So they drove a bobtail tractor 7 miles on an empty straight road with a human-driven blocking vehicle to prevent anybody from passing. We could do better than that in 2005 with our DARPA Grand Challenge vehicle. Everybody in the DARPA Grand Challenge did better than that. And they call this a "product".
"Working with partners, we will use unmanned trucks to haul freight in 2018."
These guys are 5% of the way to where they need to be. This is a business where your bug reports are written in blood.
What they seem to have is an ordinary lane-keeping / auto brake system, like a lot of cars, plus drone-type remote control. All cameras, no LIDAR. Looks like a standard anti-collision radar in the front bumper. The steering motor doesn't seem to be redundant. This is demo-grade technology with too much hype and a tear-jerking video. They put that crap on the road and they're going to kill somebody.
Even Otto was better than this when they did their Budweiser demo on an empty road in Nevada. They at least had a potentially working technology. Years later, now owned by Uber, it still barely works.
You DARPA Grand Challenge guys certainly built some impressive stuff back then, and it's hard to shake a stick at what those teams accomplished.
The problem is, most of the industry has spent the last decade adding neat features and trying to improve their reliability...without much practical thought as to increasing controllability (in terms of accident avoidance) in the inevitability of a component failure.
Controllability has basically been shortcut by keeping a driver behind the wheel. We've done pretty significant testing - regularly hauling freight on the highway while in self-driving, no-one behind the wheel in super unstructured environments, dealing with extreme edge cases w/o intervention.
The big technical accomplishment that we're showing here, is that our system is controllable in the inevitable case of failure...without using a physically-present human as a crutch.
It’s open secret in the SDV industry that all the top players have remote assistants systems, and that it is the to key removing operators from the vehicle. It’s a little disengenus to claim that Starsky is the sole player exploring this space. There are startups that provide full remote vehicle control [0], and GM’s acquisition of Cruise 1.5 years ago was in part driven by an especially good demo of their remote assistance tech.
All that matters in the end is the safety and cost of the resulting system. Remote assistance operators and bandwidth are not cheap, and a system that has a high level of remote faults is most likely operating too far out of operational domain to be truly safe.
> without much practical thought as to increasing controllability
That's not fair, Waymo and others are using redundant backup systems and obviously try to think of every failure case they can. Besides, aren't the remote-control parts as likely to fail as any other? I sure as hell wouldn't want to drive a car over facetime...
This seems unnecessarily vitriolic. If someone has founded a self-driving truck startup that isn't going anywhere, who cares?
If Tesla's self driving truck division did a crappy demo then fair enough, but cut these guys some slack, at least they aren't in a cubicle at facebook trying to find better ways to sell ads for toilet paper.
It's completely fair and completely necessary. This isn't driving by any stretch. This is like comparing the Emacs Doctor to Alexa. I think it's the first time I clicked flag on a YC submission.
Edit: I think I overreacted a bit and shouldn't have flagged it. But I don't think the commenter you replied to did and can see why that comment is on top.
It's a bit harsh, but not unreasonable. You can buy this level of self-driving at many car dealerships right now. If you take the Udacity self-driving course, you could build this. Doesn't mean you're ready to ship a road-ready product. Remote control helps some, but it won't get you out of trouble. By the time the remote driver is connected and has situational awareness, it's too late.
This isn't webcrap, where it doesn't really matter if it fails now and then. People die when self-driving vehicles screw up. Especially with heavy vehicles. California DMV doesn't allow self-driving heavy vehicles on the road yet, and that's probably a good decision.
If YC is going to fund stuff like this, they need to get some avionics people on the team. Before they kill somebody.
To be fair, this is an absurdly competitive space. If they achieved something of similar magnitude for a problem dozens of other teams weren't already solving, it would seem much more impressive.
> If they achieved something of similar magnitude for a problem dozens of other teams weren't already solving, it would seem much more impressive.
Are you saying it would be more impressive if dozens of competitors weren't already doing what they're doing? I feel like you're arguing against Starsky's competence by pointing out that they're in a competitive space with noncompetitive technology.
I think the challenge of remotely controlling a truck is not the technology. There are lots of videos on youtube of guys who convert cars to remote controls in their garage. Mythbusters did it regularly for some of the car-related myths. (I do not mean to belittle the work of Starsky Robotics, just noting that they're "formally" doing stuff that people have already been doing for a while now).
The challenge is; who changes a flat tire? who inspects the vehicle after it's been parked? who hooks up all the break lines to the trailer? who gasses it up? who will check that the idiots on the dock loaded it correctly? who will smell the burning brakes on a steep incline? how will stranded trucks be rescued? The driver is kind of like a guardian of the freight, always looking out for the delivery's best interest, no matter the issue.
It's waaayy more of a business process and parternship problem than a technology one. You're going to have to negotiate contracts with tow truck companies and service stations across the continent. You're going to have to figure out some way to cross borders without a truck driver. You're going to have to hire all sorts of operations staff to manage the trucks. I'm actually much more curious about this aspect of the problem than the technology problem. I am tempted to think it takes more people to manage remote trucks than just having a driver.
That's a fair thought when you compare unmanned trucks to O/Os, who really do bust their butts to make sure the freight gets there.
