{"version":"1.0.0","episode":{"title":"Smart Driving Cars episode 413- SpaceX, Waymo, NVIDIA, May Mobility & more","url":"http://getcarcurious.com/episodes/smart-driving-cars-episode-413-spacex-waymo-nvidia-may-mobility-more","audioUrl":"https://anchor.fm/s/9105ed8/podcast/play/120402618/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-4-22%2F424707010-44100-2-a4cf7b873b2fb.mp3","description":"SpaceX files for an IPO, Waymo pauses for flooding, Seval Oz to keynote an AV Conference plus NVIDIA, Uber, May Mobility and more. Join Princeton's Alain Kornhauser and co-host Fred Fishkin for episode 413 of Smart Driving Cars!\n"},"annotations":[{"startTime":160.16,"endTime":169.88,"type":"car","title":"Morgan Six Plus","url":"/cars/morgan/plus-six","image":"https://upload.wikimedia.org/wikipedia/commons/a/aa/2021_Morgan_Plus_6_Auto.jpg","quote":"...u a postcard from the beach. Yeah that might be a six plus. That might still not get you a seven. But Bob an...","canonicalId":"car:morgan:plus six","priority":0.5,"source":"hybrid-fuzzy+gpt-5.4-nano","data":{"explanation":"The Morgan Plus Six is a modern two-seat sports car from Morgan, built around a lightweight, classic-style body with contemporary engineering. It’s often discussed because it blends traditional roadster character with everyday usability, and its performance is a big part of why people compare it to other “six” and “seven” class sports cars. In a podcast, it may come up in the context of how different models stack up in feel, speed, and overall driving experience.","simplifiedExplanation":"The Morgan Plus Six is a small, two-seat sports car made by Morgan. It’s designed for driving for fun, with a focus on performance and a classic-looking style. People mention it when talking about how fast or exciting different sports cars are.","imageAttribution":"Calreyn88 (CC BY-SA 4.0)"}},{"startTime":977.3,"endTime":1005.6,"type":"term","title":"Robo taxis","url":"/glossary/robotaxis","quote":"I think they can get a sense of Waymo was forced to pause service in four cities this week because Robo taxis struggled to deal with heavy rain and flooded roads.","canonicalId":"term:robo-taxis","priority":0.7,"confidence":0.85,"source":"hybrid-fuzzy+gpt-5.4-nano","data":{"explanation":"“Robo taxis” are autonomous ride-hailing vehicles that drive themselves without a human driver controlling the car. Their operation depends heavily on perception and planning sensors, and adverse conditions like heavy rain and flooded roads can overwhelm detection and localization.","simplifiedExplanation":"Robo taxis are self-driving cars that you can summon like a rideshare. They still rely on sensors to “see” the road, and bad weather or flooding can make that much harder."}},{"startTime":977.3,"endTime":992.6,"type":"term","title":"flooded roads","url":"/glossary/flooded-roads","quote":"Robo taxis struggled to deal with heavy rain and flooded roads. There was a vehicle in Atlanta that got stuck Wednesday while driving through a flooded street.","canonicalId":"term:flooded-roads","priority":0.55,"confidence":0.8,"source":"hybrid-fuzzy+gpt-5.4-nano","data":{"explanation":"Flooded roads are a safety-critical edge case for autonomous vehicles because the system may not reliably detect water-covered hazards, lane boundaries, or changes in depth. Even if the vehicle can perceive the environment, water can affect traction and vehicle dynamics, increasing the risk of getting stuck.","simplifiedExplanation":"Flooded roads are dangerous for self-driving cars because the water can hide what’s under or on the road. It can also make the car lose grip and get stuck."}},{"startTime":977.3,"endTime":986.5,"type":"term","title":"heavy rain","url":"/glossary/heavy-rain","quote":"Waymo was forced to pause service in four cities this week because Robo taxis struggled to deal with heavy rain and flooded roads.","canonicalId":"term:heavy-rain","priority":0.55,"confidence":0.75,"source":"hybrid-fuzzy+gpt-5.4-nano","data":{"explanation":"Heavy rain is a challenging environment for autonomous driving because it can reduce sensor visibility and increase false detections. For camera-based systems, water on the lens and reflections can degrade image quality, while flooded roads can also change traction and road geometry.","simplifiedExplanation":"Heavy rain makes it harder for self-driving cars to “see” clearly. It can also change what the road looks like and how slippery it is."