Menu

Timesdelhi.com

March 21, 2019
Category archive

robotics - page 26

GM’s Cruise sets special self-driving event for November 28

in Automation/Automotive/autonomous car/Cruise Automation/Delhi/GM/India/Politics/robotics/series/TC/television/Transportation by

GM’s Cruise self-driving unit is hosting a special event at the end of November, the company revealed today via invites to select media. The tagline for the event is “Come experience our vision of a self-driving future,” and while advance details are scarce, it sounds likely that Cruise will take the opportunity to allow media and other guests to experience their pilot self-driving ride hailing service.

The service is currently operating in San Francisco, using the self-driving Chevrolet Bolt vehicles that Cruise has equipped with autonomous hardware and software for self-driving. It’s only available to Cruise employees, however, in a pilot that offers pickups and drop-offs anywhere in San Francisco, and which uses an app for hailing vehicles.

Cruise has talked previously about how its testing experience in the dense urban environment of San Francisco has given it an edge in terms of optimizing its systems for the most difficult use cases faced by autonomous driving. The company also announced earlier this year that it’s going to begin building cars specifically designed for autonomous use at scale with GM, using the Bolt platform as a base.

If it’s gearing up to show people outside the company what it’s like to use its ride hailing service, it’s possible we’ll also get an update regarding a timeline for a public-facing service deployment.

News Source = techcrunch.com

Building the best possible driver inside Waymo’s Castle

in Artificial Intelligence/Automation/Automotive/autonomous cars/Delhi/Emerging-Technologies/India/Politics/robotics/self-driving/self-driving cars/TC/transport/Transportation/waymo by

Waymo has been very protective of its testing process in past, but recently it started opening up – likely as a bid to help get the public more comfortable with self-driving vehicle technology as it moves towards broad deployment of its autonomous cars. As part of that, the former Google self-driving car project asked a group of journalists to pay a visit to its Castle testing facility in Northern California.

The Castle isn’t just a very cool name for a proving ground, it’s the actual name of the former air force base (used during the 1940s for training bombers for WWII) that Google took over back in 2013 to house some of its ‘X’ projects, including Project Loon and what would eventually become Waymo in 2016.

At Castle, we got a rare look at one aspect of Waymo’s testing process for its autonomous cars, complete with a briefing on the company’s approach from CEO John Krafcik, VP of Engineering Dimitry Dolgov, UX and Early Rider Program Product Manager Juliet Rothenberg and Head of UX Design Ryan Powell.

Krafcik opened by giving a rundown of the various terms that have been applied to self-driving technology, ranging from “driver assistance” to “semi-driverless cars,” noting that there’s been “a lot of confusion about what the terminology means.” Part of Waymo’s aim is to clear up the confusion – and by implication, perhaps douse the cold water of reality on some of its competition’s more grandiose claims.

It also helps Waymo clearly explain where they sit on the spectrum of driverless vehicle technologies, and how they concluded that they would focus only on technologies that would classify as Level 4 and Level 5 by the SAE’s standards – fully driverless tech requiring no intervention by a human driver.

Waymo classifies anything from Levels 1 through 3 as technically “driver assist” features, according to Krafcik, and this is an “important divide” which Waymo has observed first hand, concluding early on that it’s not an area they’re interested in pursuing.

Krafcik revealed that one of the first products Waymo considered bringing to market back in 2012 and 2013 was a highway driving assist feature, which would handle everything. between onramp and exit, but that also required drivers to be fully attentive to the road and their surroundings while it was in operation.

The results, per Krafcik, were downright frightening: Footage taken from the vehicles of Google employees testing the highway assist features, which the company showed us during the briefing, including people texting, doing makeup, fumbling around their seat for charge cables and even, in one particularly grievous instance, sleeping while driving 55 MPH on a freeway.

“We shut down this aspect of the project a couple of days after seeing that,” Krafcik said. “The better you make the driver assist technologies… the more likely the human behind the wheel is to fall asleep. and then when the vehicle says hey I need you to take over, they lack contextual awareness.”

This is why Waymo has been very vocal in the past and today about focusing on Level 4 (full autonomy within specific ‘domains’ or geographies and conditions) and Level 5 (full, unqualified autonomy).

How does Castle enter into its goal of achieving that by “building the world’s most experienced driver?” In short: Practice.

