Hacker News Reader

Comment by zitterbewegung | Hacker News Reader

Everyone comments about full self driving cars to consumers. Automating trucks would be much more trans-formative than cars .

View on HN

That's mostly because most people don't think about trucks at all. And economically speaking you're definitely right. But that isn't to say that there arent other ways that self driving cars can be transformative. I mostly walk everywhere, and at least 2-3 times a week I run across a hurried or inattentive driver that can't be bothered to stop before turning right on red, or turning left after waiting for traffic to clear without looking for pedestrians, or stop for pedestrians at an uncontrolled intersection. It would be a huge benefit to my quality of life to not have to worry about being killed by a selfish asshole like that.

I question how much peace-of-mind self-driving cars bring to the intersection situation. While the inattentive human drivers are annoying, they're also predictable. As a pedestrian, I just wait for the driver to look up and go (or stop) before I proceed. The behavior of self-driving cars is, in my opinion, much harder to predict. Who knows when the buggy control software will cause the car to slam on the gas? Of course the software will be carefully written and tested. However, anyone who writes software for a living knows that carefully written and tested code often goes against economic incentives like "release fast" and "add more features to sell more".

Why?

Most of the automation efforts revolve around "drive on the highway from point A to point B" scenario. If you have a container that's that simple, rail is much more cost-effective.

Trucking has fairly complex loading/unloading requirements, with scenarios such as "haul 8 vehicles, unload them at 8 different addresses", "haul a load of tomatoes and lettuce, do 5 drops at In'n'Out locations, 1 at Safeway, 1 at Albertsons" fairly common. There's an understandable lack of trust in the system, where the trucker is also responsible for ensuring the staff on the recipient side is not unloading (i.e. stealing) too much or helping themselves into another customer's load.

There's also "stop and wait your turn at weight stations", "stop to refuel" as well as "stop at random checkpoints when crossing state borders" scenarios that seem to require just way too much of human involvement.

Uber's "Otto" is already making autonomous trucks.

You're describing a traveling salesman problem - which there are plenty of working solutions (even if we don't know the best solution yet) And then an autonomous forklift problem - there are a few companies already making them. And packaging + placement can simplify any issues if they exist. Maybe throw in a robotic arm in the back of the truck for good measure.

Autonomously refilling a tank of gas could be a fun problem to solve. But full service stations already exist. Those should be able to stand in until there is a better solution, such as Tesla's battery swap stations but for trucks.

Now, without a human driver the trucks can be working 24/7. No need for sleep. Which might be worth it even if a human accompanies the truck and just sleeps in a back section. Also who wants to pay a person to drive a truck, when the truck can drive itself for free?

an automated truck doesn't mean a driverless truck. it means the driver can be sleeping/tweeting/whatever during the boring hours between checkpoints/stops.

So level 3 vs level 4 autonomy, in other words? Usually when people use the word "automated", they imply level 4.

I agree any sort of driver assistance tech at level 3 and below is beneficial for public safety, I am not sure it's an industry game changer.

The levels overlap and vary by environment. Your truck can be level 5 on long stretch of highway, but then ring alarm bells and (if necessary, if the driver does not take over) slow down to a graceful stop on the shoulder before exiting the highway or maneuvering through a checkpoint or delivery.

Automating trucks could also be simpler over long, boring stretches of highway than navigating complex city streets, lights, and cross-traffic, especially via brute-force - simply mapping the entire highway in high detail.

Maybe someday. Automation could be a significant safety win for the highway given tired drivers today and could increase utilization as well. But I strongly suspect that there are too many reasons to keep a human present and in the loop (at least relatively near-time) to dispense with drivers entirely.

In addition, societal issues of unemployed drivers aside, are the economics of having human drivers really such an impediment to shipping goods economically today? At least in the US, rail is mostly used for long distance shipments which is effectively automated--to a first approximation.

I wouldn't call myself a truck driver but I drive enough on highways to feel the problem.

Highway driving takes its toll on the driver. You're usually on a single lane, maintain distance from car before and follow speed limit.

Just lane following and adaptive cruise control and make this journey a lot less tiring.

Absolutely. A lot of people are fixated on the (IMO many decades out) "Johnny Cab" whereas there are potentially significant safety and driving comfort gains just from autonomy with, say, a 1 minute handoff time for limited access highway driving. And that seems much more achievable over the next decade or so.

(And even the sort of features you can buy today in luxury cars are pretty nice from what I see.)

>Automating trucks would be much more trans-formative than cars

This is already in-progress and isn't that transformative. To most people the delivery or long-distance truck drivers pretty much are invisible driver less machines.

Uber agrees:

https://www.wired.com/2016/10/ubers-self-driving-truck-makes...

The truck only autonomously drove on a limited access highway. A human driver actually made the delivery.

That would be the first real step, right? That rather changes the scope of the big rig driving job.

I imagine automating limited access highway travel is much easier than automating the "final mile". I actually can see this sort of thing happening well before cars are automated to be honest.

True...I was objecting to the wired headline: >UBER’S SELF-DRIVING TRUCK MAKES ITS FIRST DELIVERY: 50,000 BEERS

In order to see most of the benefit from self driving trucks, you need a fully autonomous vehicle that can travel without a person paid to sit in it, right?

No, even packs of 3 trucks with 1 driver (on the interstates or other long distance routes) would be substantial savings (and a huge impact on employment).

Or out source them

Have one person remotely control 100 self driving trucks simultanously

Reply on news.ycombinator.com