Tesla engineers present the hardware and software architecture behind the Tesla Bot, Full Self-Driving, the occupancy network, and Dojo training infrastructure.
Join us to build the future of AI → tesla.com/ai
--------
- Pre-show
- Tesla Bot Demo
- Tesla Bot Hardware | Hardware Architecture
- Tesla Bot Hardware | Hardware Simulation
- Tesla Bot Hardware | Actuators
- Tesla Bot Hardware | Hands
- Tesla Bot Software | Autonomy Overview
- Tesla Bot Software | Locomotion Planning
- Tesla Bot Software | Motion Control and State Estimation
- Tesla Bot Software | Manipulation
- Tesla Bot Software | What's Next?
- FSD Intro
- FSD | Planning
- FSD | Occupancy Network
- FSD | Training Infra
- FSD | Lanes and Objects
- FSD | AI Compiler & Inference
- FSD | Auto Labeling
- FSD | Simulation
- FSD | Data Engine
- Dojo Intro
- Dojo Hardware
- Dojo Software
- Q&A
Why it's here
2 people recommend this
What people say. Recommended for its detailed technical transparency regarding Tesla's autonomous driving training pipeline, simulation, and hardware.
t
timschmidton Hacker News • Recommends
On “The Retreat to Muskworld”
> If the data from supervised driving can he used for unsupervised driving So you're unaware of the AI day presentations about their driving training pipeline. Learning about their engineering in that regard really changed my perception of the likelihood that they could solve the problem. Give it a watch: link to this video > failure to keep up with competitors like Waymo Looks like each of them lead in different ways to me. Waymo leads within certain specific city limits, Tesla leads on the open road. These seem to be direct consequences of their engineering decisions. Question is which will converge on working everywhere all the time.
On “Why Tesla removed radar and ultrasonic sensors [video]”
It is pretty cool: link to this video They transitioned from 2D to 3D a couple years ago, major transition but it does seem like a critical step. We live in a 3d rather than 2d world.
On “Tesla Vision Update: Replacing Ultrasonic Sensors with Tesla Vision”
As stated by Tesla just a few days ago, the occupancy network is not currently shown in the customer-facing visualisation. (Some unrecognised objects are represented by generic placeholders. This is derived from, but not the output of, the occupancy network.) This video links to the relevant citation, and if you continue watching for around ten seconds you can see examples of the occupancy network visualised: link to this video
On “Why Tesla removed radar and ultrasonic sensors [video]”
The Tesla AI day videos 1 go into some detail about this. They use multiple networks that are dedicated to specific tasks. 1link (2021), link to this video (2022)
On “Why Tesla removed radar and ultrasonic sensors [video]”
The replies to your comment don't seem to understand you at all. in the video link here link to this video he clearly states 16x dynamic range as a result of direct photon processing.
On “Tesla Again Paints a Misleading Story with Their Crash Data”
Exactly. There's no better facsimilie for the sheer variety of public roads than, well, public roads. Tesla even has rigorous simulation in place for hostile situations that should never occur on public roads: A good general overview from two minute papers: link Tesla's AI Day 2022 video, timestamped around labeling and simulation link to this video
On “The Waymo World Model: A New Frontier for Autonomous Driving Simulation”
>I've never really thought of Waymo as a robot in the same way as e.g. a Boston Dynamics humanoid, but of course it is a robot of sorts. So for the record, with this realization you're 3+ years behind Tesla. link to this video
