Connect with us
Cruise car in San Francisco streets Cruise car in San Francisco streets

News

Cruise CEO explains robotaxi fleet’s human remote assistance system

Credit: Cruise

Published

on

Cruise CEO Kyle Vogt recently responded to allegations that the company’s driverless robotaxis are not really autonomous since they require frequent help from humans who are aiding the vehicles in a remote operations center. In a post on Hacker News, Vogt argued that Cruise’s robotaxis are only being remotely assisted 2-4% of the time on average. 

“Cruise AVs are being remotely assisted (RA) 2-4% of the time on average, in complex urban environments. This is low enough already that there isn’t a huge cost benefit to optimizing much further, especially given how useful it is to have humans review things in certain situations,” Vogt wrote.

Vogt’s comments came on the heels of a report from the New York Times, which alleged that Cruise workers intervened to help the company’s driverless robotaxis every 2.5 to 5 miles. The Cruise CEO noted that the detail shared by the NYT referenced how frequently Cruise robotaxis initiated a remote assistance (RA) session, but many of these RA sessions are resolved very quickly. 

“The stat quoted by NYT is how frequently the AVs initiate an RA session. Of those, many are resolved by the AV itself before the human even looks at things, since we often have the AV initiate proactively and before it is certain it will need help. Many sessions are quick confirmation requests (it is ok to proceed?) that are resolved in seconds. There are some that take longer and involve guiding the AV through tricky situations. Again, in aggregate, this is 2-4% of time in driverless mode,” Vogt explained. 

The CEO’s comments were supported by a spokesperson from Cruise, who noted in an emailed statement that a remote assistance session is triggered roughly every 4 to 5 miles. This effectively corrected the NYT‘s report, which noted that Cruise’s RA sessions were triggered roughly every 2.5-5 miles. 

“Oftentimes, the AV proactively initiates these before it is certain it will need help, such as when the AV’s intended path is obstructed (e.g construction blockages or detours) or if it needs help identifying an object. Remote assistance is in session about 2-4% of the time the AV is on the road, which is minimal, and in those cases, the RA advisor is providing wayfinding intel to the AV, not controlling it remotely,” the Cruise spokesperson said. 

Advertisement
-

Cruise was once considered a leader in the autonomous robotaxi segment. However, following an incident that resulted in a pedestrian — who was previously hit by a human-driven car — getting run over and dragged on the road by a robotaxi, the California DMV suspended the company’s driverless permit. Cruise would later pause its robotaxi operations across its entire fleet. 

Don’t hesitate to contact us with news tips. Just send a message to simon@teslarati.com to give us a heads up.

Simon is an experienced automotive reporter with a passion for electric cars and clean energy. Fascinated by the world envisioned by Elon Musk, he hopes to make it to Mars (at least as a tourist) someday. For stories or tips--or even to just say a simple hello--send a message to his email, simon@teslarati.com or his handle on X, @ResidentSponge.

Advertisement
Comments

News

Tesla has a ‘no human contact’ approach for Semi production

Published

on

Tesla is advancing a fully automated pipeline for the 4680 battery cells used in its all-electric Semi, spanning production from Giga Texas through shipment and direct consumption on the line at the new dedicated Semi Factory in Sparks, Nevada.

The approach was outlined by Tesla at its September 24 Semi Handover event, which launched high-volume production at its new 1.8-million-square-foot plant in Nevada, which sits adjacent to Gigafactory Nevada and is designed for an annual production rate of 50,000 trucks per year.

After years of pilot builds and what was a four-year-long redesign of the truck, Tesla moved the Semi from 2170 batteries to its in-house 4680 cells, which are made in Austin. The change cuts battery mass and total energy while holding range, a key step in making volume production a realistic possibility.

Cells will leave Giga Texas in trailers, and at the Nevada Semi plant, Tesla intends for a dedicated line to unload those trailers automatically, station the cells, and feed them straight into pack and vehicle assembly.

Both Lars Moravy, Tesla’s VP of Vehicle Engineering, and Dan Priestley, the Head of Tesla’s Semi program, described the goal as a “zero human touch point” from the moment the trailer arrives in Texas until a finished Semi drives off the production line in Nevada.

The unloading system that Moravy and Priestley described is just one piece of a much broader automation push. The plant uses what Tesla calls the highest-capacity electric monorail conveyance in vehicle manufacturing, carrying frames-in-white simultaneously. Powder-coating replaces conventional paint, and many processes that would normally require operators have been designed out.

Tesla has repeatedly said that “the best part is no part,” and the cell-handling plan extends that philosophy from the cell factory floor in Texas all the way to final assembly in Nevada.

If executed as described, the closed-loop flow would reduce labor, handling damage, and inventory buffers while tightening quality control on a component that represents a large share of the truck’s cost and weight. It also shortens the physical and organizational distance between two factories separated by more than 1,200 miles. The Semi itself now shares a bar-wound stator and other components with the Cybertruck, further linking Tesla’s passenger and commercial production systems.

