Posted on 12/10/2019 11:01:41 AM PST by C19fan
A self-driving truck has completed the first cross-country commercial freight run.
Plus.ai, announced its truck traveled 2,800 miles autonomously from California to Pennsylvania hauling a fully-loaded refrigerated trailer of perishable cargo.
The vehicle is fitted with advanced autonomous driving system that utilizes multimodal sensor fusion, deep learning visual algorithms and simultaneous location and mapping (SLAM) technologies.
The truck drove in autonomous mode across interstate 17 and interstate 70, while traveling through different terrains and weather conditions.
Although a safety driver and engineer were on-board, this journey, according to Plus.ai, validates ‘the system’s ability to safely handle a wide range of weather and road conditions.’
(Excerpt) Read more at dailymail.co.uk ...
It stopped in Pennsylvania because if it went into New Jersey, it would have been stuck in a traffic circle until it ran out of fuel.
Seems to me that driving long distances on an interstate is the easy part.
Comparing the software of safety critical systems to your desktop computer software is also apples and oranges.
The number one reason for fatalities on the road is distracted or impaired drivers. These vehicles will be immune from such problems, with both fail-safe and fail-operational backups.
Regarding impaired drivers, technology could help here with a combination of facial recognition and breathalyzer technology. Wouldn't be perfect, but could be done very well.
The bottom line is that computers and automation can help to make drivers safer, without supplanting drivers. That's preferable, because human oversight and back-up makes computers much safer.
Betting it can’t back up to a loading dock.
Don’t bet on it. Just got a 2017 Mazda SUV after being in ahoy and run from some idiot who left his license plate in the intersection.
Anyhoo, I have 7 cameras on the vehicle. Almost impossible to hot anyone in next lane or in front or behind when parking. A loading dock should be a piece of cake.
These things are using neural networks intensively, which is far from algorithm-based and is far more like how we process information. Sure, there’s still plenty of algorithms for path-planning, sensor fusion, etc. but the really hard stuff is all NN.
Consider that freeway driving has far fewer use cases than urban driving and you see why trucks will be the first to use the technology.
I’ve been writing software for 35 years and work with many OEM’s creating autonomous vehicles. I guarantee you it is coming. For passenger vehicles it is a different story, you need it to be far less expensive, along with the ability to handle far more complex scenarios - so besides from having a redundant system for fail-operational backup, the human will be told to take over, as they’re the backup to the backup. For commercial vehicles they don’t need to be cheap, you can have more than one backup with everything using high horsepower compute.
There’s still challenges but anyone saying “can’t be done” doesn’t understand the current state-of-the-art, it’s incredibly advanced technology. They’re on the roads today, still with a human but as the miles rack up and the error rates drop below human averages the truck driver will go away - NHTSA will allow it as they’ve already stated.
Future is now. Trucks running into low bridge.
https://www.youtube.com/watch?v=9k319Qfm01A
Automated ships : )
Automation is great.
Ships crashing into bridges and houses
https://www.youtube.com/watch?v=Y3yHWEu6uK4
#21 It stopped in Pennsylvania because if it went into New Jersey, it would have been hijacked by the mob.
They should never be autonomous. Why? The condition of the roads themselves, The term “rough service” is a huge understatement. Trucks are not “solid state”. There would be no profit in this trend because of downtime. Trucks do not make money when they are sitting on the side of the road with a load of perishables going bad. Have you ever physically worked on trucks in either fleet or retail maintenance and repair?
I have done both all my life, tens of thousands of them over the last 45 years. 95% of repairs needing done on heavy trucks now days are failed sensors, connectors, and wiring issues from extreme vibrations along with heating & cooling expansion & contraction. It would be impossible to maintain closed working circuits for these systems no matter how good the computer and software are. The power and signal delivery system for electronics are very unreliable with the minimal computerization they already have now. Intermittent momentary open circuits are a huge primary and perpetual problem with these systems.
Once had a whole fleet of 350 brand new trucks go down under load at about 10k like clockwork. And not just ours... Everyone who had one made that year. There were not enough sensors stocked and available for all these new trucks going down across the country, they could not make the replacements fast enough. The manufacturer was shipping sensors from/to all over the country to these broken trucks. It was perpetual for almost a year because they absolutely refused to redesign the sensor and kept replacing with the same bad sensors.
That one sensor cost our company millions and millions in late loads refused from the customers and delivery price renegotiation. The sensor? A simple coolant level sensor that was programmed to shut the truck down if they fail. Coolant level fine, but because of no reading from this unnecessary “go/no go” sensor all these trucks were rendered unusable by the computer. In the mean time neither Peterbilt or Cummins would step up and take responsibility for the sensor and warranty it. Both denied ownership of the part because the “cab computer” belonged to Peterbilt, and the “engine computer” belonged to Cummins. This sensor was one of those “marriage parts” of the two systems so they ended up blaming each other for the problem. Cummins engineers designed it, but Paccar/Peterbilt had it physically manufactured.
There is already a very fine line between profit and loss in that industry which absolutely depends on reliability and 100% up time. The less to break, the more dependable they are going to be. The electronic complication in this application and industry is already going far beyond that point and becoming grossly unproductive. Let alone the human nature factor that is never considered like the conflict between Peterbilt and Cummins over a simple “unneeded” sensor... A simple coolant level “sight glass” ALWAYS works and requires absolutely no wiring, power, or signal.
