Investor's Corner
Tesla patents AR-based system for faster, more accurate vehicle production
Being a company led by an unorthodox CEO with roots in Silicon Valley, Tesla is on the bleeding edge of the automotive market. Tech is evident in Tesla’s DNA, from the automation in its factories to the deep integration of software on its electric vehicles. If a recently published patent is any indication, even more tech-driven solutions are coming to Tesla’s production lines.
A recent patent, dubbed as “Augmented Reality Application for Manufacturing,” was published last Thursday. In the description of the patent, Tesla noted that existing automotive manufacturing techniques are time-consuming and still require a notable amount of manual calibration and inspection. An example of this is the practice of marking joints and/or inspecting dimensional accuracy of car components by having workers manually overlay plastic molds over a sheet metal object to mark certain parts. These processes take a lot of time and effort, resulting in extra operational costs.
Tesla’s solution is rather simple. Instead of using manual processes to perform tasks that include setup, configuration, calibration, and quality inspection, it would be better to utilize available technologies to make operations faster and more precise. One of these technologies is computer vision and augmented reality tools.
Tesla’s patent uses AR applications and computer vision to “identify an object of interest and the relationship between a user and the object.” The AR device captures a live view of an object, determines the location of the device, as well as the type of the object of interest. By using this system, workers will be able to view instant data about the components they are working on.
“(For example), the AR device identifies that the object of interest is a right-hand front shock tower of a vehicle. The AR device then overlays data corresponding to features of the object of interest, such as mechanical joints, interfaces with other parts, thickness of e-coating, etc. on top of the view of the object of interest. Examples of the joint features include spot welds, self-pierced rivets, laser welds, structural adhesive, and sealers, among others.
“As the user moves around the object, the view of the object from the perspective of the AR device and the overlaid data of the detected features adjust accordingly. The user can also interact with the AR device. For example, a user can display information on each of the identified features. In some embodiments, for example, the AR device displays the tolerances associated with each detected feature, such as the location of a spot weld or hole.”
Apart from allowing production to move faster, the AR-based system could also be used for quality inspections. Tesla even noted that such a system could be tapped to determine if panels in vehicles are within tolerances, and if holes in the electric cars’ frames are drilled or punched at the correct location.
-
- An illustration of Tesla’s AR-augmented production system. [Credit: US Patent Office]
-
- An illustration of Tesla’s AR-augmented production system. [Credit: US Patent Office]
An illustration of Tesla’s AR-augmented production system. [Credit: US Patent Office]
“There are many practical applications for the augmented reality (AR) manufacturing techniques discussed herein. In some embodiments, the AR device is used to program a robot to assemble one or more parts including identifying and marking the precise location and order of welds, self-pierced rivets, laser welds, adhesives, sealers, holes, fasteners, or other mechanical joints, etc. As another example, the AR device can be used to inspect the quality of the assembly for a vehicle such as whether the locations of welds are correct, whether the interfaces between parts such as body panels are within tolerances, whether holes are drilled or punched at the correct location, whether the fit and finish of assembly is correct, etc.
“In some embodiments, vision recognition is utilized. Individual sheet metal components and/or assemblies that are or will be part of the body-in-white (also known as the structural frame or body) are recognized. Once the component/system has been identified, computer-aided design (CAD) information (e.g., information and/or symbols associated with the mechanical joints) is aligned/scaled and rendered on corresponding identified physical model components. The application of the disclosed techniques applies to many different contexts of manufacturing.
“For example, the AR device can be used to map the quality of a coating on an automotive part such as determining the thickness of an e-coating on a vehicle body and identifying problem areas that are difficult to coat. In some embodiments, the AR device is used to map out a factory floor and to identify the precise location and orientation robots should be installed at to build out an assembly line. The robots are positioned based on the AR device such that the installed robots will not interfere with each other or other obstructions in the environment.”
An AR-based system that augments production fits very well with Tesla’s reputation as a car maker that never stays stagnant. During an interview at Gigafactory 1, Tesla President of Automotive Jerome Guillen mentioned that the company’s battery cells — while already industry-leading — are always evolving. Elon Musk echoed this idea as well, when he noted that improvements to Tesla’s electric cars are being rolled out as soon as they are ready. Optimizations such as the use of AR and computer vision in the production line is yet another example.
