If there is a factory that allows a worker to step in front of a robot and depends on a wireless communication mechanism for safety, something is very very wrong.
There are hundreds of those things moving around, often with heavy loads (enough to injure if not enough to kill).
And it has been that way for years. [0]
[0] - https://www.wired.com/story/amazon-warehouse-robots/
EDIT : Adding Amazon’s page on robots that also talks about safety: https://www.amazon.science/latest-news/amazon-robotics-auton...
All of those robots leave enough threshold to avoid collisions with other robots should they need to stop suddenly. The robots do on device calculations and report back their status to the central server to help other robots route around "damage" (stopped robots, for example). Instead, they give the robots general path instructions with enough buffer area to allow the robots to not trigger their own on device collision sensing. In the links that you gave, it's very clear that the robots do not depend on communicating with a central server if a worker steps in front of a robot.
By the way, in warehouses without such advanced protection, humans are _absolutely_ banned from the floor and it's treated like any other large industrial scale operation, including fail safes on gates (if gate is open, do not allow restart and human presence sensing (often through a badge of some sort).
Failure of this sort would lead to massive liabilities to the warehouse and robot owners. They are heavily incentivized to do things the right way. I'm not saying it's perfect, but it's actually quite advanced and safe.
And it has been that way for years.
> The drives have enough smarts to move safely around humans, communicate with nearby robots so they do not collide, and report any problems like spills or obstructions back to the controller.
The robots are clearly designed to fail safe if they cannot communicate with the central controller. It would be an extremely poor design to have them operate in an unsafe mode in the event of interference in an unlicensed spectrum (or even a licensed spectrum, for that matter).
I am very much aware that robots have fail safes and all sorts of graceful failure modes.
What I was trying to communicate is that wireless communications is very much used for safety (positioning, allstop type commands, etc). The fail safes are there as a last resort (e.g. someone walking in front of it).
Still not sure I'm using the right words to describe my thoughts, so maybe I'm just tired. I appreciate all the feedback, though.
Nite.
A factory seems like a big space where there could perhaps be a predictable well known radio spectrum, and where that spectrum could reliably be monitored for stability. Unlike most spaces, there's a lot of possibilities for controlling the environment well, if you wanted; no end-user devices allowed, nothing but known systems.
This feels like you could very quickly get to some kind of known state. "We will be able to send priority signals within under 2ms." Or some such quality metric. Keep a signal analyzer going: any time this isn't met, everything goes into an independent failsafe shutdown mode until the issue is debugged and started up again.
Our instincts to judge & discard ideas & possibilities is so dangerous, is such a deep human peril. Your instinct feels like it comes from a good place, feels correct, but ultimately, this is acting in fear uncertainty & doubt, & your execution rests on no contentions other than it's own self certainty.
I think we must be much more thorough in our thinking & arguing, must not leap to discard ideas so quickly totally & casually; FUD must be rooted out deep within ourselves & challenged. Let not progress be onstructed by meek wills.
Sure, engineer the machines to immediately halt if a human is detected, but also design the system so that close physical proximity is never required.
I think I have gone through efforts to elaborate why I think high reliability is achievable over wireless systems. It seems irrational to me to hate wireless so.
If I were a squishy human in a factory, I feel like I would far far far prefer some highly reliable central systems with near godlike omniscience of the factory floor watch things, & use well quantified known wireless channels (albeit no WiFi that exists today, without a lot of other promises) to communicate, than rely on individual robots relying on embodied knowledge. You all sound like cranks to me, given how incredibly fantastically super seriously I would want the former, not the latter.
Because industry standard safety practices are there for a reason and taken very seriously. The parent poster said:
> allows a worker to step in front of a robot
and
> depends on a wireless communication mechanism for safety
But industry standard safety practices would ensure at least one of those is not true. What the person you are replying to is suggesting is that you can have robots with wireless safety mechanisms or you can have robots which people can walk in front of (which have wired safety mechanisms), you just do not want both. That is a pretty mild claim you are responding to.
I am a robotics engineer and we are very aware of the risks robots pose to human beings. Furthermore business management is very aware of the liability concerns these risks pose to the business.
It isn't FUD to say that we would not put humans in the path of a robot which had wireless safety systems. That's just a fact of standard practices.
https://webstore.ansi.org/industry/robotics/safety
https://www.osha.gov/robotics/standards
Of course the standards could be changed, or other standards could be adopted. But you really went on a pretty long rant about open mindedness in reply to a person who was making a factual and industry-standard statement about robots in factories.
In the airline industry they say the safety rules are written in blood, because after someone is killed they do a detailed investigation and update safety rules accordingly. I suspect that it is similar in robotics as industrial robots kill people all the time. Safety rules could be changed, but it's a perfectly normal thing for a person to say "you are unlikely to encounter said scenario because it violates the normal rules for doing the thing". If a person said "you are unlikely to see a new passenger car sold without seatbelts" that is not cause to chastise them about open mindedness, that is a boring normal statement that is factual and makes sense.