Elon Musk started Tesla's AI Day 2022 by saying, "I want to set some expectations with respect to our Optimus Robot," just before the doors opened behind him. A robot walked out, waved at the audience, and did a little dance. Admittedly a humble beginning, he explained, "the Robot can actually do a lot more than what we just showed you. We just didn't want it to fall on its face." Musk's vision for the Tesla Robot, "Optimus is going to be incredible in five years, ten years mind-blowing." The CEO said other technologies that have changed the world have plateaued; the Robot is just starting.
Tesla's CEO envisions Optimus eventually being like Commander Data, the android from Star Trek the Next Generation, except it "would be programmed to be less robot-like and more friendly." Undoubtedly there is a long way to go to achieve what Doctor Noonien Soong created in Star Trek TNG. What was demonstrated onstage wasn't at that level, but several videos throughout the presentation highlighted what the Robot is capable of at its very early stage in development. The audience watched the Robot pick up boxes, deliver packages, water plants and work at a station at the Tesla factory in Fremont.
Development over 8 Months
The breakdown of some of the systems of the Tesla Robot
Tesla (Edited by Not a Tesla App)
The first Robot to take the stage at AI Day was not Optimus, but Bumble C, another acknowledgement to The Transformers, as Bumble Bee played a significant role in that franchise. However, Bumble C is far less advanced than Optimus, who did appear later but was on a cart.
Several Tesla engineers took turns on the microphone describing some of the most complex elements of the project that was first announced one year ago. Perhaps the best description of the project was the company moving from building a robot on wheels to a robot on legs. However, that may be oversimplifying. For example, the car has two motors, and the Robot has 28 actuators.
Overall Design and Battery Life
Tesla's brightest demonstrated how the production has come to life over the past eight months. It seems this group of computer masterminds had to become anatomist experts as Tesla took hints from the human body to create a humanoid robot. That is an essential factor in creating Optimus. Everything people interact with is made usable by a human, with two legs, two arms, ten fingers etc. If the Robot differed from what the world is already designed for, everything would have to change. However, recreating the human body and its countless movements would take far too long, so Tesla has stripped it down to less than 30 core movements, not including the hand.
Like the human torso contains the heart, the Robot's chest holds the battery. It's projected that a single charge would provide enough for a full day's work with a 2.3-kilowatt-hour battery. All the battery electronics are integrated into a single printed circuit board within the pack. That technology keeps charge management and power distribution all in one place. Tesla used lessons learned from vehicle and energy production to create the battery allowing for streamlined manufacturing and simple and effective cooling methods.
Autopilot Technology
Tesla showed what the Robot sees, and it looked very familiar. That's because the neural networks are pulling directly from Autopilot. Training data had to be collected to show indoor settings and other products not used with the car. Engineers have trained neural networks to identify high-frequency features and key points within the Robot's camera streams, such as a charging station. Tesla has also been using the Autopilot simulator but has integrated it for use with the Robot programming.
Tesla shows off what the Optimus robot sees
Tesla (Edited by Not a Tesla App)
The torso also contains the centralized computer that Tesla says will do everything a human brain does, such as processing vision data, making split-second decisions based on multi-sensory inputs and supporting communications. In addition, the Robot is equipped with wireless connectivity and audio support. Yes, the Robot is going to have conversations, "we really want to have fun, be utilitarian and also be a friend and hang out with you," said Musk.
Motors Mimic Joints
The 28 actuators throughout the Robot's frame are placed where many joints are in the human body. Just one of those actuators was shown lifting a half-tonne nine-foot concert grand piano. There have been thousands of test models run to show how each motor works with the other and how to effectively operate the most relevant actuators for a task. Even the act of walking takes several calculations that the Robot must make in real-time, not only to perform but also appear natural. The robots will be programmed with a locomotion code; the desired path goes to the locomotion planner, which uses trajectories to state estimations, very similar to the human vestibular system.
Human hands can move 300 degrees per second and have tens of thousands of tactile sensors. Hands can manipulate anything in our daily lives, from bulky, heavy items to something delicate. Now Tesla is recreating that with Optimus. Six actuators and 11 degrees of freedom are incorporated into the robot hand. It has an in-hand controller that drives the fingers and receives sensory feedback. The fingers have metallic tendons to allow for flexibility and strength. The hands are being created to allow for a precision grip of small parts and tools.
Responsible Robot Safety
Musk wanted to start AI day with the epic opening scene from Terminator when a robot crushed a skull. He has heard the fears and people warning, "don't go down the terminator path," but the CEO said safety is a top priority. There are safeguards in place, including designs for a localized control ROM that would not be connected to the internet that can turn the Robot off. He sees this as a stop button or remote control.
Optimus Price
Musk said the development of Optimus may broaden Tesla's mission statement to include "making the future awesome." He believes the potential is not recognized by most, and it "really boggles the mind." Musk said, "this means a future of abundance. There is no poverty. You can have whatever you want in terms of products and services. It really is a fundamental transformation of civilization as we know it." All of this at a price predicted to be less than $20,000 USD.
