I equally love and fear to see how far these robotics have come. Coming at it from a physical therapist’s perspective though - I think people don’t realize just how hard it is to walk. People believe that the hands and upper body are the most complex, but walking is by far some of the most challenging tasks we have to teach to people. I love to see the toe push-off on Tesla’s model, but it’s almost not enough. I also see that in neither video that the “knees” never are fully extended (straight). I’m sure there’s a mechanical component as to why they’re designed to keep that joint flexed, but it makes the robots look funny. There are probably a few things they’re lacking in the models they have currently that I would say need attention to improve their gait (walking). First, they need more articulation in the feet (more movable joints) rather than one hinge joint at the ankle and the other at the toes plus a spring. Specifically they need ankle plantar flexion, the ability to point the ankle down like a dancer, to get better toe push off and knee extension. Second, the torso needs to be able to rotate forward/back as it walks. These are just two of many suggestions. Here’s a video breaking down the mechanics of gait if you’re further interested!
You gave a great explanation regarding the shortcomings of the lower extremities, particularly the feet and the overall gait. It's amazing to reflect on how complex just the walking motion is and that we (humans) perform this with little to no active thought. There must be a lot going on behind the scenes in our brains.
Interesting, why are your expectations low? Do you think there are fundamental pieces of technology that are still a ways off before these become more impressive?
The whole thing is a glorified tech demo with zero practical application and will remain nothing more for a long time. Boston Dynamics Dancing robots are a fun act, too. This may sound overly pessimistic but achieving agility, dexterity and precision on a humanoid level will take many more years and even then, it will be very expensive, esp. when they fall over or get damaged ever so easily. Might be cheaper in the long run to clone people and program them to do certain jobs... oops, David Brin's Piecework, a recommended read. ;)
Thanks for the summary, David. These look like impressive improvements, but I keep my expectations in check in line with your reservations. Still, fascinating to see.
Thanks, Nathan! It's just one of those areas that is really difficult to know how close we are until someone get's a product out. I personally wouldn't mind if progress slowed down a bit.
Great summary! It'll be exciting to see just how Tesla intends to use these robots going forward and the impact they will have. I definitely see their top priority being to be use them in their own manufacturing centers to displace the rising cost of labor.
I am curious about their Optimus production capabilities, e.g., if they hand assembled it or they have a production facility. I think they will probably need 50-100 of these to really show them off. The labor market is about to change.
I equally love and fear to see how far these robotics have come. Coming at it from a physical therapist’s perspective though - I think people don’t realize just how hard it is to walk. People believe that the hands and upper body are the most complex, but walking is by far some of the most challenging tasks we have to teach to people. I love to see the toe push-off on Tesla’s model, but it’s almost not enough. I also see that in neither video that the “knees” never are fully extended (straight). I’m sure there’s a mechanical component as to why they’re designed to keep that joint flexed, but it makes the robots look funny. There are probably a few things they’re lacking in the models they have currently that I would say need attention to improve their gait (walking). First, they need more articulation in the feet (more movable joints) rather than one hinge joint at the ankle and the other at the toes plus a spring. Specifically they need ankle plantar flexion, the ability to point the ankle down like a dancer, to get better toe push off and knee extension. Second, the torso needs to be able to rotate forward/back as it walks. These are just two of many suggestions. Here’s a video breaking down the mechanics of gait if you’re further interested!
https://youtu.be/cu2xvCbpI3o?si=3XbaeodA7jhj70Cc
You gave a great explanation regarding the shortcomings of the lower extremities, particularly the feet and the overall gait. It's amazing to reflect on how complex just the walking motion is and that we (humans) perform this with little to no active thought. There must be a lot going on behind the scenes in our brains.
I think the competition between Elon's Team and Boston Dynamics will lead to amazing results way beyond what we see today!
I agree! Even as advanced as the Boston dynamics robots are, I think we may see many other competitors emerge on the scene.
Competition is great for progress
Humanoid robots, they’re coming, efficiency, dexterity, and cost factor aside. My expectations are low, though.
Interesting, why are your expectations low? Do you think there are fundamental pieces of technology that are still a ways off before these become more impressive?
The whole thing is a glorified tech demo with zero practical application and will remain nothing more for a long time. Boston Dynamics Dancing robots are a fun act, too. This may sound overly pessimistic but achieving agility, dexterity and precision on a humanoid level will take many more years and even then, it will be very expensive, esp. when they fall over or get damaged ever so easily. Might be cheaper in the long run to clone people and program them to do certain jobs... oops, David Brin's Piecework, a recommended read. ;)
Thanks for the summary, David. These look like impressive improvements, but I keep my expectations in check in line with your reservations. Still, fascinating to see.
Thanks, Nathan! It's just one of those areas that is really difficult to know how close we are until someone get's a product out. I personally wouldn't mind if progress slowed down a bit.
Great summary! It'll be exciting to see just how Tesla intends to use these robots going forward and the impact they will have. I definitely see their top priority being to be use them in their own manufacturing centers to displace the rising cost of labor.
I am curious about their Optimus production capabilities, e.g., if they hand assembled it or they have a production facility. I think they will probably need 50-100 of these to really show them off. The labor market is about to change.