# Episode 81: Vision for self-driving cars - Vassia Simaiaki

- Show: [Robot Talk](https://hardwarepodcasts.com/podcast/robot-talk)
- Published: 2024-04-19
- Length: 18m
- Episode: 81
- Page: https://hardwarepodcasts.com/podcast/robot-talk/2024-04-19-episode-81-vision-for-self-driving-cars-vassia-simaiaki
- Listen: https://ukrobotics.libsyn.com/episode-eighty-one-vassia-simaiaki

## Summary

Vassia Simaiaki, Head of AI Vision and Graphics at Wayve, explains the company's end-to-end AI approach to autonomous driving, which relies on camera data rather than expensive hardware like LiDAR or HD maps. She details how Wayve uses novel view synthesis and a neural simulator called NeuroSim to generate synthetic data, allowing their models to generalize to unseen scenarios like the 'plastic bag problem' or complex London traffic. The discussion highlights Wayve's partnership with Asda to expand grocery delivery coverage and their focus on proving safety through simulation to build public trust.

## Chapters

- [0:08](https://hardwarepodcasts.com/podcast/robot-talk/2024-04-19-episode-81-vision-for-self-driving-cars-vassia-simaiaki#t=8) Introduction: Robot Talk and Wayve's AV capabilities
- [3:16](https://hardwarepodcasts.com/podcast/robot-talk/2024-04-19-episode-81-vision-for-self-driving-cars-vassia-simaiaki#t=196) End-to-end AI vs. modular approaches in autonomous driving
- [5:31](https://hardwarepodcasts.com/podcast/robot-talk/2024-04-19-episode-81-vision-for-self-driving-cars-vassia-simaiaki#t=331) Novel view synthesis and handling dynamic agents
- [9:04](https://hardwarepodcasts.com/podcast/robot-talk/2024-04-19-episode-81-vision-for-self-driving-cars-vassia-simaiaki#t=544) Camera-only sensors and the Asda partnership
- [11:53](https://hardwarepodcasts.com/podcast/robot-talk/2024-04-19-episode-81-vision-for-self-driving-cars-vassia-simaiaki#t=713) Solving the 'plastic bag' problem with synthetic data
- [15:22](https://hardwarepodcasts.com/podcast/robot-talk/2024-04-19-episode-81-vision-for-self-driving-cars-vassia-simaiaki#t=922) Current focus on NeuroSim and safety validation

## Topics

- [Robotics & autonomy](https://hardwarepodcasts.com/topic/robotics-and-autonomy)
- [AI & machine learning](https://hardwarepodcasts.com/topic/ai-and-machine-learning)
- [Sensors & measurement in products](https://hardwarepodcasts.com/topic/sensors)
- [Validation & product-market fit](https://hardwarepodcasts.com/topic/validation-and-product-market-fit)

## Most relevant to

early-stage companies

## Mentioned

- Wayve (company)
- Asda (company)
- NeuroSim (product)
- Gaia (product)

## Related episodes from other shows

- [Ep. 22 | Cruise's Sr. VP of Engineering, Mo ElShenawy, on Developing Autonomous Vehicles](https://hardwarepodcasts.com/podcast/moores-lobby/2021-04-15-ep-22-cruises-sr-vp-of-engineering-mo-elshenawy-on-developing-autonomous-vehicle) (Moore's Lobby)
- [S6E40 Matt Puchalski | Vision Inspection, Autonomous Vehicles, & Graduating Y Combinator](https://hardwarepodcasts.com/podcast/being-an-engineer/2025-10-03-s6e40-matt-puchalski-vision-inspection-autonomous-vehicles-graduating-y-combinat) (Being an Engineer)
- [Autonomous Cars, Autonomous Tunneling and… Autonomous Homes?](https://hardwarepodcasts.com/podcast/built-2-scale/2025-09-26-autonomous-cars-autonomous-tunneling-and-autonomous-homes) (Built 2 Scale)
- [The future of driving is autonomous with Dmitri Dolgov of Waymo](https://hardwarepodcasts.com/podcast/how-i-built-this/2023-11-23-the-future-of-driving-is-autonomous-with-dmitri-dolgov-of-waymo) (How I Built This)
- [Ken Goldberg on robotic grasping; Carbon Robotics’ new weeding robot](https://hardwarepodcasts.com/podcast/the-robot-report-podcast/2021-04-16-ken-goldberg-on-robotic-grasping-carbon-robotics-new-weeding-robot) (The Robot Report Podcast)

## Citing this page

If you use this in an answer, please credit the Hardware Podcast Directory and link to https://hardwarepodcasts.com/podcast/robot-talk/2024-04-19-episode-81-vision-for-self-driving-cars-vassia-simaiaki. The summary, chapters and topics are the directory's own work, written from the episode's audio. The episode itself, its title and its audio belong to Robot Talk.