Investor's Corner
Tesla has a Cybercab problem nobody saw coming
Tesla’s Cybercab line now builds robotaxis faster than Tesla can deploy them, Lars Moravy says.
Tesla’s Cybercab line in Texas can now build the two seat robotaxi faster than the company can put it into service, according to Lars Moravy, Tesla’s Vice President of Vehicle Engineering. “We don’t run every day because the line can run so fast. It’s currently outpacing our deployments,” Moravy said in a new Cybercab deep dive from Munro Live. “So, it’s a bit of a race right now. Who’s going to go faster? Right now the manufacturing line’s ahead.”
Tesla’s official Robotaxi account shared a Cybercab analysis video on X on Monday, calling it a “Cybercab engineering deep dive.” Moravy’s comments go further than what he told analysts on the Q3 earnings call last week, when he said the Cybercab line’s listed capacity of more than 125,000 units a year undersells what it can actually run.
The tour shows where that speed comes from. Tesla’s unboxed process splits the Cybercab into front, rear, side and center modules that are built and tested on their own before they meet on a short final line. That final line has just 25 fully automated stations, which Tesla’s team estimated is a fifth to a tenth of what a Model Y needs. The full line is about 78% automated, the framing line is already at 100%, and the layout uses roughly 50% less floor space per vehicle. The stated goal is “100% automation in 10 second cycle time,” or one finished Cybercab every 10 seconds.
Tesla also deleted the paint shop. Only the side modules are coated, and the exterior panels get their color inside the molding machine. Engineers said the car is designed to run at least 500,000 miles, which matters for a vehicle that will spend most of its day carrying riders.
The battery got the same treatment. The Cybercab uses an 88S6P pack of 4680 cells in a steel enclosure, a first for Tesla, with each module potted separately so a single failed module can be swapped instead of the whole pack. Wireless battery management boards replace a wiring harness, and new contactors are fast enough to drop the pyro fuse entirely. Tesla’s battery director graded the pack an A minus, compared with a D for the Model Y structural pack and a B minus for Cybertruck. Up front, the drive unit runs an 11:1 gear ratio versus roughly 9:1 on most Teslas, since the Cybercab does not need a high top speed.
Cybercab engineering deep dive — Robotaxi (@robotaxi) October 26, 2026
The deployment side is now the bottleneck Moravy described. Tesla had more than 50 Cybercabs working the Formula 1 weekend in Austin, and Texas records show 463 Cybercabs registered. Tesla said on its earnings call that Cybercab service will launch in Dallas next month, and Moravy said the company is aiming to get Cybercabs to customers by the end of 2026. Every unit built so far has gone into Tesla’s own fleet since the line moved into volume production in April.
Munro Live also asked when it could get a Cybercab to tear down. Tesla’s answer: “Not yet.”
Tesla (NASDAQ: TSLA) reported its earnings for the third quarter of 2026, marking a reasonable performance on the various financial metrics. Tesla still plans to hold a call that will field investor questions at 5:30 p.m. ET, 4:30 p.m. CT.
Here’s where Earnings came in:
- Total Revenues: $28.046 reported vs. $28.34B expected
- Non-GAAP EPS: $0.48 reported vs. $0.45 expected
- Operating Margin: 2.6 % reported vs. 2.5% expected
- Operating Income: $718M reported vs. $721M expected
- Free Cash Flow: $1.531B reported vs. ~-$4.51B expected
Tesla $TSLA Earnings Results:
Revenues: $28.046B
Non-GAAP EPS: $0.48
Operating Margin: 2.6%
Operating Income: $718M
FCF: $1.531B— TESLARATI (@Teslarati) October 21, 2026
Major Takeaways
Full Self-Driving (Supervised)
“FSD (Supervised)⁴ attach rate continued to grow, reaching over 75% of new vehicle deliveries in North America – our most mature market – a nearly twenty percentage point sequential increase. We believe that FSD is driving demand in markets where it is available, and we continue to work with regulators to get it approved in other markets.”