Waymo likes to quantify its progress in terms of miles driven, since driving experience is the primary means of improvement for autonomous technology, according to it and many others in this space. Krafcik said at the event that Waymo has managed 3.5 million autonomous miles across testing in 20 different cities this year, and it managed 2.5 billion (with a ‘b’) miles in 2016 in simulation, or via testing in virtual software environments reflecting real-world conditions.

At Castle, you get aspects of the unpredictability of real-world driving, combined with the control of simulation. Stephanie Villegas, who leads ‘Structured Testing’ at Castle, explained that this type of testing allows them to model and stage challenging situations Waymo has encountered in real live, and also to validate things they know the cars have been able to do well when they issue updates to make sure there aren’t any regressions.

Structured Testing sounds kind of complicated but it’s actually explained in the name – Waymo sets up (structures) tests using its self-driving vehicles (the latest generation Chrysler Pacifica-based test car in the examples we saw), as well as things they call “fauxes” (pronounced “foxes” by Villegas. These are other cars, pedestrians, cyclists and other variables (contractors working for Waymo) who replicate the real world conditions that Waymo is trying to test for. The team runs these Tess over and over, “as many times as we can where we’re still seeing improvement” per Villegas – and each time the conditions will vary slightly since it’s real-world testing with actual human beings.

Waymo and Villegas took us through three structured tests, including one in which a passing car cuts off the self-driving van without much warning; one where the self-driving car has to deal with a vehicle backing out of a driveway on a corner; and one where it encounters movers in a roadway and has to navigate around them, while also heeding oncoming traffic.

The self-driving car handled every situation, all of which featured three test runs, with aplomb, and Villegas said that although Waymo always performs its tests with safety drivers on board, each of these was done fully autonomously with no intervention from the drivers at all.

In general, Waymo says it’s essentially nailed down Level 4 self-driving, especially in the controlled confines of its autonomous proving ground at Castle. We even got a ride in the self-driving Pacifica – without anyone even at the wheel at all – and it went smoothly (more on that here). But it doesn’t sound like Castle’s useful life is anywhere near at an end: Villegas said that she’s run countless Structured Tests in her time at Waymo since 2012, first at a semi-private and disused parking garage for the Shoreline Ampitheater near Google’s Mountain View HQ, and later at Castle when the company outgrew that space.

Getting Waymo’s tech ready for Level 4 autonomy in public deployment will require more testing still, as will making the eventual leap from Level 4 to Level 5, the company’s true ultimate goal. It’s not just a matter of having somewhere Waymo can test without worrying about state regulations – it’s about a place where serendipity can be manufactured, to help ensure its cars are ready for anything, without having to wait for them to encounter those scenarios on real roads when the stakes are highest.

News Source = techcrunch.com

Taking a truly driverless ride in Waymo’s Chrysler Pacifica

in Automation/Automotive/autonomous cars/Delhi/Emerging-Technologies/India/John Krafcik/Politics/robotics/TC/traffic/traffic light/transport/Transportation/waymo/X by

Today was a first for me: I drove in a fully autonomous vehicle on roads without anyone behind the wheel. They weren’t public roads, but they did have intersections, other vehicles, pedestrian traffic, cyclists and more, and the car managed a fairly long route without any human intervention – and without any cause for concern on my part.

I’ve done a lot of self-driving vehicle demos, including in Waymo’s own previous-generation Lexus test vehicles, so I wasn’t apprehensive about being ferried around in Waymo’s Chrysler Pacifica minivan to begin with. But the experience still took me by surprise, in terms of just how freeing it was once it became apparent that the car was handling shit all on its own, and would continue to do so safely regardless of what else was going on around it.

Waymo’s test track at Castle (more on that facility here) included multiple intersections with traffic lights, a roundabout, cars stopped on the shoulder, crossing foot band cycle traffic and more. Even if these were staged, they’d be hard to replicate in exact detail every time, so despite the fact that Waymo clearly had more control here than they would out in the real world, the driving experience was still impressive.

In particular, one event stuck with me: A squirrel (or other small rodent, I’m no expert on the fauna of Northern California) darted out quickly in front of the car, before turning back off the road – but the vehicle perceptibly slowed in case it needed to avoid it. Barring an incredibly lifelike animatronic, this isn’t something Waymo could’ve planned for.

