Discover the all new Boston Dynamics Atlas robot, featuring advanced AI, electric mobility, powerful robotic hands and industrial automation.
Boston Dynamics has unveiled a new generation of Atlas, its fully electric humanoid robot designed for AI-powered industrial work.
Standing 1.9 meters tall and weighing 90 kilograms, the Boston Dynamics Atlas robot combines human-scale proportions with movement that goes beyond human anatomy. Its 56 degrees of freedom allow it to bend, twist and reposition its body in unusual ways, while 360-degree cameras help it monitor its surroundings. Built-in human detection supports operation in shared workspaces.
Strength is another headline feature. The Atlas humanoid robot can briefly lift up to 50 kilograms, sustain loads of 30 kilograms and handle 20 kilograms with one hand, according to Boston Dynamics' 2026 specifications. A 2.3-meter reach gives it access to shelves, workstations and equipment designed for people.
One of the biggest Atlas robot upgrades arrived in October 2026: a redesigned four-fingered robotic hand. With 13 degrees of freedom, compared with seven in the previous design, the new hand uses tactile pressure sensors in its fingertips and palm to improve precision. Demonstrations showed Atlas inserting a drill bit, using a power drill and turning a small nut. The missing fifth finger is deliberate: fewer components can reduce complexity and potential failure points.
Artificial intelligence and reinforcement learning are intended to make Atlas adaptable rather than limited to one repetitive movement. The robot is being developed to learn skills in simulation, apply them in physical settings and share newly learned tasks across a robot fleet. Potential applications include material handling, machine tending, parts sorting and order fulfillment.
Battery management also sets this electric humanoid robot apart. Atlas is rated for up to four hours of operation, or about two hours during heavy lifting, and can autonomously replace its battery in roughly three minutes. Its IP67 rating is designed to protect against dust and water exposure.
The new generation of Atlas, it's a very exciting robot.
When we started working on its design,
we set out to build a robot that was designed for low cost,
ease of manufacturing, reliability, and simplicity.
Really, it's a robot for which we've
tried to reduce the complexity as much as possible.
One of the cool things is that we've been able to,
despite that simplification,
maintain many of the things
that make Boston Dynamics robots fun to work with.
It's a robot that is very strong, it's a robot that is very agile
and fast, and it's very easy to control. We're very successful at
Having fun in simulation designing behaviors
that then almost always work with the real hardware.
One of the goals that we've had
in the last couple months since we've been working with this robot
is basically being able to prove to ourselves that
what we thought was possible with this robot is actually possible.
So what we're seeing today is the new generation of hands for Atlas.
They're a perfect companion to where Atlas is today.
It's been designed with simplicity in mind
in its trajectory to mass manufacturing.
For the kinematics of the hand,
we have increased the number of degrees of freedom.
GR2 had seven degrees of freedom. GR3 now has 13.
The size and strength of the new hand
is a little bit larger than an average human hand,
but it's also on average a bit stronger.
We went into the design process with an idea
of the kinds of dexterous behaviors that we wanted to
be intrinsically possible with these hands.
So, for example, being able to achieve a pinch grasp
that is dexterous, so like when you're grasping something small
and rubbing it against your thumb,
or being able to achieve a tripodal grasp
and you're holding something with some amount of
strength but you still want to be able to move it.
Being able to grasp the handles of tools but
At the same time, being able to press their trigger.
So a large variety of dexterous, manipulative behaviors,
we knew that were important in that roadmap
of skills for Atlas.
I'm personally very excited about the fact
that you can simulate it cleanly,
and it enables very interesting work
in reinforcement learning,
but it's also close to anthropomorphic.
It has a very small gap between human demonstrations
and the embodiment of this hand.
The reason we picked the tasks that we're looking
at right now is because they're representative
of the tasks that we really care about.
This kind of object reorientation, both of these tasks require that.
But if we're able to do these tasks,
it kind of represents what we would be able to do
with tools or with pieces that we have to assemble together,
which we actually do care
about in the long run.
So right now, reinforcement learning is used
a lot for actually training the whole body.
And we're trying to see how we can use those tools
to actually get the robot to be able to
use its arms and its hands to manipulate things.
We've worked on getting these hands to be
simulatable and also be transparent to force and motion.
So any forces that the environment
applies on these fingers get translated
and we can proprioceptively sense them.
And any motion that we want to apply
to the environment gets applied very transparently.
Proprioception is a biological term which means your ability
to sense where your body or muscles are in space,
if they're moving, how much force is applied to them.
