TESLA – Artificial Intelligence & Autopilot – Tesla Bot

We develop and deploy autonomy at scale in vehicles, robots and more. We believe that an approach based on advanced AI for vision and planning, supported by efficient use of inference hardware, is the only way to achieve a general solution for full self-driving and beyond.


Build silicon chips that power our full self-driving software from the ground up, taking every small architectural and micro-architectural improvement into account while pushing hard to squeeze maximum silicon performance-per-watt. Perform floor-planning, timing and power analyses on the design. Write robust, randomized tests and scoreboards to verify functionality and performance. Implement compilers and drivers to program and communicate with the chip, with a strong focus on performance optimization and power savings. Finally, validate the silicon chip and bring it to mass production.

Neural Networks

Apply cutting-edge research to train deep neural networks on problems ranging from perception to control. Our per-camera networks analyze raw images to perform semantic segmentation, object detection and monocular depth estimation. Our birds-eye-view networks take video from all cameras to output the road layout, static infrastructure and 3D objects directly in the top-down view. Our networks learn from the most complicated and diverse scenarios in the world, iteratively sourced from our fleet of nearly 1M vehicles in real time. A full build of Autopilot neural networks involves 48 networks that take 70,000 GPU hours to train . Together, they output 1,000 distinct tensors (predictions) at each timestep.

Autonomy Algorithms

Develop the core algorithms that drive the car by creating a high-fidelity representation of the world and planning trajectories in that space. In order to train the neural networks to predict such representations, algorithmically create accurate and large-scale ground truth data by combining information from the car’s sensors across space and time. Use state-of-the-art techniques to build a robust planning and decision-making system that operates in complicated real-world situations under uncertainty. Evaluate your algorithms at the scale of the entire Tesla fleet.

Code Foundations

Throughput, latency, correctness and determinism are the main metrics we optimize our code for. Build the Autopilot software foundations up from the lowest levels of the stack, tightly integrating with our custom hardware. Implement super-reliable bootloaders with support for over-the-air updates and bring up customized Linux kernels. Write fast, memory-efficient low-level code to capture high-frequency, high-volume data from our sensors, and to share it with multiple consumer processes— without impacting central memory access latency or starving critical functional code from CPU cycles. Squeeze and pipeline compute across a variety of hardware processing units, distributed across multiple system-on-chips.

Evaluation Infrastructure

Build open- and closed-loop, hardware-in-the-loop evaluation tools and infrastructure at scale, to accelerate the pace of innovation, track performance improvements and prevent regressions. Leverage anonymized characteristic clips from our fleet and integrate them into large suites of test cases. Write code simulating our real-world environment, producing highly realistic graphics and other sensor data that feed our Autopilot software for live debugging or automated testing.

Tesla Bot

Develop the next generation of automation, including a general purpose, bi-pedal, humanoid robot capable of performing tasks that are unsafe, repetitive or boring. We’re seeking mechanical, electrical, controls and software engineers to help us leverage our AI expertise beyond our vehicle fleet.

Tesla Powerwall Rival Seeks to Bring Hydrogen Into Your Home


It’s about the size of Tesla Inc.’s Powerwall, but can store up to three times as much energy over a longer period.

That’s the promise of a new hydrogen-based energy-storage system for homes and businesses being developed by Australian startup Lavo Hydrogen Technology Ltd. The technology, developed with scientists at the University of New South Wales, uses power from rooftop solar panels to produce hydrogen from water by electrolysis. The gas is stored in a metal hydride container and converted back into electricity when needed using a fuel cell.

Australia’s world-beating rooftop-solar take-up rates make it an ideal early market, said Lavo Chief Executive Officer Alan Yu. The unit will go on sale from November, with installations starting in June 2021, subject to final approvals. The company plans to sell 10,000 units a year by 2022.

“Our mission is to try and change the way people live with energy,” Yu said in a phone interview.

Companies and governments are plowing billions of dollars into hydrogen as a potential cleaner alternative to fossil fuels such as natural gas. Still, commercial application of the fuel for use in heavy transportation and industrial processes such as steel-making is still seen as several years away.

At about triple the price of a Powerwall, the Lavo unit’s main selling point will be its ability to store more energy for longer. Each system will initially cost A$34,750 ($24,620) and will be able to hold 40 kilowatt-hours of power — enough to supply an average household for more than two days, according to the company. Tesla’s Powerwall holds about 13.5 kilowatt-hours.

Tesla founder Elon Musk has been critical of moves to develop hydrogen-powered cars, which compete with his own electric vehicles, arguing that hydrogen storage can never be as efficient as a lithium-ion battery. And investors are wary about bold claims for new hydrogen technology after startup Nikola Corp. was accused of misleading statements about its zero-emission trucks.

“Getting from laboratory to commercial-scale deployment is incredibly difficult,” said Jake Whitehead, fellow at the University of Queensland, whose research has examined the challenges of storing hydrogen on a large scale. He said electrolyzers need a lot of power and suggested that many household solar arrays may not generate enough electricity to run the system efficiently.

Lavo’s Yu acknowledged that the higher cost of the system might initially limit interest to energy-technology enthusiasts initially, but he also sees it as a solution for small off-grid rural villages to replace diesel generators or a compact solution for communities and homes cut off from the main grid by natural disasters such as bushfires.

From Bloomberg:

Tesla has unveiled in Los Angeles its new electric model, the Cybertruck, a pick-up with an extravagant design with up to 805 kilometers of autonomy capable of accelerating from 0 to 96 km / h in 2.9 seconds. Its production will begin in 2021 and will hit the market with a starting price of $ 40,000 (36,000 euros).

The Tesla Cybertruck, one of the safest pick-up or caravan vehicles in the world

Cybertruck is manufactured with an exterior chassis made to provide the greatest durability and protection for passengers. Starting with an almost impenetrable exoskeleton, all components are engineered to provide superior strength and solidity, from the ultra-rugged 30x cold-rolled stainless steel frame cladding to Tesla’s armored glass.


If there was something better, we would use it. Help prevent dents, damage and long-term corrosion with a smooth monochrome exoskeleton that places the chassis on the outside of the car and provides you and your passengers with maximum protection.30X ULTRA-RESISTANT COLD ROLLED STAINLESS STEEL

Regarding the other great claim in terms of foreign security by the new Tesla model, the  armored glasses  that Cybertruck mounts , called by the brand as Tesla Armor Glass, Elon Musk has once again used his Twitter account to demonstrate the Their resistance was once evident after one of them broke when tested in full presentation.


Ultra-tough glass and polymer-layered composite can absorb and redirect impact force to improve performance and damage tolerance. Regarding the other great claim in terms of foreign security by the new Tesla model, the  armored glasses  that Cybertruck mounts , called by the brand as Tesla Armor Glass, Elon Musk has once again used his Twitter account to demonstrate the Their resistance was once evident after one of them broke when tested in full presentation.