I Spent $4,000 on a Unitree Robot Dog From China

Unitree robot dog ownership began for me on a sunny morning in June, walking to work in Washington, DC's Mount Pleasant neighborhood. My quadruped companion drew more attention from strangers than anything I have ever carried, worn, or walked beside. People snapped pictures. Several asked questions. Was it mine? Yes. Did I build it? No. Was it being used for surveillance? No. Biological dogs kept their distance from my mechanical companion. Some growled or barked. Children were fascinated, so I paused and had it do tricks: shake hands, do a handstand, leap into the air.

The two-mile walk to my office near the White House was mostly downhill, and the robot arrived with battery capacity to spare. I recharged it during the workday. The walk home was a different story.

The Afternoon the Robot Collapsed

By the time I headed home, the route was mostly uphill and the temperature had climbed to 87°F (30°C). The robot's steps grew labored. The path got steeper. As I entered my own neighborhood, I glanced at two indicators in the corner of my phone screen, and one showed the battery at 5 percent, dangerously close to empty, while the other showed the internal temperature at 84°C (183°F). We were within sight of my front door when the robot suddenly collapsed. I'm not sure if it ran out of power or overheated, but either way it didn't shut down gracefully. It rolled onto its back. Its legs were in the air.

What Is a Robot Dog Actually For?

Several people have asked what my robot is useful for. Honest answer? Not much. Unitree quadrupeds are widely used for academic research and sometimes for entertainment, though when you look closely at the actual market you start to notice there don't seem to be a ton of practical applications that justify the cost. Wheeled robots are faster and more energy-efficient, making them better for deliveries. Flying drones are a better choice for a lot of surveying and inspection work. And my robot has no arms or hands. It's mostly useless around the house.

But my robot had one big thing going for it. It was astonishingly cheap. I paid $4,017. That's more money than I've ever spent to review a product, and yet it's also far less than I would have had to pay for this type of robot a few years ago, which is the part that really matters. Sometimes what changes the world isn't the invention of a new technology. It's figuring out how to make it affordable enough for a mass market.

Xerox built the first personal computer with a graphical user interface. But Apple, IBM, and Microsoft made the technology mainstream. So perhaps Unitree will play a similar role for quadruped robots, though its robots now face legal restrictions in the United States, and that's a fact. It's not clear yet.

How Unitree Democratized Legged Robotics

Earlier in June, I visited Professor Xuesu Xiao, a roboticist at George Mason University. His lab had four Unitree quadrupeds, each costing around $15,000. The lab also had a quadruped called Spot, made by Boston Dynamics, widely seen as the industry leader before Unitree came along. Spot is expensive, starting around $75,000.

"Ten years ago, only a very small set of research groups were working on quadruped locomotion because they were the only people on the planet who could build a quadruped," Xiao told me. "Then Unitree came onto the market. And it basically opened up quadruped locomotion research to everyone."

Unitree founder Wang Xingxing developed a crude quadruped robot called XDog for his master's thesis at Shanghai University. "Marc Raibert from Boston Dynamics is my idol," Wang told IEEE Spectrum in March 2016. "Their papers helped me to design XDog." Early Boston Dynamics prototypes, with names like BigDog and WildCat, had gasoline engines and hydraulic actuators. This made them too large, noisy, and polluting for practical use. In that 2016 interview, Wang said his goal was to "make quadruped robots simpler and smaller, so that they can help ordinary people with things like carrying objects or as companions."

That created an opening for Unitree. Wang founded it in May 2016. The company's first quadruped products, Laikago in 2017 and AlienGo in 2019, were powered by electric motors, and designed for research labs, they cost tens of thousands of dollars. In 2021, Unitree launched the Go1 line. It started at $2,700 for the Air model. In 2023, Unitree unveiled the Go2. It was even cheaper: $1,600 for the Air and $2,800 for the more capable Pro. Today, Unitree's cheapest robot, the Go2 Air, is more than 97 percent cheaper than Spot. This isn't an apples-to-apples comparison, since Spot is larger and can carry heavier payloads. Still, Unitree made quadruped robots affordable to many people who could never afford Spot, including me. My wife never would've let me spend $75,000 or even $15,000 on a robot dog. But I convinced her to let me spend $4,017, after tariffs and shipping costs, on a Go2 Pro.

