China To Host World's First Human-Robot Marathon (scmp.com) 12
Beijing will host the world's first human-robot half-marathon in April, with dozens of humanoid robots competing alongside 12,000 human runners in the capital's Daxing district. The robots, from more than 20 companies, must be between 0.5 and 2 meters tall, bipedal, and capable of walking or running without wheels, according to local authorities. Both remote-controlled and autonomous robots can participate, with battery changes permitted during the 21km (13 miles) race.
Walking is stupid (Score:4, Interesting)
Nearly all robotics research has gone into getting robots to walk. What was the point of that? It has almost no commercial value compared to wheeled transport (ok shut up about esoteric use cases). Where we need to have been focusing on is getting the robots to pick and place things better or even almost equal to a human. We need better grippers and better manipulation technology.
I'm saying why not spend all that capital and resources on getting close to passing the Robot Dexterity Turing test (I said close, because it's likely to be absolutely impossible to achieve, but then so many people say that about fusion)? I know it's fucking hard, but it's also what will make robots useful:
1. From a table on which there are about 20 screws of varying sizes strewn about confidently pick up only the eyeglass frame screw.
2. Place and screw the picked-up screw into an eyeglass frame
3. Pick up a single red m&m only from a table that has m&m strewn on it
4. Pick up a dry rice grain from a table.
5. From a small bag of various trinkets, feel around and pick out only the rubber band from it.
6. Sculpt a recognizable face on a small piece of clay
7. Assemble a standard lego set
8. Assemble a motor, including wrapping of stator wires
9. Sculpt a face into granite.
10. Draw the Mona Lisa.
No robotic hand or gripper is even close to being able to doing those.
Re: (Score:3)
Walking is important because despite wheelchairs and crutches, much of our environment is designed for people to traverse on two legs. We want robots that can go everywhere we can, with equal or better nimbleness.
Grip and object manipulation is just as important, but it is a parallel concern.
Re: (Score:2)
The corporations want walking bots so they can quickly swap failing humans out for robot equivalent. They don't want to redesign the workstations around a mobile, but not feet & legs mobile, bot. Gotta get that cog replacement jolly as directly as possible.
There are some mobility cases where walking / running would be a positive, but mostly I'm with you, manipulation above ground is something that should have gotten most of the focus. There's always ways around the bipedal issues so many are obsessed wi
Re: (Score:3)
I'm kind of fond of quadrupeds where the 'feet' are wheels. When walking is better, the wheels can lock. When rolling is better, the legs can lock. When you want a stationary platform, lock both.
Re: (Score:2)
Yup, every video I've seen of that configuration shows them 10x better and more agile than foot walkers. Only question is how tightly it can lock .. does it use a mechanical wheel lock with some kind of latch or just motor power?
Re: (Score:2)
The sole reason for human-like robots is to being able to replace humans in work situations where humans work, and humans work increasingly only where more specialized machines don't.
They're not for replacing more specialized robots or other machines optimized for very narrow tasks. Nobody needs a human-like robot to draw the Mona Lisa when you can just print it.
I agree that there's lots of room for improvement here, but walking is highly important because it makes robots mobile, in environments that are op
Re: (Score:2)
"In a fixed location there are much easier ways to sort screws by size or to remove a rice grain from a table."
The idea behind have a dexterous hand station is that you can get the efficiency and cost savings of mass manufacturing for one-off production. So right now there may be a machine configuration for putting screws in an object (though nearly all the videos I see of Chinese factories show humans doing that). But that machine is highly specific, so you can only justify buying one if you were going to
Re: (Score:2)
There's little point in doing anything of what you describe when the robot can't walk there and sit down at a table to begin with. There's also very little point in robots being universal when they can't walk from this job to another.
Um... ok...
In a fixed location there are much easier ways to sort screws by size or to remove a rice grain from a table.
Um... have you applied that logic to the robot need for walking? Robots going from one job to another - there are much easier ways to commute than to walk.
I don't think these are asking for enough of a challenge. Though it's great that we can design a task specific machine for something, it's really not all that impressive. What we should be aiming for is a "robot" that creates a tool that solves the problem. Table full of screws and you want them sorted? Robot makes a general purpose screw sorti
Re: (Score:1)
Re: (Score:2)
The market leader is Da Vinci which is mostly human-controlled, but they also have the more automated Ion system for specific tasks
https://www.intuitive.com/en-u... [intuitive.com]
Sigh (Score:2)
Gimmick vs demonstration (Score:2)
I think having the humans and human-controlled robots is unnecessary - on a prepared course the tech exists for fully autonomous robots to do this, and it could be a pure apples to apples performance comparison.