No, it has already gone beyond all common sense and logic, it is not needed, and should never happen. Let alone consider allowing electronics to actually physically control the vehicle... No matter how dependable it is claimed to be, it will still always be “driver error” anyhow. The engineers and makers will never take the blame for their own screw ups, so just let drivers be drivers. Just the perpetual open circuits alone in this system application will be far far more dangerous, less reliable, and less profitable.
I remember reading about that. My question was/is why didn’t someone just bridge the connector with a resistor of the appropriate ohms to fool the computer into thinking it was within operating range? I have done that on two pickups in the last 20 years when the sensors failed on trips away from services. I now carry spare sensors on every vehicle. They seem to be a weak point in the control system.
It was not just a simple old school “resistance” type sensor, that would have been better of course. These sensors had a chip with firmware, an engineer’s “better idea”. They work like a radio signal transceiver on a modified sine wave sending signals back and forth to the ECM using the power voltage as only a “carrier” just like a radio. Without the ECM, cab computer, and the sensor “handshaking” and “seeing” each other the ECM and cab computer software would both agree to go into self protection mode and shut the engine down.
There was absolutely no need for this as a default in that application. If the level was fine, the driver could have ignored the red light on the dash and got it back to the shop to be repaired AFTER the load was delivered. The previous years did indeed allow this advantageous ability to still USE the truck when this particular unimportant non-critical sensor went bad. Alerting a driver and completely disabling are worlds apart in logic and rationality.
They are making everything far far more complicated than it should ever or need to be. We do not need rocket scientists or software engineers designing trucks. Ever... :)
Wow! Why so complicated? Just, as you say, overkill. We have a canbus and we are going to use it!
Thing is, the ECM still had all the overheat monitoring and shutdown protections in place separately, and a working temp gauge on the instrument panel, So even if the coolant level was indeed shy, it still would have protected it’s self from overheating. The level sensor should have done nothing but just active a warning light. In no way should it have ever disabled the vehicle. It was just job security for over ambitious engineers who were bored and worried about being laid off. Keeping themselves employed with unneeded crap at the extreme cost and inconvenience of those who have to use the vehicle and those who have to work on the vehicle. :)
Yup. I supervise process control systems. In that roll I have to discourage engineers from overlapping features that are in danger of conflicting each other on a regular basis.
Here is a devious one for you, just one more actually engineered to break on purpose.
Dodge Ram Cummins with automatic trans and it’s own Trans computer. The computer software has overheat sensors and “derate” type protection in place. The sequence of control if it starts to overheat is to first kick it out of overdrive without any other indicators, then it kicks it’s self into neutral with no other indicators, then after a bit the red overheat warning light finally lights up last to let the driver know that the reason it has already done those previous is because it is overheating.
Now why doesn’t the red warning light indicator come on FIRST before starting to go through the physical self protection sequence?
So, a common thing to happen with these is the pin connectors on the trans temp sensor are very small pin connectors. After a few thousand miles these connectors get loose and can break contact inside the connector housing intermittently causing a brief open circuit. Because of this quick break in contact it makes the computer go through the whole self protection sequence, Kicks out of overdrive, and kicks into neutral, but it resets before the overheat light actually comes on.
This starts happening every time you hit a hard bump causing the connection to open a slip second. But it never does get to the point that the warning light comes on to alert you that the issue might be part of the trans temp sensor or wiring to that sensor. Because it was programmed to come on LAST rather than FIRST in the sequence. So the first thing that comes to mind for the driver is that the trans is actually failing, and repair shops are NOT going to argue, and will agree with the driver because it is big money for them.
I know for a fact that thousands of transmissions were replaced that did not need to be replaced because of how this sequence was programmed in, when a simple easy to fix loose connector terminal and the computer sequence was actually the problem. If the warning light came on first in the sequence instead of last, this would have prevented all of it.
“Yup. I supervise process control systems. In that roll I have to discourage engineers from overlapping features that are in danger of conflicting each other on a regular basis.”
Good for you! Because there is far too much of that happening!
Disgusting. Was that after the merger with the Euros?
Believe it or not, before. And aside from the purposeful programming, the main cause was wanting to save 2 cents on the cost of the connector. The style previous had “less” issues because the metal terminals inside were larger and more robust as to lock together better and not vibrate loose. So to save just a couple cents per connector plug, they went to the mini pin type connectors which still have tons of connection issues like this in every application they are used. And now EVERYONE uses these. In this case if the connector to the temp sensor had not vibrated loose none of the following would have happened.
Which comes back to my original point about how highway vehicles are NOT SOLID STATE, and if you use them at all, sensors, wiring, and connector systems are never going to be reliable enough to support any type of extremely complicated autonomous system. The “fail safe” system will be rendering the vehicle disabled perpetually and consistently for safety reasons. They will become unusable more than they are usable. Disabled more than they are operational. It really is a road we just should never even take.
I appreciate your comments. There’s so many changes happening in the entire automotive field right now. That includes electrification, where there’s less to go wrong. Look at what Nikola Motors is doing.
It’s a hydrogen based fuel cell with electric drive. Other’s considering Lithium Ion batteries. So while I’m no Tesla fan-boy I do appreciate the way they’ve challenged all the auto makers and advanced many technologies.
I can only stress that the Volvo’s and Daimler’s of the world are pouring money into developing them. There’s never enough drivers. They may have to have a network of engineers across regions to support problems, or have one riding in a train of trucks that can service many. Of course nobody knows exactly how it’ll all level out but it is coming - from companies that are well aware of the real world challenges.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.