High-volume output is expected to ramp gradually after the first trucks left the new line in April 2026. Early customers include PepsiCo, DHL, and U.S. Foods. Whether the automated trailer-to-line process reaches the promised zero-touch standard will be visible in the coming months as production scales. For Tesla, the Semi factory is another test of how far it can push “the machine that builds the machine” across sites.

Continue Reading

Elon Musk

Elon Musk’s AI Grok Bot can now handle banking while your Tesla FSD handles the road

Elon Musk says Grok Bot can manage your finances through linked bank and investment accounts.

Published

on

By

Concept of SuperGrok Bot handling banking in a Tesla via Grok
Concept of SuperGrok Bot handling banking in a Tesla via Grok

Grok Bot now wants access to your wallet, with SpaceXAI rolling out a new Finance integration for its agent platform that lets users link bank, credit card and investment accounts thereby letting their Bots help manage spending, investments and more. Elon Musk amplified the announcement on X with a short endorsement, “Grok Bot can manage your finances.”

The feature builds on two earlier steps. In early September, Grok gained the ability to answer questions about spending, savings, investments and cash flow using accounts connected through Plaid, starting with users in the U.S. Before that, on August 28, SpaceXAI let Grok Bot buy things online through Link, with users approving every spend request and the Bot receiving a single use card for each payment.

Musk has already shown how far he wants users to push it. In late August, when Tesla investor account Teslaconomics said he was weighing whether to give Grok Bot access to his bank accounts, Musk replied, “Try it out. If Grok Bot messes up, we will make you whole.” That promise goes beyond SpaceXAI’s consumer terms, which make users responsible for what their agents do and generally cap the company’s liability at the greater of fees paid or $100. SpaceXAI’s own documentation recommends requiring approval for purchases and financial transfers.

For Tesla owners, the update lands five days after Tesla brought Grok Bot into its vehicles, letting drivers hand off errands by voice while FSD (Supervised) handles the road. Bot access inside the car is currently limited to SuperGrok Heavy subscribers, though Connectors are open to anyone signed into Grok. With Finance linked, a driver could ask for a spending summary or a check on upcoming bills during the commute.

Grok’s role in the car has grown quickly since Tesla’s Summer Update let it control cabin features by voice. We have been using Grok Bot in our own Tesla for several weeks, and here’s how our latest test went.

Advertisement
-
Continue Reading

Elon Musk

SpaceX just got the green light Starship has waited years for

The FAA has cleared Starship Flight 14, setting up SpaceX’s first orbital attempt on Monday.

Published

on

By

SpaceX has cleared the last regulatory hurdle standing between Starship and its first trip to orbit. The Federal Aviation Administration issued the launch license for Starship Flight 14 late Saturday, keeping the mission on track for liftoff Monday, September 28, from Pad 2 at Starbase, Texas.

The 75 minute launch window opens at 7:15 a.m. Central, and Boca Chica Beach closures are also scheduled for September 29 and 30 as backup dates. This will be Starship’s first revenue generating mission.

The license was the missing piece after SpaceX completed a full wet dress rehearsal with Booster 21 and Ship 41 on September 24. At the time, the company said the flight remained on track pending regulatory approval. Because Flight 14 flies an orbital profile, the FAA had to sign off on a modified license that met its safety, payload and financial responsibility requirements.

Observers combing through the new FAA paperwork also noticed that lightning no longer appears among Starship’s listed launch hazards. If that holds, it matters more for where Starship is headed than for Monday’s attempt. Florida and Louisiana, home to LC-39A and the planned Starbase Louisiana site, see some of the most frequent lightning in the United States.

SpaceX tells the FCC that Starship Flight 14 is going to orbit

Flight 14 is the mission SpaceX has been building toward for months. Ship 41 will carry 26 Starlink V3 satellites, the first operational V3 units to be deployed, and attempt roughly six orbits at about 275 kilometers over a flight lasting just under 10 hours. SpaceX says the ship will only perform its orbital insertion burn after flight controllers confirm enough hardware redundancy remains for the deorbit burn at the end of the mission. Ship 41 is targeting a splashdown in the Pacific west of Chile, while Super Heavy will return to the Gulf of Mexico.

The date carries some symbolism as well. A Monday launch would come 10 years and one day after Elon Musk first presented the Interplanetary Transport System, the design that became Starship, at the International Astronautical Congress in Guadalajara, Mexico.

Advertisement
-

SpaceX has not announced what comes next, but air traffic planning slides reported this week, list Flight 15 no earlier than October 19 and a first Starship launch from LC-39A in Florida no earlier than October 30. Both dates depend on how Monday goes.

Continue Reading