Connect with us

Published

on

Tesla is starting to release a new Full Self-Driving (FSD) Beta software update that includes many high-level changes that should positively impact performance.

FSD Beta enables Tesla vehicles to drive autonomously to a destination entered in the car’s navigation system, but the driver needs to remain vigilant and ready to take control at all times.

Since the responsibility lies with the driver and not Tesla’s system, it is still considered a level two driver-assist system despite its name. It has been sort of a “two steps forward, one step back” type of program, as some updates have seen regressions in terms of driving capabilities.

Tesla has been frequently releasing new software updates to the FSD Beta program and adding more owners to it.

The company now has over 100,000 people in the FSD Beta program and plans to expand it to everyone who buys access in North America by the end of the year through a few more software updates to refine the system.

Considering we are already in November and it generally takes at least a month for Tesla to deliver a new FSD Beta update, we expect Tesla is one or two updates away from the promised wider release.

Today, the automaker has started pushing a new FSD Beta update (v10.69.3) to employees for internal testing, which generally means that it will expand to beta testers in the customer fleet soon.

According to the release notes below, the update doesn’t include any new features, but it includes a lot of high-level updates to Tesla’s neural nets to improve the overall performance of the system.

Tesla Full Self-Driving Beta Release Notes v10.69.3 Release Notes via Not a Tesla App:

– Upgraded the Object Detection network to photon count video streams and retrained all parameters with the latest autolabeled datasets (with a special emphasis on low visibility scenarios).

– Improved the architecture for better accuracy and latency, higher recall of far away vehicles, lower velocity error of crossing vehicles by 20%, and improved VRU precision by 20%.

– Converted the VRU Velocity network to a two-stage network, which reduced latency and improved crossing pedestrian velocity error by 6%.

– Converted the non-VRU Attributes network to a two-stage network, which reduced latency, reduced incorrect lane assignment of crossing vehicles by 45%, and reduced incorrect parked predictions by 15%.

– Reformulated the autoregressive Vector Lanes grammar to improve the precision of lanes by 9.2%, recall of lanes by 18.7%, and recall of forks by 51.1%. Includes a full network update where all components were retrained with 3.8x the amount of data.

– Added a new “road markings” module to the Vector Lanes neural network which improves lane topology error at intersections by 38.9%.

– Upgraded the Occupancy Network to align with road surface instead of ego for improved detection stability and improved recall at hill crest.

– Reduced runtime of candidate trajectory generation by approximately 80% and improved smoothness by distilling an expensive trajectory optimization procedure into a lightweight planner neural network.

– Improved decision-making for short-deadline lane changes around gores by richer modeling of the trade-off between going off-route versus trajectory required to drive through the gore region.

– Reduced false slowdowns for pedestrians near crosswalks by using a better model for the kinematics of the pedestrian.

– Added control for more precise object geometry as detected by the general occupancy network.

– Improved control for vehicles cutting out of our desired path by better modeling of their turning/lateral maneuvers thus avoiding unnatural slowdowns.

– Improved longitudinal control while offsetting around static obstacles by searching over feasible vehicle motion profiles.

– Improved longitudinal control smoothness for in-lane vehicles during high relative velocity scenarios by also considering relative acceleration in the trajectory optimization.

– Reduced best-case object photon-to-control system latency by 26% through adaptive planner scheduling, restructuring of trajectory selection, and parallelizing perception compute. This allows us to make quicker decisions and improves reaction time.

FTC: We use income earning auto affiliate links. More.


Subscribe to Electrek on YouTube for exclusive videos and subscribe to the podcast.

Continue Reading

Environment

New GM, Porsche and Honda EVs boost US sales: Here’s a look at the top sellers in Q1

Published

on

By

New GM, Porsche and Honda EVs boost US sales: Here's a look at the top sellers in Q1

With new models rolling out from General Motors, Porsche, Honda, and several others, US EV sales increased by over 10% in the first three months of 2025. Nearly 300,000 EVs were sold in the first quarter of 2025. These were the top-selling models.

New EVs drive US sales growth in Q1 2025

Electric vehicle sales showed mixed results in the first quarter. Although Tesla is the center of attention as it continues to lose market share, several new EV models made an impressive debut.

With over 30,000 EVs sold in the first quarter, more than double the number sold last year, GM surpassed Ford and Hyundai Motor, placing second behind Tesla. GM’s Chevy is now the fastest-growing EV brand in the US, with the new electric Equinox, Blazer, and Silverado arriving.

GM sold 10,329 Chevy Equinox, 6,187 Blazer, and another 2,383 Silverado EVs in Q1. Thanks to its partnership with GM, Honda had an impressive sales quarter, selling over 14,000 EVs, including its luxury Acura brand.

Advertisement – scroll for more content

The Prologue SUV remained one of the top-sellers with 9,561 units sold in the first quarter, while the Acura ZDX added another 4,813.

Q1-2025-EV-sales-US
New Entries: EV sales volume in Q1 2025 (Source: Cox Automotive)

According to Cox Automotive, Honda led EV sales growth for new entrants in Q1, followed by Acura, Jeep, and Dodge.

Jeep sold 2,595 Wagoneer S models during the quarter, its first electric SUV sold in the US. Dodge, another Stellantis-owned brand, sold 1,947 Charger EVs, or what it calls the world’s first electric muscle car.

Although Chevy’s Equinox EV made a statement in Q1, Ford’s Mustang Mach-E remained the top-selling non-Tesla with 11,607 models sold.