Regarding how it actually works, once in the vehicle and buckled up, a rider taps a button to start the ride, and then displays mounted on the backs of the front seats show a visualization of what the car’s sensors see, but selectively simplified and redesigned to draw focus to things that riders find important, and to reassure them about the system’s competence and ability to spot all the key variables on the road.

This is essentially the same car driving riders around Chandler, in Phoenix, where the current Waymo pilot is operating. It’s still essentially a stock Pacifica van, with a premium trim upgrade, but included features in that vehicle, including the many USB ports for charging located throughout, the dual screens mentioned above on the seat backs, and the rear cabin AC and climate controls all make it particularly well suited to the task of putting the rider first.

I also noticed that the Pacifica drove in a manner which itself made me feel more comfortable as a rider, essentially by making it familiar. It edged into intersections cautiously, moved forward slowly when it had the right of way but its path was obstructed by a pedestrian crossing the street, and did a number of other things that made its driving feel more “human” than you might expect from an exacting computer system.

Waymo’s self-driving car ride won’t be my last, and it certainly wasn’t my first – but it was the first that suggested we might be closer than many think to Level 4 autonomous vehicles operating on public roads for a public customer base. When asked directly for a timeline on a public service launch, Waymo CEO John Krafcik declined to even claim a specific year, but he did say it’s probably going to happen sooner than many would believe.

News Source = techcrunch.com

Wonder Workshop raises $41M for its chatty robots that help kids learn to code

in Delhi/Education/India/Politics/robotics/TC/Wonder Workshop by

The Bay Area-based Wonder Workshop announced today that it has closed a $41 million Series C round of funding. The team has built a number of very cool little robots that kids can program on their mobile phone in a manner that helps them grasp at some computer science basics.

Tencent Holdings, SoftBank Korea, TAL Education Group, MindWorks Ventures, Madrona Venture Group and VTRON Group participated in the round, alongside some of the startup’s previous investors. Wonder Workshop raised $20 million in July of 2016 and has now closed more than $78 million in funding to date, according to Crunchbase.

There have been a handful of startups using hardware kits to let kids bring coding concepts into a more tangible setting. Wonder Workshop is unique in the way it thinks about robotics and CEO Vokas Gupta tells TechCrunch that their strategy is especially effective in ensuring that kids don’t stay in instructional “silos” and bring others into the experience.

“Robots are the natural way for multiple people to collaborate,” Gupta says.

Wonder Workshop’s programmable robots have been used in 12,000 elementary schools across the country. The startup has also put together its own robotics competition to teach kids STEM concepts.

With some of its new products, Wonder Workshop is looking to expand beyond instruction, from targeting 8-10-year-olds, to skills that are more engaging for pre-teens and teens.

Its latest friendly robotic coding companion, Cue, is for ages “11 and up.” The $200 robot launched last month and integrates a number of sensors that users can gather data from and control responses. It can be customized with a number of different “avatars” that give the robot a different personality.

Gupta tells me the new funding will be used to continue expanding the “global footprint” of current products while also investing in development of future devices.

News Source = techcrunch.com

Toyota will test autonomous cars at California’s GoMentum station

in Automation/Automotive/autonomous cars/Delhi/India/Politics/robotics/TC/Toyota/toyota research institute/transport/Transportation by

Toyota’s Research Institute will test its autonomous vehicle tech at GoMentum Station, a 5,000 acre proving ground for self-driving vehicle tech located in Walnut Creek, California. The proving ground will allow TRI to test out both its ‘Guardian’ and its ‘Chauffeur’ autonomous driving systems, which aim at automated safety protocols to assist human drivers, and full autonomy respectively.

TRI has just unveiled its platform 2.1 test vehicle, which includes new sensor hardware and compute, as well as updated version of its test systems. It’s also the first test car platform created by TRI that allows for testing of both Chauffeur and Guardian in the same vehicle – previously they required separate cars specifically tuned for each to test.

GoMentum station is one of 10 officially designated pilot proving grounds identified by the U.S. Department of Transportation earlier this year, as a way to help set the direction of policy making and testing procedures going forward. The GoMentum facility features simulated real-world driving conditions, including infrastructure like bridges and parking lots. It’ll help TRI to replicate some of the toughest conditions enounctemed by drivers and cars without having to wait for them to happen in real life.

This is just one new site in a number where Toyota Research Institute tests its vehicles, but it’s an important addition its ability to trial and prove out its autonomous vehicle systems.

News Source = techcrunch.com

1 24 25 26 27 28 32
Go to Top