Backdrivability is not only beneficial in proprioception
and being able to generate
dexterous behaviors, but it's also really good in an impact.
So when you hit something
really hard, the joint is able to accelerate and move out of the way,
whereas if it had a lot of inertia or a lot of friction,
the gearbox would be damaged.
So this is not only beneficial for performance,
but also for ruggedness.
When we want to actually simulate these actuators
and this hand in a simulator,
there's three things that we generally care about.
The first one is kinematics,
so what is the geometry of the hand,
where are the links, where are the joints.
And the second one is dynamics,
where we think about what is the friction in the system,
what torques can it apply, what is the backlash in the system,
and how do we simulate that.
Lastly, we start worrying about contact dynamics.
So how does this gripper interact with the
environment? One of the things we think about
when we are doing this sim to real match is
not just going at it from one direction,
but approaching it from both directions.
We considered many, many designs, and there were many questions like,
do we want the hand to have one thumb or two thumbs?
Do we really want the hand to have a pinky or not?
And most of these don't have straight answers, right?
There's always some amount of intuition and experimentation.
It boils down to a trade of different competing objectives.
So we use many techniques to decide,
like, for example, using simulation
or using 3D-printed mock-up designs, or even just trying it ourselves.
At some point, our CTO, Zach, he asked us to tape
our pinky to our next finger and spent a day like that.
And then the next day is when we decided that,
OK, probably we didn't need that finger.
I wasn't here for that. I kind of wish I was.
I'm tempted to do it just in retrospect.
There's no pinky because the team determined
that the additional dexterity and tasks you'd
be able to accomplish is not worth
the extra complexity of three additional degrees of
freedom, the size, the power consumption,
all of the things that come with adding additional
actuators.
The journey for hand is a long one,
but this hand really set us in a good position for
the work we have to do today.
The multi-fingered hand is like a whole mini robot
when you think about the number of joints
and the number of motors in there.
The hardest thing that we were working on this gripper,
I was not expecting to do so much science in this job.
I think I'm really excited for all
the science that I get to do.
We are actively pushing the state of the art on the Atlas team.
Basically Atlas needs to be a tool.
A tool basically that is similar to humans which means
it needs to start interacting with objects
and objects come in all shapes and forms and because
Atlas is a beast and we know that it's capable
of lifting heavy objects we basically wanted to
jump in the deep end.
The empty fridge is 50 pounds and that is mostly what we shot with.
In the lab to really see what we could
do we were able to go up to 100 pounds.
Which was entirely unseen for the policy,
it was always trained at about 50 to 70 pounds.
And this is really pushing the limits of what humanoid robots can do.
I don't know of any other humanoid robot
that has moved a big heavy object like a fridge.
So the fridge experiment was really cool
and something I've kind of always been wanting to do,
which is basically instead of just grabbing things like with your hand
and grasping it and kind of moving it like this,
it was really using the whole body and really like leveraging like,
you know, straight arms, lift up a thing
and like really put your whole body into it was kind of the idea.
And I've always wanted to do that with a robot.
You know, a couple of things have come together recently.
We have a really...
Capable new robot that could actually do it
and we have a lot of really cool new tools on the team that we're
Utilizing to program it to do these kinds of behaviors
I've been here at Boston Dynamics for 15 years
and I've been a leader on the controls team for about that long and
We've gone through many cycles and many, you know pivots and I think
this one where we are right now is probably the most exciting
In the six weeks,
I've noticed that it's fairly easy for us to test things.
There's a pipeline, there's
a rigorous pipeline that's been established,
and there's a lot of people working behind the scenes.
The whole system in itself is a packaged system for us to...
test new policies on.
So I could be training a policy today, and tomorrow I have a baked-in
policy, and within like an hour, my policy is on the robot.
I'm testing, I'm collecting data,
I'm seeing what's happening, and I'm iterating, and I'm getting back.
So that whole pipeline is
seamless. We kind of have a very close sim
to real gap with just the robot, and that's been
very fun to focus on and not worry about that aspect.
We put together an animation, a reference
of what it would look like for the robot to move the fridge.
Then in simulation, for millions of hours,
we let the robot practice moving the fridge in the exact same way.
We encouraged it to move the fridge like we told it,
to not drop the fridge, and all those sorts of things.
And then once you get sort of the reward tuning right,
the physics correct for the hand dragging along the fridge,
And you run it on the hardware.
It does.
Perfectly. We have not seen the limits of what Atlas can do.
We are still pushing the limits in terms of the sort
of big heavy object that Atlas can pick up.
We're always going to keep pushing it.
All right, backflip in three, two, one.
Like a champ.