}},{"startTime":977.3,"endTime":1005.6,"type":"company","title":"Waymo","url":"/glossary/waymo","quote":"I think they can get a sense of Waymo was forced to pause service in four cities this week because Robo taxis struggled to deal with heavy rain and flooded roads.","canonicalId":"company:waymo","priority":0.45,"confidence":0.9,"source":"hybrid-fuzzy+gpt-5.4-nano","data":{"explanation":"Waymo is an autonomous driving company known for deploying self-driving vehicles in public areas. In this segment, it’s referenced in connection with pausing service due to difficulties handling heavy rain and flooded roads.","simplifiedExplanation":"Waymo is a company that builds self-driving cars. Here, they’re mentioned because their service was paused after problems in bad weather and flooding."}},{"startTime":1005.6,"endTime":1030.1,"type":"term","title":"memory management","url":"/glossary/memory-management","quote":"unfortunately, we didn't have one line of code in our stuff. And therefore, we didn't do many memory management properly. And after 9.8 miles, we ran out of memory.","canonicalId":"term:memory-management","priority":0.65,"confidence":0.9,"source":"hybrid-fuzzy+gpt-5.4-nano","data":{"explanation":"Memory management is how software allocates, tracks, and frees computer memory while it runs. In autonomous driving stacks, poor memory management can cause the system to run out of resources during perception and planning, leading to failures or forced shutdowns.","simplifiedExplanation":"Memory management is how a computer program keeps track of its “working space” while it’s running. If it doesn’t manage that space well, the program can run out and stop doing the job it needs to do."}},{"startTime":1005.6,"endTime":1087.4,"type":"concept","title":"DARPA challenge","url":"/glossary/darpa-challenge","quote":"when we did the DARPA challenge in 2005, unfortunately, we didn't have one line of code in our stuff... And after 9.8 miles, we ran out of memory.","canonicalId":"concept:darpa-challenge","priority":0.4,"confidence":0.8,"source":"hybrid-fuzzy+gpt-5.4-nano","data":{"explanation":"The DARPA Challenge refers to DARPA’s autonomous vehicle competitions that pushed self-driving research forward. The speaker uses it as a historical example of early autonomy systems and how software limitations (like memory issues) affected performance.","simplifiedExplanation":"The DARPA Challenge was a competition that tested self-driving technology. The speaker is using it to explain how early software problems could stop a vehicle from completing a route."}},{"startTime":1013.3,"endTime":1064.5,"type":"concept","title":"world model (saving historic locations of detected objects)","url":"/glossary/world-model-saving-historic-locations-of-detected-objects","quote":"we were saving the location, historic location of every object we had detected... We might actually be able to go in reverse and not hit something and then find it different way out.","canonicalId":"concept:world-model-saving-historic-locations-of-detected-objects","priority":0.55,"confidence":0.7,"source":"hybrid-fuzzy+gpt-5.4-nano","data":{"explanation":"A “world model” is the internal representation of the driving environment used for planning—often including where objects were seen over time. Saving historic locations helps the system reason about where it is and what might be behind it, enabling safer maneuvers like reversing.","simplifiedExplanation":"A world model is the car’s internal “map” of what’s happening around it. Keeping track of where objects were seen helps it make better decisions, like whether it can back up safely."}},{"startTime":1030.1,"endTime":1046.4,"type":"term","title":"one camera looking forward","url":"/glossary/one-camera-looking-forward","quote":"we could only afford one camera looking forward. In case we had to go backwards, we say, what the hell is behind us?","canonicalId":"term:one-camera-looking-forward","priority":0.6,"confidence":0.85,"source":"hybrid-fuzzy+gpt-5.4-nano","data":{"explanation":"Using “one camera looking forward” means the perception system relies on a single forward-facing viewpoint to detect objects and understand the scene. That limitation can affect how well the vehicle handles situations where the safest maneuver requires awareness of what’s behind or around it.","simplifiedExplanation":"“One camera looking forward” means the car is mostly relying on a single front-facing view to understand the world. If you need to maneuver, you may not know what’s behind you as well."