Back in January, Apptronik said He worked on a new general commercial service Humanoid robot called Apollo. I say “new” because in the past seven or eight years, Apptronik has developed more than half a dozen Humanoid robots as well as some exoskeletons of the full body. But as a company told us Earlier this year, he decided that now is absolutely time for Bipedal humanoids To become a salesperson.
Today, Apptronik unveils Apollo. He indicates that the robot is “designed to transform the industrial workforce and beyond the service of improving human experience”. It will first be used in logistics and manufacturing, but Apptronik promises “endless long -term potential applications”. However, the company must get there: it is a big step of a prototype to a commercial product.
The biped that we saw in January was a prototype for Apollo, but today Apptronik shows an alpha version of the real thing. The robot measures roughly the size of the man, standing 1.7 meters high and weighing 73 kilograms, with a maximum payload of 25 kg. It can operate for about 4 hours on a swapable battery. The company has two of these robots right now, and it is building four others.
While Apptronik initially focuses on the treatment solutions for boxes and tote in the logistics and manufacturing industries, Apollo is a general-used robot designed to operate in the real world where development partners will extend the Apollo solutions far beyond logistics and manufacturing finally extending to construction, oil and gas, electronic production, retail, home delivery, elder care and innumerable others. Apollo is the “iPhone” of robots, allowing development partners to develop solutions developed by Apptronik and to extend the digital world in the physical world to work alongside people and do the work they do not want to do .
I am generally not a big fan of the analogy “iPhone of robots”, mainly because the iPhone was profitable and largely desirable as a versatile tool even before developers I really got involved. Historically, robots have not succeeded in this way. It will take a while to know if Apollo will be able to demonstrate that the ready -to -use versatility, but I assume that Apollo’s initial success (as with essentially all other robots) will mainly depend on which practical applications apptronik him -Mend will be able to configure it. Perhaps at one point, the humanoids will be so affordable and easy to use that there will be an open developer market, but we are not yet close to that.
Almost all humanoid robots entering the market are intended for the handling of standard containers, known as boxes and bins. And for a good reason: the work is boring and trying physically, and there are not enough people ready to do so. There is a lot of room for robots like Apollo, provided that the cost is not too high.
To understand how Apollo can be competitive, we talked to the CEO of Apptronik Jeff Cardenas and cto Nick Paine.
How are you going to make Apollo affordable?
Jeff Cardenas: It was not our first humanoid that we built – we made about eight. The approach that we adopted with our robots from the start was to build the best thing we could and to worry about reducing the cost later. But we hit a wall every time. A big goal with Apollo was not to start again. We had to start thinking about the cost from the start, and we had to make sure that the first alpha unit that we build is as close to the gamma unit as possible. Many people will wave a wand and say: “One day there will be millions of humanoids, so things like harmonic readers will become much cheaper on a large scale.” But when you really cite components with very high volumes, you do not get the price break that you think you will get. Electronics – Automobile drivers with actuators – 60% or more from the system’s cost are there.
Nick Paine: We try to think of Apollo from a long -term perspective. We wanted to avoid the situation where we were building a robot just to show that we could do something, but then have to understand how to exchange high precision pieces for something else while presenting our team of controls with a completely new problem Also.
The emphasis is therefore placed on the Apollo actuators?
Paine: Apptronik is a bit unique in what we have formed an actuation experience through a range of projects on which we have worked – I think we have designed around 13 complete systems, so we have experienced the whole range of the type of Actuation Architectures work well for which scenarios and which applications. Apollo is really a highlight of all this knowledge gathered on many years of iterative learning, optimized for the case of use of humanoid and being very intentional on the properties of the point of view of the first principles that we wanted to have to Each robot joint. Which led to a combination of Linear and rotary actuators throughout the system.
Cardenas: What we target is affordability, and part of the way we get there is with our action approach. The new actuators we use have about a third of components less than our previous actuators. They also take around a third of the assembly time. In the long term, our roadmap is really concentrated on supply chain: How can we move away from sellers with a single source and start to take advantage of the components much more easily available? We believe that this will be important for the cost and scaling of long -term systems.
Can you share technical details on actuators?
Paine: People can watch the patents When they go out, but I was delighted with the design experience of the first principles of our teams and the previous history of integration into the system.
But is it not like you had a magical technology of the new actuator?
Cardenas: We do not rely on fundamental breakthroughs to reach this performance threshold. We have to bring our robots out into the world, and we are able to take advantage of the technologies that already exist. And with our experience and a kind of reflection on the systems that we bring it together in a new way.
What does “affordable” mean in the context of a robot like Apollo?
Cardenas: I think in the long term, a humanoid should cost less than US $ 50,000. They should be comparable to the price of many cars.
Paine: I think that in fact, we could be much cheaper than cars, depending on the hypothesis that on the scale, the cost of a product generally addresses the cost of its constituent materials. The cars weigh approximately 1,800 kilograms and our robot weighs 70 kilograms. It is 25 times less raw materials. And as Jeff said, we already have a path and a supply chain for very profitable actuators. I think it’s a really interesting analysis to think, and we are delighted to see where it is going.
Some videos show Apollo with a five fingers hand. What is your perspective on final effectors?
Cardenas: We think that long -term hands will be important for humanoids, although they should not necessarily be from five fingers. The final effector is modular. For the first applications when we choose boxes, we do not need a five fingers hand for this. And so we will simplify the problem and deploy it with a simpler end effector.
Paine: I have the impression that some people try to make hands because they think it’s cool, or because it shows that their team is capable. The way I think about it is, humanoids are quite difficult as they are – there are a lot of challenges and complexities to understand. We are a very pragmatic team from an engineering point of view, and we are very careful to choose our battles, by putting our resources where they are the most precious. And so for the Alpha version of Apollo, we have a modular interface with the wrist. We do not solve the generic five fingers problem of fine dexterity and manipulation. But we believe that in the long term, the best versatile final effector is a hand.
These initial applications that you are targeting with Apollo do not seem to take advantage of his biped mobility. Why have a robot with legs at all?
Cardenas: One of the things we have learned on the legs is that they meet the need to reach the ground and tend high. If you try to solve this problem with the wheels, you end up with a very large base, because it must be static. The customers we work with are really interested in this idea of renovation. They don’t want to have to make changes in the workspace. The workstations are really narrow – they are designed around the human form, and we therefore think that the legs will be the way to get there.
Legs are an elegant solution to make a light system that can work in large vertical work spaces in small footprints. —Nick Paine, CTO Apptronik
Can be safe Apollo to fall And go up?
Paine: A very important requirement is that Apollo must be able to fall and not to break, which leads to certain key activation requirements. One of the unique things with Apollo is that not only is it well suited to manipulation at the OSHA useful loads, but it is also well suited to robbed the impacts with the environment. And from the maintenance point of view, two bolts are everything you need to withdraw an actuator.
Cardenas says that Apptronik has more than 10 drivers planned with the selection of cases as an initial application. The rest of this year will focus on internal demonstrations with the Apollo Alpha units, with field pilots planned for next year with production robots. A complete commercial version is scheduled for the end of 2024. It is certainly an aggressive chronology, but Apptronik is confident in its approach. “The beauty of robotics is to show in relation to the revelation, ”explains Cardenas. “This is what we are trying to do with this launch.”
From your site items
Related items on the web