The use case that we're solving to is the big company driver who, at the first sight of trouble, calls dispatch to send out a tow truck so that they don't waste precious hours of service. The folks who use the full-service gas stations to fill up.
A lot of long-haul truck driving has already been setup to limit the participation of the on-board driver. We're just taking that a step further.
Thanks for the response! Admittedly, I haven't had much exposure to long-haul trucking. My uncle did short hauls around the province, so my comments come from hearing his experiences over the years.
I think things would adapt to the automation, everything about trucks / freight is built for humans. If trucks could hand off their freight from one truck to another automatically that would help a lot. Smaller containers more trucks could help a lot. I would think the managment of trucks / freight can be done as a service. Tow trucks could be automated. Everything about freight/trucks would look different once it hits a tipping point. But I think it's going to take a while to get there.
You could just pay and operator to be on site and manage all that. They'd even have better engagement and awareness of 9ther issues if they didn't have to drive the vehicle, just observe and handle any issues.
One of the issues I have with all the technological unemployment discussion. The ONLY reason automation will destroy jobs is due to greed. Good companies will now utilize there newly freed up and empower3d employees to 10x there productivity.
Good for Starsky, but from what I can gather after reading this article they are behind Embark, TuSimple, and even Otto - not to mention whatever Tesla, Daimler, and other big names are doing.
Self-driving trucks always seemed like a no-brainer to me, but as I start to actually examine the space I realize it's more complicated than I initially thought. It'll be fun to watch from the sidelines, but I suspect there will be 1, maybe 2 big winners in this space.
Not that I know of: none of those folks have actually taken the person out of the vehicle, and getting someone in the truck is the main problem the industry faces.
Similar some of to the others - we've hauled freight autonomously (we've actually hauled quite a bit of it), but we've also done yard jockey work in truck yards and done whole trips that didn't require a person in the vehicle.
So really this is just a demonstration of the truck being remote controlled and being monitored by a full-time driver in a remote location? Okay, I can see why that's an important tool to make this a viable product, but it doesn't scale and doesn't strike me as a differentiator (I know some of your competitors already do this).
Anyway, rather than argue, I wish you luck. I've got no horse in this race.
Why don't they just have remote control trucks (with really good feeds of sound/video/vibrations/etc) and outsource the driving to people in a low cost of living area? Imagining how drones are piloted in offices in innocuous shopping malls.
Latency and internet up time. Just from playing online multiplayer video games with people in the same city, there can be issues with this making video games unplayable for short periods.
We do that remote thing with military drones with pilots sitting in Nevada controlling drones in Afghanistan but the real time requirements for that are much lower, i.e. can fly for long periods without worrying about traffic or very restricted flight near areas needing traffic control /no dogfighting capability - they can fire a few missiles at mostly static targets on the ground.
Cool, that's what I figured, but I'm not entirely done with this line of thinking yet...
Has anyone done any estimates on what kind of latency requirements are necessary for that? There's got to be some mention of the reaction time interval or something somewhere?
^ That would be interesting me also for the perspective of understanding what new markets would be opened by what new wireless technology (à la disruption curves in Innovator's Dilemma)
What about a two-driver solution with two independent internet links?
Let's say there is an airport somewhere flat and with no trees, so let's assume LOS (Line of Sight) conditions. We want to provide a courtesy bus system, 24 hours a day, to drive around at speeds no more than 10mph. Shuffle people around terminals, to rental car lots, to designated ridesharing collection areas, etc.
...You want to give control of a huge, multi-ton vehicle to someone far away in another state (or God forbid, another country) based on how low you can pay them?
That might be a wonderful business case! Whole building somewhere packed with guys remotely driving trucks/Uber cars 800$/month. No visa issues, different shifts to be available 24/7 for client. And a private radio link to prevent connectivity problems.
I believe Disney is likely working on it for their monorails after they lost a driver. But who knows the status and it was more of a rumor but it would not surprise me given how much less friction their monorails theoretically have compared to automated trains.
I like the demo. I think it comes down to how many miles of totally un-manned driving they can rack up and record. If that number gets big enough, it's a real win in terms of demonstrating viability.
AFAIK, TuSimple (http://www.tusimple.com/index-en.html) is much more mature on autonomous trucks. At least they have completed more road test. Last July, "TuSimple completed a 170-mile public road test from San Diego, California to Yuma, Arizona using its Level 4 system."
TuSimple has definitely been doing some great stuff. We did a similar test (w/freight) for the first time in January 2017...have have been doing that a lot over the last 15 months
"Working with partners, we will use unmanned trucks to haul freight in 2018." These guys are 5% of the way to where they need to be. This is a business where your bug reports are written in blood.
What they seem to have is an ordinary lane-keeping / auto brake system, like a lot of cars, plus drone-type remote control. All cameras, no LIDAR. Looks like a standard anti-collision radar in the front bumper. The steering motor doesn't seem to be redundant. This is demo-grade technology with too much hype and a tear-jerking video. They put that crap on the road and they're going to kill somebody.
Even Otto was better than this when they did their Budweiser demo on an empty road in Nevada. They at least had a potentially working technology. Years later, now owned by Uber, it still barely works.