}},{"startTime":1030.1,"endTime":1046.4,"type":"term","title":"detecting objects","url":"/glossary/detecting-objects","quote":"we were saving the location, historic location of every object we had detected to get that far.","canonicalId":"term:detecting-objects","priority":0.5,"confidence":0.75,"source":"hybrid-fuzzy+gpt-5.4-nano","data":{"explanation":"Object detection is the perception step where the vehicle identifies other road users and obstacles (like cars, pedestrians, and static hazards) from sensor data. The transcript ties it to storing object locations, which is part of building a consistent world model for planning.","simplifiedExplanation":"Object detection is how the car figures out what other things are around it. It’s like the car trying to label “there’s a car here” or “there’s an obstacle there.”"}},{"startTime":1722.44,"endTime":1737.1,"type":"company","title":"Nvidia","url":"/glossary/nvidia","quote":"I'm thrilled. And, you know, if it's Nvidia's providing the chips to do that, they're probably the most. I, of course, think they're the most competent folks out there doing it.","canonicalId":"company:nvidia","priority":0.55,"confidence":0.95,"source":"hybrid-fuzzy+gpt-5.4-nano","data":{"explanation":"Nvidia is a semiconductor company best known for GPUs (graphics processing units). In autonomous driving, those chips are used to run the heavy AI workloads for perception and decision-making.","simplifiedExplanation":"Nvidia makes powerful computer chips. For self-driving cars, those chips help the car’s software “think” by running the AI that sees the road and plans what to do."}},{"startTime":1858.1,"endTime":1917.2,"type":"company","title":"May Mobility","url":"/glossary/may-mobility","quote":"eCar X backed by Gillies Lee Shifu will sell Robo Taxis to May Mobility in a $750 million deal that's going to involve, I think, thousands of vehicles... These things then are productive elements in society, which actually should generate a return for May Mobility.","canonicalId":"company:may-mobility","priority":0.7,"confidence":0.9,"source":"hybrid-fuzzy+gpt-5.4-nano","data":{"explanation":"May Mobility is a company focused on autonomous “robo-taxi” style services, typically using driverless shuttles in geofenced areas. The segment discusses May Mobility as the operator that would receive Robo Taxis via a large acquisition deal.","simplifiedExplanation":"May Mobility is a company that runs self-driving taxi/shuttle services. The discussion is about them getting more vehicles to expand where they operate."}},{"startTime":1922.8,"endTime":1937.6,"type":"concept","title":"driverless cars","url":"/glossary/driverless-cars","quote":"A bill that would have allowed driverless cars in Minnesota did not pass as the legislature there wrapped up the latest session.","canonicalId":"concept:driverless-cars","priority":0.65,"confidence":0.85,"source":"hybrid-fuzzy+gpt-5.4-nano","data":{"explanation":"“Driverless cars” refers to vehicles operating without a human driver controlling the car. The segment ties this to legislation—specifically a bill in Minnesota that would have allowed driverless cars but did not pass.","simplifiedExplanation":"Driverless cars are cars that can drive themselves without a person behind the wheel. The hosts are talking about laws that determine whether and where those cars are allowed to operate."}},{"startTime":1937.6,"endTime":1943.32,"type":"concept","title":"federal regulation","url":"/glossary/federal-regulation","quote":"Yeah. Well, that's why we need the federal regulation, which is coming out. And","canonicalId":"concept:federal-regulation","priority":0.6,"confidence":0.8,"source":"hybrid-fuzzy+gpt-5.4-nano","data":{"explanation":"“Federal regulation” means rules set at the national level rather than by individual states. In autonomous driving, federal rules are often discussed because they could standardize safety requirements and deployment permissions across the country.","simplifiedExplanation":"Federal regulation means national rules. For self-driving cars, the idea is that one set of rules could make it easier to deploy them consistently across many states."}}],"speakers":[{"id":"s1","name":"Fred Fishkin/Alain Kornhauser","role":"host"}],"transcripts":[{"url":"http://getcarcurious.com/episodes/smart-driving-cars-episode-413-spacex-waymo-nvidia-may-mobility-more/transcript.vtt","type":"text/vtt"}]}