Rank EV model Q1 2025 sales
1 Tesla Model Y 64,051
2 Tesla Model 3 52,520
3 Ford Mustang Mach-E 11,607
4 Chevrolet Equinox EV 10,329
5 Honda Prologue 9,561
6 Hyundai IONIQ 5 8,611
7 Volkswagen ID.4 7,663
8 Ford F-150 Lightning 7,187
9 BMW i4 7,125
10 Tesla Cybertruck 6,406
Top 10 best-selling EVs in the US in Q1 2025 (Source: Cox Automotive)

After introducing the upgraded 2025 IONIQ 5 (which now has even more range and an NACS charging port), Hyundai sold 8,611 electric SUVs in Q1, an increase of 26% from last year.

Porsche had the highest EV sales volume growth after launching the electric Macan. With 3,339 units added, the Macan EV made up for Porsche Taycan sales falling 18% to just 1,019.

Q1-2025-EV-sales-US
EV sales volume change by brand Q1 2025 vs Q1 2024 (Source: Cox Automotive)

As Cox Automotive Analyst Stephanie Valdez Streaty noted, “The year certainly started strong, but the road ahead will be anything but smooth.”

Trump ending federal incentives and introducing new tariffs will “pose a monumental challenge for many automakers,” according to Valdez Streaty. Despite several new models arriving and significant incentives being offered (at least for now), the rest of 2025 “will likely be a volatile one for EV sales in the US.”

Ready to score some savings while they are still here? We can help you get started. You can use our links below to find deals on the top-selling EVs in your area.

FTC: We use income earning auto affiliate links. More.

Continue Reading

Environment

Electric concrete pump truck can drive 30 miles, pump 65 cubic yards [video]

Published

on

By

Electric concrete pump truck can drive 30 miles, pump 65 cubic yards [video]

Based on a capable Volvo FM Electric 8×4 chassis, Putzmeister revealed one of the world’s largest all electric concrete pump trucks at the bauma equipment expo in Munich, Germany this week. The zero-emission concrete pumper can up to 50 km and pump approximately 50 cubic meters of concrete on a single charge.

50 km (a little over 30 miles) and 50 cubic meters (about 65 cubic yards) may not seem like impressive numbers, but consider this: a single cubic yard of concrete weighs a little over 4,000 lbs. (2 tons). A bit of simple math later, and you’ve got a quiet, vibration-free machine blasting (65 cu. yds ×4,100 lbs./yd = 266,500 lbs.) of construction material nearly 140 feet (42 meters) in the air.

That’s over 130 tons of construction material moved a really long way, and that’s (of course) without the use of diesel or gas.

“Volvo Trucks is the innovator when it comes to new technologies in combination with electric trucks. After presenting electric concrete mixers and heavy applications for mining, we are proud to show yet another world-class innovation for the construction segment here at bauma,” says Christoph Fitz, Head of Sales at Volvo Trucks in Germany. “With this electric pump truck, customers can have a zero-exhaust emission solution, low-noise operation and an efficient process thanks to the work-while-charging capacity.”

Advertisement – scroll for more content

The Volvo FM Electric-based concrete pump is motivated by a pair of electric motors developing a continuous 330 kW (442 hp) of output through the company’s proprietary I-Shift gearbox. The truck’s four battery packs add up to 360 kWh of capacity, which can DC fast charge at speeds up to 250 kW or operate continuously (pumping even more material) with grid power or PU500 remote power connection.

Electrek’s Take

There will surely be a few nay-sayers who’ll try to cite the relatively short-sounding range of trucks like this, or the 100-ton Tadano mobile electric crane, but the range is typically more than enough to operate in urban environments and motivate the asset across even the largest job sites. Additionally, the ability to plug in to grid power and operate 24/7 makes all of that quieter, safer, cleaner … and moot.

SOURCES | IMAGES: Putzmeister; Volvo Trucks.

FTC: We use income earning auto affiliate links. More.

Continue Reading

Environment

Wheel-E Podcast: China tariffs killing e-bikes, USB-C e-bike charging, more

Published

on

By

Wheel-E Podcast: China tariffs killing e-bikes, USB-C e-bike charging, more

This week on Electrek’s Wheel-E podcast, we discuss the most popular news stories from the world of electric bikes and other nontraditional electric vehicles. This time, that includes an analysis of how the Trump tariffs will affect e-bike pricing in the US, USB-C chargeable e-bikes launched by Ampler, Specialized e-bike recall, Juiced Bikes revived as a brand, kayak camping with the JackRabbit XG Pro, Walkcar’s new device that does the walking for you, and more.

The Wheel-E podcast returns every two weeks on Electrek’s YouTube channel, Facebook, Linkedin, and Twitter.

As a reminder, we’ll have an accompanying post, like this one, on the site with an embedded link to the live stream. Head to the YouTube channel to get your questions and comments in.

After the show ends, the video will be archived on YouTube and the audio on all your favorite podcast apps:

Advertisement – scroll for more content

Apple Podcasts

Spotify

Overcast

Pocket Casts

Castro

RSS

We also have a Patreon if you want to help us to avoid more ads and invest more in our content. We have some awesome gifts for our Patreons and more coming.

Here are a few of the articles that we will discuss during the Wheel-E podcast today:

Here’s the live stream for today’s episode starting at 9:00 a.m. ET (or the video after 10:00 a.m. ET):

FTC: We use income earning auto affiliate links. More.

Continue Reading

Trending