Sertac Karaman is a professor at MIT, co-founder of the autonomous vehicle company Optimus Ride, and is one of top roboticists in the world, including robots that drive and robots that fly. Support this podcast by signing up with these sponsors: – Cash App – use code “LexPodcast” and download: – Cash App (App Store): https://apple.co/2sPrUHe – Cash App (Google Play): https://bit.ly/2MlvP5w EPISODE LINKS: Sertac's Website: http://sertac.scripts.mit.edu/web/ Sertac's Twitter: https://twitter.com/sertackaraman Optimus Ride: https://www.optimusride.com/ 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 Apple Podcasts, follow on Spotify, or support it on Patreon. Here's the outline of the episode. On some podcast players you should be able to click the timestamp to jump to that time. OUTLINE: 00:00 - Introduction 01:44 - Autonomous flying vs autonomous driving 06:37 - Flying cars 10:27 - Role of simulation in robotics 17:35 - Game theory and robotics 24:30 - Autonomous vehicle company strategies 29:46 - Optimus Ride 47:08 - Waymo, Tesla, Optimus Ride timelines 53:22 - Achieving the impossible 53:50 - Iterative learning 58:39 - Is Lidar is a crutch? 1:03:21 - Fast autonomous flight 1:18:06 - Most beautiful idea in robotics
In this podcast episode, Lex Friedman sits down with Sertesh Karaman, a professor at MIT and co-founder of Optimus Ride, to discuss the future of autonomous vehicles and robotics.
Autonomous flying has the potential to revolutionize transportation logistics, cutting travel time and offering new opportunities. While we've seen some small scale deployment, widespread autonomous flying at a large scale is yet to be achieved.
The next challenge after simulating dynamics of physics and developing perception algorithms would be simulating human behavior in a simulation environment.
The speaker discusses game theory and understanding people's social value orientation in order to program robots to make better decisions. Although simulating cameras is difficult, as the physics of the real world are known, game theory and understanding human behavior can help create robots that are less aggressive.
As we deploy robots and autonomous vehicles, societal questions around sustainability, ethics and safety arise, highlighting the need to consider the impact of technology on society as a whole. Examining the differences between companies can help start the conversation needed to address these issues.
The development of autonomous vehicles has been discussed since 2014, with projections about fully autonomous vehicles being available within two or three years. It is possible that the development of autonomous technology will lead to a new industry standard.
Ryan Chin discusses Optimus Ride's approach to self-driving cars and emphasizes targeting geofenced areas, such as environments where transportation is required, for practicality and functionality.
The speaker suggests that optimizing ride-sharing routes by splitting up seats can lead to more efficient travel and cost savings, especially in areas with a limited number of ride requests.
The speaker discusses the importance of companies like Tesla informing the public about the technology they are providing, including both the good and the bad. He also posits that building efficient urban cars could lead to transportation being less than a dollar to go from A to B.
The speaker discusses the challenges of developing autonomous vehicles, including the use of LIDAR and the need for clear communication about how they work.
Using its computing resources instead of rendering, an autonomous car equipped with AI could take advantage of a very fast camera at the time of an accident on a highway to take the necessary actions to avoid it.
The speaker reflects on how little we truly know about the effectiveness of decision-making in machine learning, drawing parallels to our knowledge of the beginning of time and our own future. They acknowledge that while we should be cautious and mindful of the limits, we should also push the boundaries in order to test the abilities of machine learning algorithms.
Lex Fridman interviews Sirtash Karaman, and they discuss robotics, representing motion, augmented reality, and more. This episode includes an ad for Cash App.