Interesting article with good points, but some of it is pretty silly:
> To be fair, “Testing Robustness” is followed by a written comment indicating that a “person (not shown) drives the robot up to the door, points the hand at the door handle, then gives the ‘GO’ command, both at the beginning of the video and again at 42 seconds.” The rest of the time the robot presumably executes its routine without human intervention. But this kind of task-and-time-limited autonomy has been around for decades, while few people know what “driving” the robot to the lab door means or that a teleoperator is necessary for nearly all of its movements.
Come on. We know how to make robots that walk to doors. The whole point of the video is to show the robustness of the robot in attempting to open the door. I couldn’t care less if someone drove it to the door then started the program.
I love those videos. Maybe I'm jaded, but I never assumed they were autonomous... hell, it's hard enough to get a game AI character to open a 'door.' The mechanical aspect, on the other hand -- the balancing and movement -- is very impressive.
If it was me, I'd ditch the entire AI aspect, and just hire a thousand offshore workers at pennies an hour to remotely command my 1,000 ATLASes as they march across (insert name of country you want to invade.) Sort of like drones that fly across the Middle East while being piloted by humans from a nice, safe, air-conditioned office in, for instance, Lackland AFB.
> Boston Dynamics has made little progress in robot autonomy, whatever we might think of abandoning the old folks to nonhuman machines. It is simply not its forte.
Eh? They are absolutely in the lead of autonomous, dynamic robotic motion.
There is just a long, long road to "full" autonomy.
4 comments
[ 0.13 ms ] story [ 1137 ms ] thread> To be fair, “Testing Robustness” is followed by a written comment indicating that a “person (not shown) drives the robot up to the door, points the hand at the door handle, then gives the ‘GO’ command, both at the beginning of the video and again at 42 seconds.” The rest of the time the robot presumably executes its routine without human intervention. But this kind of task-and-time-limited autonomy has been around for decades, while few people know what “driving” the robot to the lab door means or that a teleoperator is necessary for nearly all of its movements.
Come on. We know how to make robots that walk to doors. The whole point of the video is to show the robustness of the robot in attempting to open the door. I couldn’t care less if someone drove it to the door then started the program.
If it was me, I'd ditch the entire AI aspect, and just hire a thousand offshore workers at pennies an hour to remotely command my 1,000 ATLASes as they march across (insert name of country you want to invade.) Sort of like drones that fly across the Middle East while being piloted by humans from a nice, safe, air-conditioned office in, for instance, Lackland AFB.
Eh? They are absolutely in the lead of autonomous, dynamic robotic motion.
There is just a long, long road to "full" autonomy.