Tesla Semi
“We began volume production of Tesla Semi, our Class 8 heavy-duty truck. The top variant can go 500 miles at full 82,000 lbs gross combination weight while achieving an efficiency of 1.7 kWh/mile. That efficiency allows the Tesla Semi to use a third of the energy used by a comparable diesel truck to haul the same payload. In a transportation market where energy is one of the largest components of total cost per mile, this will provide a meaningful advantage to Tesla Semi operators.”
SI Compute
“We plan to reach 400 MW of SI training compute by the end of the year, supporting the development of both vehicle and humanoid robot autonomy software. Additionally, we continued construction for the Austin Fab, where we plan to start commissioning equipment in 2027.”
Robotaxi
“We began deployment of Cybercab into our Robotaxi fleet in Austin. We reached nearly two million cumulative unsupervised miles for our Robotaxi service as of the end of the quarter. Operating hours in Austin are now 6am to midnight, and we expect to reduce wait times via increased fleet supply and improvement of Robotaxi orchestration algorithms. Grok is available in Cybercab with access to Grok Bot and Connectors, which allows users to manage their inbox, calendars, files, chats and tasks – all hands free via voice command – making Cybercab a mode of transport, a productivity space and, with our entertainment options, a second living room.”
Interested in ordering a Tesla? Use my referral code for three free months of Full Self-Driving (Supervised) here.
Tesla (NASDAQ: TSLA) reports its earnings for Q3 today. Here’s what to expect, as the company will reveal its balance sheet after the market closes on Wednesday.
Tesla already reported deliveries just after Q3 ended, and it demolished Wall Street consensus estimates of roughly 462,000 vehicles. Tesla delivered 486,532 cars in the third quarter, which was a big beat, but was down 2.1 percent from the same quarter last year. Energy storage deployments were 13.7 GWh, up year-over-year.
Tesla showrooms picked clean ahead of Q3 end as demand looks strong
For the quarter, analysts have already compiled their predictions for what Tesla will report this afternoon:
- Total Revenues: $28.34B
- Non-GAAP EPS: $0.43
- Operating Margin: 2.5%
- Operating Income: $721M
- Free Cash Flow: ~-$4.51B
Here are a few things we are looking forward to hearing about on the call:
Automotive Gross Margin and Overall Profitability
This was 16.3 percent in Q2, down from 19.2 percent in Q1, and was impacted by warranty charges and some fading regulatory credits. Consensus implies overall gross margin near 18 percent, but a miss here would potentially reinforce concerns about pricing pressure on its vehicles.
Pay attention to energy storage margins as well, especially since Tesla missed GWh expectations, although it was still a strong quarter.
Robotaxi/Cybercab, Unsupervised FSD, and Optimus Progress
The Say questions from retail investors usually focus on these types of projects, and this quarter is no different. Scaling the Cybercab fleet beyond Austin amid the open NHTSA safety review, timeline for Unsupervised FSD in customer cars, Robotaxi unit economics, and Optimus cost per unit plus when it could start generating revenue, are all things to be looking for.
Any concrete timelines or regulatory path details will likely move the stock more than the near-term numbers. SpaceX merger speculation, which was detailed during SpaceX’s earnings call last night, may also surface, although the key details were shared last night.
Elon Musk just confirmed the Tesla and SpaceX merger step everyone was waiting for
Say Investor Questions
- How does the Cybercab fleet scale past Austin, and what’s the regulatory path outside Texas given NHTSA’s open safety review?
- When can we anticipate FSD unsupervised in customer cars?
- When will the CyberCab be available for customer purchase/ownership?
- What’s the unit economics per paid robotaxi mile, and how does it compare to the thirty-cent target?
- Tesla has acknowledged that HW3 vehicles cannot support unsupervised FSD. When will owners know whether they can upgrade their hardware for free, and when will Tesla provide a clear plan?
The full Earnings Call will be streamed this evening after market close around 5 p.m. this evening.
Starlink is ‘biggest competitive advantage,’ but it’s temporary, United CEO says
Tesla Cybercab’s unorthodox paint process explained
