Zum Player springenZum Hauptinhalt springen
😇 Dein Abo hilft uns: https://tublo.eu/abonnieren
✅ Source: Boston Dynamics
âžĄïž Mehr Infos: https://www.tuningblog.eu/?s=boston+dynamics

Tauche ein in die faszinierende Welt der Robotik und erlebe hautnah, wie Boston Dynamics die humanoide Hand des Atlas-Roboters entwickelt. In diesem exklusiven Behind-the-Scenes-Video zeigen Ingenieure, wie komplex und prĂ€zise moderne Greifer konstruiert sind – robust genug fĂŒr harte Arbeiten, aber auch feinfĂŒhlig fĂŒr zerbrechliche GegenstĂ€nde.

Die Hand des Atlas-Roboters ist ein technisches Meisterwerk mit hochentwickelter Sensorik und Aktorik. Erfahre, welche Prinzipien Boston Dynamics bei der Entwicklung verfolgt, wie sich der Greifer im Laufe der Zeit verÀndert hat und welche Herausforderungen dabei gelöst wurden.

Dieses Video bietet spannende Einblicke in die Zukunft der Mensch-Maschine-Interaktion und erklĂ€rt, welche Rolle die Greiftechnologie in der Weiterentwicklung humanoider Roboter spielt. Egal ob Technikfan, Entwickler oder einfach neugierig – hier bekommst du fundiertes Wissen und faszinierende Bilder aus dem Herzen eines der fĂŒhrenden Robotik-Unternehmen der Welt.

#BostonDynamics, #Atlas, #Roboterhand, #Robotik, #HumanoiderRoboter, #Technik, #Greifer #tuningblog - das Magazin fĂŒr Auto-Tuning und MobilitĂ€t!

Kategorie

🚗
Motor
Transkript
00:00The transition from hydraulics to electric Atlas gave us an interesting jumping point.
00:08We knew that right about the same time that Boston Dynamics and Atlas wanted to focus more on manipulation,
00:16not just mobility and locomotion.
00:18And that was just a natural point to explore grippers with higher dexterity.
00:23We've known from the beginning that the gripper journey is a long one.
00:27Grippers are one of the most intricate components of a humanoid robot.
00:32They pack tons of functionality.
00:34We have to put in a lot of actuation and sensing into a very small space.
00:39So it's a very hard design problem.
00:41We've taken that long-term perspective and tried to maximize learnings through that path.
00:48GR1 is a gripper that is the first gripper of what we call the GR line,
00:53where basically we were looking to build something that had the most fundamental
00:59and, in a way, minimalistic capabilities of a human hand.
01:03GR1 allowed us to learn a ton of what it means to mount a gripper to a humanoid robot.
01:09That works most of the time well, but sometimes it falls,
01:13and inevitably once in a while it's going to fall on top of the gripper.
01:16So we wanted to figure out what is a good way to build a gripper that can resist that kind of failure mode,
01:23which is very important to our development path,
01:26being able to build grippers that are rugged and reliable.
01:29This is our second-generation gripper.
01:32It has seven degrees of freedom.
01:35We have seven different actuators within it,
01:37two for each of the three fingers,
01:39and the one for this articulated thumb joint.
01:42We have tactile sensing on the fingertips,
01:45and we have cameras here in the palm.
01:48The whole module is self-contained with all the actuation within it,
01:51and it's very easy to put on and off of the robot.
01:54And it was an iteration from our first-generation gripper,
01:57which had a similar three fingers,
01:59but there was no thumb, so they're all in the same line.
02:02Maybe the most important distinction from GR2 to GR1
02:06is the addition of a thumb, an opposable thumb.
02:09That really expands the type of grasps that it allows us to do.
02:13It really increases the flexibility of which objects we can grasp with it.
02:18And really, over the last year or so,
02:20we've realized that we can grasp almost anything that we throw at it.
02:27We landed on three because we believe that that's the fewest amount of fingers,
02:31that can achieve very complex manipulation tasks.
02:36So the fact that you do have three fingers brings a lot more to the table over just two,
02:40because the fact that there's some distance between them
02:43can help in maintaining a stable grasp,
02:46especially when you're maintaining larger or heavier objects
02:49that want to kind of rotate out of your hand.
02:51We do have the opportunity with this thumb to do some two-finger pinch grasps,
02:55which can be very helpful for delicate manipulation of very tiny objects,
03:00but that third finger coming into play when you are grasping something a little heavier
03:04or a little larger can be really helpful in maintaining a stable grasp.
03:09We've debated a lot, and we do wonder if there's an opportunity to add more fingers
03:14and whether they'd bring much to the table.
03:16We decided not to add more fingers because adding more fingers,
03:20it just adds more complexity that if it's not necessary,
03:23it always ends up meaning lower reliability, higher cost,
03:27just in general lower speed of development.
03:30We shouldn't take that as a dogma though, right?
03:33Three fingers was the right answer for the first phases of this program.
03:38We'll see what is the answer moving forward.
03:41Tactile sensing is force feedback.
03:47You can think of it as your sense of touch that you have in your own fingers.
03:51The tactile sensors live here on the fingertips,
03:53in this elastomer here that's at the top,
03:56that provides two functions.
03:58One is to give a high friction surface,
04:00and then also as it deforms,
04:02we have sensors within those fingertips that translate that into a force feedback.
04:06By having that sense of touch on your fingertips,
04:09you can apply very gentle forces to something.
04:11If you're perhaps manipulating a fragile object,
04:14you might want to handle it gingerly.
04:16You can also detect if you've dropped something.
04:18So if you didn't mean to, but it's fallen out of your hand,
04:20those tactile sensors can give you that feedback
04:22to understand what's going on.
04:24The goal is to apply as little force as possible,
04:27but maintaining a stable grasp.
04:29That's very similar to when you pick something up.
04:31You don't want to crush the object,
04:33but you want to make sure that it stays in your hand,
04:34it doesn't slip out of your hand.
04:35Too light a grasp, and something might slip away,
04:37and too heavy a grasp, and you might actually damage it.
04:45So inward, we can rotate up to 90 degrees,
04:48very similar to what your hand can do,
04:49but this has some extra human capability
04:51in that all these fingers can bend backwards completely.
04:54We can do some very clever things
04:55where you would actually be grasping on the backside of the gripper.
04:57So we actually have a left and right version of this gripper,
05:00similar to how our own hands,
05:01we have a left and right hand that are mirrored,
05:04but not the same.
05:05So this thumb always comes around on this one side.
05:08Atlas will usually be planning for the most optimal route
05:12to get the job done that it's trying to do.
05:14So if standing in a certain position
05:17and reaching in with the left hand
05:19will provide a more stable grasp
05:20or allow you to avoid objects in the environment,
05:22that's usually the way that it will choose.
05:24It doesn't tend to have a dominant left or right hand like you and I do.
05:33We're setting the next milestone in the direction of dexterity.
05:37It's becoming clear that tasks like bin picking or tool use
05:41or in general handling small objects are very prevalent in manufacturing.
05:47Interestingly, all of these things kind of are pushing us,
05:51not necessarily by design,
05:53but sort of naturally organically
05:55into more anthropomorphic designs of the gripper.
06:00Finding the gripper with the right sweet spot
06:02of dexterity, actuation and sensing
06:05is one of the most interesting journeys of the next few years
06:08and we're very excited to see where it takes us.
06:21For more videos, just subscribe to the channel.
06:34See you then.
06:35See you then.
06:36See you then.
Schreibe den ersten Kommentar
Kommentar hinzufĂŒgen

Empfohlen