Why Are Unitree Robots So Cheap?

Last year, Simplexity tore a Go2 robot dog apart. They made a video. What did they find? Each of the robot's four legs is powered by three motors, and there is a motor in the shoulder that controls the angle of the legs plus a motor driving each of the two leg segments. So that's the layout. It's simple.

"With three motors, you get a really dynamic range of motion," said Luis Elenes, a mechanical engineer at Simplexity. "They use all the same motors throughout. All four shoulders are identical in arrangement. There's tons of benefit to that. There's reduced cost, there's reduced part count. The more you can reuse motors and reuse parts, the simpler your design gets, and the sturdier your design will be overall."

Jakub Bartoszek knows motors and legged robots. He's an expert at the startup MAB Robotics. He argues that Unitree also saved money by using low-quality components. The motors in Unitree robots, many of which are made in-house, tend to wear out more quickly than those in some other robot brands, he told me, and that's a fact you can't ignore when you're weighing what these machines really cost over time. But the cost savings make the robots affordable to more people. Unitree seems to have designed its robots for easy repairs when they wear out.

"They want these legs to be serviceable in the field," Elenes said. Thanks to the simple way the robot's legs are attached to its body, "you can swap out a leg pretty easily. I would guess it would take you less than a minute."

Unitree gets help from Beijing. Tax credits flow in. Public institutions buy big. It's hard to quantify the scale of this support because the Chinese system blurs the line between public and private, military and civilian, and that blurring makes any clean accounting impossible. But policy clearly helped. Unitree scaled up manufacturing and drove down the cost of each robot.

The Counterintuitive Motor Strategy

Unitree has another counterintuitive cost-saving strategy: using large and powerful motors. More powerful motors are not inherently cheaper. But they allow Unitree to save money on another component called the reducer, which can be even more expensive.

Suppose you have a lever where one side is five times longer than the other. Push the long side down five inches. The short side goes up one inch. But force is magnified. That's the trick. 10 pounds on the long side becomes 50 pounds on the short side, which means that a small effort applied over a greater distance on one end produces a much larger force over a shorter distance on the other end. Many robots use gear systems called reducers that serve the same function. They convert the fast, relatively weak movement of an electric motor into a slower but stronger movement of a robot's body parts.

Traditional industrial robots require extreme precision, so they tend to have large reduction ratios. A page on the Boston Dynamics website, for example, indicates that two of the motors in Spot's legs are paired with reducers that have gear ratios of 51 to 1. In other words, the motor would need to do 51 full rotations to produce one full rotation of a leg joint. This enables Spot's movements to be very precise while magnifying the power of its motors. But it also has disadvantages. One is cost. Reducers with 51:1 ratios are complex and tend to be significantly more expensive than reducers with lower ratios. Another is rigidity. When a robot's arm encounters physical resistance, it should yield gracefully, a property called backdriveability. It is also helpful if a robot can sense this kind of physical resistance electrically. Robots with higher gear ratios perform badly on both fronts. Their limbs feel stiffer and they are less sensitive to physical resistance.

Unitree takes a different path. It uses large motors with a simple 6.33-to-1 gearbox, a combination that makes its robots more nimble and dynamic while also reducing costs, and because that simpler design is easier to simulate, it's easier to train the robots too. The lower gear ratio isn't an isolated choice. It's part of an industry-wide trend. High gear ratios made sense for industrial robots programmed to perform simple, repetitive motions. But many modern robots perform complex actions in unpredictable environments, which requires sophisticated control software that can respond flexibly to changing conditions. The software is constantly making small corrections anyway, so it can compensate for less precise hardware.

The Humanoid Pivot

One of the most impressive and crowd-pleasing capabilities of my Go2 Pro robot dog is handstands. The robot can balance on either its front or hind legs indefinitely, and can even move forward, backward, or side to side while doing so. So it was natural for Unitree to expand into humanoids.

