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.

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.

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.

How does this differ from Uber's recent AT deployment? https://arstechnica.com/tech-policy/2018/03/ubers-self-drivi...

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.

We should really have self driving trains by now.

I would love to hear balanced comparison between the various driverless systems. What are the key differentiators here?

undefined

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."

undefined