# 170. Robot That Drives Better Than The Average American

- Show: [The Next Byte Podcast](https://hardwarepodcasts.com/podcast/the-next-byte-podcast)
- Published: 2024-04-16
- Length: 20m
- Page: https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2024-04-16-170-robot-that-drives-better-than-the-average-american
- Listen: https://the-next-byte-wevolver.simplecast.com/episodes/170-robot-that-drives-better-than-the-average-american-jd_M61nf

## Summary

Daniel and Forbode discuss research from Professor Sue Xiao’s Robotics Lab at George Mason University, which developed an autonomous robot capable of driving better than humans on variable terrain. The team instrumented an off-the-shelf robot with visual and inertial sensors to collect data on stability, training a machine learning model that reduced instability by 62% while sacrificing only 8.6% of speed. This technology, applicable to first responders and drones, allows robots to adapt their driving style to terrain changes like gravel or ice, improving safety for both autonomous and human-in-the-loop scenarios.

## Chapters

- [0:00](https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2024-04-16-170-robot-that-drives-better-than-the-average-american#t=0) Introduction: George Mason University and the Robot XX Lab
- [3:45](https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2024-04-16-170-robot-that-drives-better-than-the-average-american#t=225) The Problem: Robot Instability on Variable Terrain
- [9:13](https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2024-04-16-170-robot-that-drives-better-than-the-average-american#t=553) Sensor Instrumentation: Visual and Inertial Feedback
- [12:15](https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2024-04-16-170-robot-that-drives-better-than-the-average-american#t=735) Data Collection and Machine Learning Model Training
- [14:50](https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2024-04-16-170-robot-that-drives-better-than-the-average-american#t=890) Results: 62% Instability Reduction and Speed Trade-off
- [17:05](https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2024-04-16-170-robot-that-drives-better-than-the-average-american#t=1025) Applications: First Responders, Drones, and Human-in-the-Loop

## Topics

- [Robotics & autonomy](https://hardwarepodcasts.com/topic/robotics-and-autonomy)
- [Sensors & measurement in products](https://hardwarepodcasts.com/topic/sensors)
- [AI & machine learning](https://hardwarepodcasts.com/topic/ai-and-machine-learning)
- [Mechanical engineering](https://hardwarepodcasts.com/topic/mechanical-engineering)

## Most relevant to

early-stage companies

## Mentioned

- George Mason University (company)
- Robotics Lab (other)
- Wevolver (company)

## Related episodes from other shows

- [Niels Jul Jacobsen, CEO, Capra Robotics; Spider-Man Robot Fail](https://hardwarepodcasts.com/podcast/the-robot-report-podcast/2022-06-17-niels-jul-jacobsen-ceo-capra-robotics-spider-man-robot-fail) (The Robot Report Podcast)
- [Episode Eleven – Self-Driving Cars: behind the wheel](https://hardwarepodcasts.com/podcast/robot-talk/2021-10-29-episode-eleven-self-driving-cars-behind-the-wheel) (Robot Talk)
- [Episode 91: Robot navigation on land and in water - John Leonard](https://hardwarepodcasts.com/podcast/robot-talk/2024-09-27-episode-91-robot-navigation-on-land-and-in-water-john-leonard) (Robot Talk)
- [Episode 155: Making aerial robots smarter - Melissa Greeff](https://hardwarepodcasts.com/podcast/robot-talk/2026-05-08-episode-155-making-aerial-robots-smarter-melissa-greeff) (Robot Talk)
- [Autonomous vehicle technology deep dive at John Deere and Zoox](https://hardwarepodcasts.com/podcast/the-robot-report-podcast/2023-04-18-autonomous-vehicle-technology-deep-dive-at-john-deere-and-zoox) (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/the-next-byte-podcast/2024-04-16-170-robot-that-drives-better-than-the-average-american. 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 The Next Byte Podcast.