Tesla Shows Off its First Robot at AI Day 2
Subscribe
Subscribe to our newsletter to stay up to date on the latest Tesla news, upcoming features and software updates.
As December approaches, Tesla’s highly anticipated Holiday update draws closer. Each year, this eagerly awaited software release transforms Tesla vehicles with new features and festive flair. If you’re not familiar with Tesla’s holiday updates, take a look at what Tesla has launched in the Holiday update the past few years.
For this chapter in our series, we’re dreaming up ways Tesla could improve the charging experience and even add some additional safety features. So let’s take a look.
Destination State of Charge
Today, navigating to a destination is pretty straightforward on your Tesla. Your vehicle will automatically let you know when and where to charge, as well as for how long. However, you’ll likely arrive at your destination at a low state of charge.
Being able to set your destination state of charge would be an absolute game-changer for ease of road-tripping. After all, the best EV to road trip in is a Tesla due to the Supercharger network. It looks like Tesla may be listening. Last week, Tesla updated their app and hinted at such a feature coming to the Tesla app. A Christmas present, maybe?
Battery Precondition Options
While Tesla automatically preconditions your battery when needed for fast charging, there are various situations where manually preconditioning the battery would be beneficial.
Currently, there is no way to precondition for third-party chargers unless you “navigate” to a nearby Supercharger. If you need to navigate to a Supercharger that’s close by, the short distance between your location and the Supercharger will also not allow enough time to warm up the battery, causing slower charging times.
While we already mentioned Live Activities in the Tesla app wishlist, they’d be especially useful while Supercharging. Live Activities are useful for short-term information you want to monitor, especially if it changes often — which makes them perfect for Supercharging, especially if you want to avoid idle fees.
Vehicle-to-Load / Vehicle-to-Home Functionality
The Cybertruck introduced Tesla Power Share, Tesla’s name for Vehicle-to-Home functionality (V2H). V2H allows an EV to supply power directly to a home. By leveraging the vehicle’s battery, V2H can provide backup power during outages and reduce energy costs by using stored energy during peak rates.
Tesla Power Share integrates seamlessly with Tesla Energy products and the Tesla app. We’d love to see this functionality across the entire Tesla lineup. Recently a third party demonstrated that bidirectional charging does work on current Tesla vehicles – namely on a 2022 Model Y.
Adaptive Headlights for North America
While Europe and China have had access to the Adaptive Headlights since earlier this year, North America is still waiting. The good news is that Lars Moravy, VP of Vehicle Engineering, said that these are on their way soon.
Blind Spot Indication with Ambient Lighting
Both the 2024 Highland Model 3 Refresh and the Cybertruck already have ambient lighting features, but they don’t currently offer a practical purpose besides some eye candy. So why not integrate that ambient lighting into the Blindspot Warning system so that the left or right side of the vehicle lights up when there’s a vehicle in your blind spot? Currently, only a simple red dot lights up in the front speaker grill, and the on-screen camera will also appear with a red border when signaling.
Having the ambient lighting change colors when a vehicle is in your blind spot would be a cool use of the technology, especially since the Model Y Juniper Refresh and Models S and X are supposed to get ambient lighting as well.
Tesla’s Holiday update is expected to arrive with update 2024.44.25 in just a few short weeks. We’ll have extensive coverage of its features when it finally arrives, but in the meantime, be sure to check out our other wishlist articles:
It’s time for another dive into how Tesla intends to implement FSD. Once again, a shout out to SETI Park over on X for their excellent coverage of Tesla’s patents.
This time, it's about how Tesla is building a “universal translator” for AI, allowing its FSD or other neural networks to adapt seamlessly to different hardware platforms.
That translating layer can allow a complex neural net—like FSD—to run on pretty much any platform that meets its minimum requirements. This will drastically help reduce training time, adapt to platform-specific constraints, decide faster, and learn faster.
We’ll break down the key points of the patents and make them as understandable as possible. This new patent is likely how Tesla will implement FSD on non-Tesla vehicles, Optimus, and other devices.
Decision Making
Imagine a neural network as a decision-making machine. But building one also requires making a series of decisions about its structure and data processing methods. Think of it like choosing the right ingredients and cooking techniques for a complex recipe. These choices, called "decision points," play a crucial role in how well the neural network performs on a given hardware platform.
To make these decisions automatically, Tesla has developed a system that acts like a "run-while-training" neural net. This ingenious system analyzes the hardware's capabilities and adapts the neural network on the fly, ensuring optimal performance regardless of the platform.
Constraints
Every hardware platform has its limitations – processing power, memory capacity, supported instructions, and so on. These limitations act as "constraints" that dictate how the neural network can be configured. Think of it like trying to bake a cake in a kitchen with a small oven and limited counter space. You need to adjust your recipe and techniques to fit the constraints of your kitchen or tools.
