natural and comfortable lane changes in autonomous driving and the current limitations in longitudinal control.
George Hotz identifies the counterfactual problem as a crucial aspect of autonomous driving that requires a solution, involving predicting and addressing different driving styles and behaviors.
Deep dives
Developing an AI-based vehicle automation system
George Hotts, founder of Coma AI, discusses his journey in developing a machine learning based vehicle automation system.
The challenge of determining if we are living in a simulation
Hotts explores the concept of living in a simulation and the difficulty of proving whether or not we are in one.
The importance of good lane keeping and driver monitoring
Hotts emphasizes the value of accurate and reliable lane keeping systems and the need for effective driver monitoring to ensure driver engagement and safety.
The evolution and limitations of open pilot
Hotts discusses the current limitations of open pilot, including the challenges in navigation, stop car detection, and the need for continuous driver monitoring.
The importance of lane keeping and driver monitoring
Lane keeping and driver monitoring are crucial aspects of autonomous vehicles. Cami emphasizes the significance of these features in ensuring safe and efficient driving. Cami believes that lane keeping can be achieved through a combination of mapping, localization, and careful monitoring of lane changes. Additionally, driver monitoring plays a vital role in maintaining attention and ensuring quick response in case manual control is required.
The challenges of longitudinal control and natural lane changes
Cami acknowledges the difficulty of achieving natural and comfortable lane changes in autonomous driving. While lateral control has been improved through mapping, training models, and end-to-end learning, longitudinal control remains a challenge. Cami believes that current systems lack the ability to provide a truly natural driving experience when it comes to braking, accelerating, and lane changing. Meeting this challenge is crucial for creating a more comfortable and human-like driving experience.
The need for a solution to the counterfactual problem
Cami identifies the counterfactual problem as a crucial aspect of autonomous driving that still requires a solution. This problem involves predicting and addressing different driving styles and behaviors that humans exhibit during lane changes and other maneuvers. Cami believes that identifying and learning from different driving styles can lead to a better understanding of safe and natural lane changes. The goal is to develop an autonomous system that can accurately predict and replicate different driving styles while maintaining safety and comfort.
Cami's long-term vision and perspective on the future of autonomous driving
Cami envisions a future where autonomous vehicles become more advanced and integrated into society. They believe that developing deep connections and merging with AI systems like machines can lead to significant advancements. Cami sees potential in VR brothels, sophisticated simulations, and AI systems that can play out hypothetical scenarios tailored to an individual's personal development. While discussing the singularity, Cami believes that the dominance of silicon-based machine intelligence over biological intelligence signifies the crossing point to an advanced future.
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. This conversation is part of the Artificial Intelligence podcast. If you would like to get more information about this podcast go to https://lexfridman.com/ai or connect with @lexfridman on Twitter, LinkedIn, Facebook, Medium, or YouTube where you can watch the video versions of these conversations. If you enjoy the podcast, please rate it 5 stars on iTunes or support it on Patreon.
Get the Snipd podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered podcast player
Listen to all your favourite podcasts with AI-powered features
Discover highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share & Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered podcast player
Listen to all your favourite podcasts with AI-powered features
Discover highlights
Listen to the best highlights from the podcasts you love and dive into the full episode