MIT-AVT is a large-scale semi-autonomous driving study aimed at understanding how human-AI interaction in driving can be safe and enjoyable. The emphasis is on objective, data-driven analysis through large-scale real-world driving data collection and deep learning based parsing of that data.

Link: https://hcai.mit.edu/avt
Paper: https://arxiv.org/abs/1711.06976

CONNECT:
- If you enjoyed this video, please subscribe to this channel.
- AI Podcast: https://lexfridman.com/ai/
- Show your support: https://www.patreon.com/lexfridman
- LinkedIn: https://www.linkedin.com/in/lexfridman
- Twitter: https://twitter.com/lexfridman
- Facebook: https://www.facebook.com/lexfridman
- Instagram: https://www.instagram.com/lexfridman
- Slack: https://deep-mit-slack.herokuapp.com

Currently, the Tesla fleet for the MIT Autonomous Vehicle Technology Study includes the Model S and the Model X.

But we're here today in our first Model 3 that we're going to instrument and add to the study.

It has the same sensor suite as the same Autopilot hardware 2 in this vehicle as it does in the Model S and the Model X.

And as far as we can tell, the compute resources and the algorithms performing the autonomous steering in this car is the same as in the Model S and the Model X.

The Model 3 is a really interesting car to add to our study because it has the same kind of autonomous technology as does the Model S and the Model X, but is more affordable, therefore allowing a larger number of people to use this technology.

However, on the instrumentation side, there's a few challenges.

To instrument this vehicle, we first need to place our sensors and run our wires to our rider recording box.

This box also requires power and CAN to function.

Since this vehicle does not have an OBD2 port, we need to find other means of both powering our box as well as collecting CAN data.

There are multiple methods for powering our Ryder recording box.

1 is to use external power from a battery.

A second is to use a 12-volt auxiliary outlet, much like the cigarette outlet in the center console to power it.

A third method is to find the 12-volt battery source in this vehicle and run power directly from it so that we have constant power.


Speaker 0: Currently, the Tesla fleet for the MIT Autonomous Vehicle Technology Study includes the Model S and the Model X. But we're here today in our first Model 3 that we're going to instrument and add to the study. It has the same sensor suite as the same Autopilot hardware 2 in this vehicle as it does in the Model S and the Model X. And as far as we can tell, the compute resources and the algorithms performing the autonomous steering in this car is the same as in the Model S and the Model X. The Model 3 is a really interesting car to add to our study because it has the same kind of autonomous technology as does the Model S and the Model X, but is more affordable, therefore allowing a larger number of people to use this technology.

However, on the instrumentation side, there's a few challenges.

Speaker 1: To instrument this vehicle, we first need to place our sensors and run our wires to our rider recording box. This box also requires power and CAN to function. Since this vehicle does not have an OBD2 port, we need to find other means of both powering our box as well as collecting CAN data. There are multiple methods for powering our Ryder recording box. 1 is to use external power from a battery.

A second is to use a 12-volt auxiliary outlet, much like the cigarette outlet in the center console to power it. A third method is to find the 12-volt battery source in this vehicle and run power directly from it so that we have constant power.

Speaker 0: Do you think we'll figure it out? Of course. You you you you

See all Lex Fridman transcripts on Youtube

MIT-AVT: Tesla Model 3