Unitree first debuted a humanoid called the H1 in 2023. The next year, Unitree unveiled a cheaper and more capable robot called the G1. I got to see one when I visited Xiao's lab in June. He paid around $50,000 for a research-grade EDU version. The consumer version starts at $13,500. That's cheap. This is shockingly cheap given the robot's capabilities, and it's a price point that makes you wonder how they're doing it, because robots with these specs don't usually come anywhere near that number.

A humanoid robot isn't just a quadruped on its hind legs. My Go2 quadruped robot has three motors per leg, for a total of 12. Now look at the cheapest G1 humanoid, which packs five motors in each arm, six in each leg, and one in the torso, adding up to 23 motors overall. That's a big jump. The leg motors in a humanoid robot also need to be more powerful, since it's more work to balance on two legs than to stand on four, and they're doing that work constantly.

Still, I suspect Unitree's experience with quadrupeds gave it a leg up on humanoids. By the early 2020s, Unitree had been shipping quadruped robots for several years, and the company had deep expertise in actuator design and a wide network of suppliers. That's a real edge. According to filings connected to Unitree's August stock offering, the company's quadruped revenue tripled between 2024 and 2025, from RMB 230 million ($34 million) to RMB 697 million ($104 million). The comparable figures for Unitree's humanoids were RMB 107 million ($16 million) and RMB 867 million ($129 million), an eightfold increase. Humanoids accounted for 51 percent of Unitree's revenue in 2025.

The DJI Parallel and What Comes Next

Unitree debuted on the Shanghai stock market on August 19. On its first day of trading, shares shot up more than fivefold. It has lost some altitude since then, but at Monday's closing price, the company was still valued at $34 billion, more than triple its valuation before the IPO.

"We are witnessing the birth of another Chinese hardware giant," wrote a team at SemiAnalysis in June. "Three years ago, Unitree was a quadruped company. By last year, they parlayed quadruped dominance into creating and leading the humanoid market."

The SemiAnalysis authors draw a parallel to DJI. That's the Chinese company dominating global drones. "DJI's Phantom 1 shipped January 2013 at $679, and was not a fully-fledged product at the time," the SemiAnalysis team writes, noting that it had no built-in camera, no gimbal (stabilizer), ten minutes of flight, no live video feed, but it was roughly half the cost of the build-it-yourself drone. And they're right.

Like DJI in 2013, Unitree's robots today have a lot of rough edges. Mine sure does. Then there was the time my robot collapsed just feet from my house. But for bleeding-edge technologies, this kind of polish may not be very important. Far more important is getting costs down.

"DJI chose to inhouse the most expensive and technically difficult component first: the flight controller," SemiAnalysis writes. "Later on, DJI brought inhouse the gimbals, motors, and ESCs." DJI figured out how to make these components more cheaply than they could be purchased from external suppliers, which in turn allowed it to undercut other drone makers. And that expanded the market for DJI's drones. Before DJI came along, "professional aerial photography was the domain of helicopters and Hollywood second-unit teams, but now, small businesses could perform this on their own. As such, whole new markets were unlocked for DJI, like real estate listings, wedding videos, local news, agricultural surveying."

There is a flywheel here. The more units a company sells, the better deals it can negotiate with suppliers and the more money it can spend optimizing its manufacturing process. Larger sales volumes also allow a company to bring more components in-house. This allows the company to push costs even lower, which means more sales and even more money to invest in improving the production process. Over a few years, this flywheel helped DJI dominate the global drone market. SemiAnalysis argues that Unitree is on track to do the same thing for legged robots. Unitree has developed its own motors, gearboxes, lidar sensors, and cameras.

So what does this actually mean for the reader? A Unitree robot dog is not a finished consumer product. It is a platform, sold at a price that invites experimentation. My $4,017 bought me a machine that can do a handstand, draw a crowd on a morning commute, and collapse on its back within sight of my front door. It also bought a front-row seat to a company that may be doing for legged robots what DJI did for drones.