Tesla's system automatically identifies these constraints, ensuring the neural network can operate within the boundaries of the hardware. This means FSD could potentially be transferred from one vehicle to another and adapt quickly to the new environment.
Let’s break down some of the key decision points and constraints involved:
Data Layout: Neural networks process vast amounts of data. How this data is organized in memory (the "data layout") significantly impacts performance. Different hardware platforms may favor different layouts. For example, some might be more efficient with data organized in the NCHW format (batch, channels, height, width), while others might prefer NHWC (batch, height, width, channels). Tesla's system automatically selects the optimal layout for the target hardware.
Algorithm Selection: Many algorithms can be used for operations within a neural network, such as convolution, which is essential for image processing. Some algorithms, like the Winograd convolution, are faster but may require specific hardware support. Others, like Fast Fourier Transform (FFT) convolution, are more versatile but might be slower. Tesla's system intelligently chooses the best algorithm based on the hardware's capabilities.
Hardware Acceleration: Modern hardware often includes specialized processors designed to accelerate neural network operations. These include Graphics Processing Units (GPUs) and Tensor Processing Units (TPUs). Tesla's system identifies and utilizes these accelerators, maximizing performance on the given platform.
Satisfiability
To find the best configuration for a given platform, Tesla employs a "satisfiability solver." This powerful tool, specifically a Satisfiability Modulo Theories (SMT) solver, acts like a sophisticated puzzle-solving engine. It takes the neural network's requirements and the hardware's limitations, expressed as logical formulas, and searches for a solution that satisfies all constraints. Try thinking of it as putting the puzzle pieces together after the borders (constraints) have been established.
Here's how it works, step-by-step:
Define the Problem: The system translates the neural network's needs and the hardware's constraints into a set of logical statements. For example, "the data layout must be NHWC" or "the convolution algorithm must be supported by the GPU."
Search for Solutions: The SMT solver explores the vast space of possible configurations, using logical deduction to eliminate invalid options. It systematically tries different combinations of settings, like adjusting the data layout, selecting algorithms, and enabling hardware acceleration.
Find Valid Configurations: The solver identifies configurations that satisfy all the constraints. These are potential solutions to the "puzzle" of running the neural network efficiently on the given hardware.
Optimization
Finding a working configuration is one thing, but finding the best configuration is the real challenge. This involves optimizing for various performance metrics, such as:
Inference Speed: How quickly the network processes data and makes decisions. This is crucial for real-time applications like FSD.
Power Consumption: The amount of energy used by the network. Optimizing power consumption is essential for extending battery life in electric vehicles and robots.
Memory Usage: The amount of memory required to store the network and its data. Minimizing memory usage is especially important for resource-constrained devices.
Accuracy: Ensuring the network maintains or improves its accuracy on the new platform is paramount for safety and reliability.
Tesla's system evaluates candidate configurations based on these metrics, selecting the one that delivers the best overall performance.
Translation Layer vs Satisfiability Solver
It's important to distinguish between the "translation layer" and the satisfiability solver. The translation layer is the overarching system that manages the entire adaptation process. It includes components that analyze the hardware, define the constraints, and invoke the SMT solver. The solver is a specific tool used by the translation layer to find valid configurations. Think of the translation layer as the conductor of an orchestra and the SMT solver as one of the instruments playing a crucial role in the symphony of AI adaptation.
Simple Terms
Imagine you have a complex recipe (the neural network) and want to cook it in different kitchens (hardware platforms). Some kitchens have a gas stove, others electric; some have a large oven, others a small one. Tesla's system acts like a master chef, adjusting the recipe and techniques to work best in each kitchen, ensuring a delicious meal (efficient AI) no matter the cooking environment.
What Does This Mean?
Now, let’s wrap this all up and put it into context—what does it mean for Tesla? There’s quite a lot, in fact. It means that Tesla is building a translation layer that will be able to adapt FSD for any platform, as long as it meets the minimum constraints.
That means Tesla will be able to rapidly accelerate the deployment of FSD on new platforms while also finding the ideal configurations to maximize both decision-making speed and power efficiency across that range of platforms.
Putting it all together, Tesla is preparing to license FSD, Which is an exciting future. And not just on vehicles - remember that Tesla’s humanoid robot - Optimus - also runs on FSD. FSD itself may be an extremely adaptable vision-based AI.
![Tesla Unveils V4 Superchargers Capable of Charging at 500kW [VIDEO]](https://www.notateslaapp.com/img/containers/article_images/charging/v4_supercharger.jpg/e6e109be929ba0765b4303a7e9d5bb7d/v4_supercharger.jpg)
![Tesla's Hidden 'Elon Mode' Unveiled: A Sneak Peek into the Future of FSD [Video]](https://www.notateslaapp.com/images/news/2022/fsd-beta-inside_300w.jpg)
