Inside the Korean hotel training humanoid robots with cameras on workers’ hands
The project reflects South Korea’s wider ambition to turn its chip industry, manufacturing strength and industrial know-how into an edge in ‘physical AI’. But can it catch up in a field still dominated by the US and China?
In South Korea, hotel workers are folding napkins and polishing glasses while cameras track every movement, all to teach humanoid robots how to do the same work inside hotels, factories, and warehouses.
At a high-end hotel in the country’s capital, Seoul, David Park is folding napkins, wiping glasses down, and setting tables, all while every movement is recorded in detail, with cameras strapped to his head, chest, and hands.
Park takes part in the recording sessions about once a month as part of a project run by South Korean artificial intelligence (AI) company RLWRLD, attempting to develop AI systems for five-finger robotic hands intended to more closely replicate human touch and movement.
The company says the process captures highly detailed information, including finger positioning, joint angles, and the amount of force applied during tasks.
Developers then use that data to train robots equipped with humanlike metal hands and onboard cameras.
In demonstrations, robots sort cutlery, lift cups, organise trays, and fold cloth napkins inside recreated hotel environments.
Current humanoid systems remain far slower than humans. RLWRLD says a robot would currently need several hours to clean a hotel room that staff can prepare in around 40 minutes.
However, the company says advances in AI software and robotic hardware are accelerating rapidly and it hopes its technology can be used in industrial AI robots by 2028.
RLWRLD says hospitality work provides valuable training because many hotel tasks require precision and subtle hand control.
“For example, with Lotte Hotel, if you were to have a robot fold napkins, a gripper wouldn’t be able to achieve the precise and crisp folds expected of hotel service quality. It wouldn’t be able to achieve a level that can be used in service,” said Hyemin Cho, RLWRLD business and strategy executive.
The company says it is also collecting similar data from logistics workers at South Korean conglomerate CJ Group’s warehouses and from staff at Japanese convenience store chain Lawson, where workers’ hand movements are tracked as they arrange food displays and handle goods.
The goal is to build AI software that can operate across robots used in a range of factories and other workplaces in the coming years, before potentially expanding into homes.
RLWRLD’s engineers say replicating the dexterity of human hands is a key priority.
In South Korea, hotel workers are folding napkins and polishing glasses while cameras track every movement, all to teach humanoid robots how to do the same work inside hotels, factories, and warehouses.
At a high-end hotel in the country’s capital, Seoul, David Park is folding napkins, wiping glasses down, and setting tables, all while every movement is recorded in detail, with cameras strapped to his head, chest, and hands.
Park takes part in the recording sessions about once a month as part of a project run by South Korean artificial intelligence (AI) company RLWRLD, attempting to develop AI systems for five-finger robotic hands intended to more closely replicate human touch and movement.
The company says the process captures highly detailed information, including finger positioning, joint angles, and the amount of force applied during tasks.
Developers then use that data to train robots equipped with humanlike metal hands and onboard cameras.
In demonstrations, robots sort cutlery, lift cups, organise trays, and fold cloth napkins inside recreated hotel environments.
Current humanoid systems remain far slower than humans. RLWRLD says a robot would currently need several hours to clean a hotel room that staff can prepare in around 40 minutes.
However, the company says advances in AI software and robotic hardware are accelerating rapidly and it hopes its technology can be used in industrial AI robots by 2028.
RLWRLD says hospitality work provides valuable training because many hotel tasks require precision and subtle hand control.
“For example, with Lotte Hotel, if you were to have a robot fold napkins, a gripper wouldn’t be able to achieve the precise and crisp folds expected of hotel service quality. It wouldn’t be able to achieve a level that can be used in service,” said Hyemin Cho, RLWRLD business and strategy executive.
The company says it is also collecting similar data from logistics workers at South Korean conglomerate CJ Group’s warehouses and from staff at Japanese convenience store chain Lawson, where workers’ hand movements are tracked as they arrange food displays and handle goods.
The goal is to build AI software that can operate across robots used in a range of factories and other workplaces in the coming years, before potentially expanding into homes.
RLWRLD’s engineers say replicating the dexterity of human hands is a key priority.
Physical AI race
The project is part of South Korea’s growing push into “physical AI,” a sector focused on robots that can perceive, decide, and act in real-world environments.
Just as chatbots such as ChatGPT and Gemini train on vast troves of internet text, AI robots require extensive data on human action to handle advanced physical tasks.
South Korean companies believe they may have an advantage because of the country’s manufacturing base and its large pool of skilled industrial workers, whose expertise can be translated into robot training systems.
The push is part of a wider national effort to turn South Korea’s semiconductor and manufacturing strengths into a stronger position in AI robotics, even as the United States and China continue to lead the field as part of their wider technological rivalry.
The country is stepping up efforts to compete in the humanoid robotics race, with its government recently announcing a $33 million (€28 million) national project aimed at recording the “instinctive know-how and skills” of experienced technicians to help train AI-powered manufacturing robots.
Major corporations are also investing heavily. Hyundai Motor plans to introduce humanoid robots developed by Boston Dynamics at its factories from 2028.
Samsung Electronics says it aims to convert all manufacturing facilities into “AI-driven factories” by 2030 using humanoids and task-specific robots across production lines.
The development has also raised concerns among some labour groups that robots could eventually replace jobs.
However, for Park, who has worked in hospitality for nine years, the innovation is more exciting than worrying.
“If you look at the entire process of preparing for an event in the back-of-house space, we think humanoids might be able to take over about 30% to 40% of that workload,” Park said.
“However, I think it will be difficult for them to replace the remaining 50%, 60%, 70% of the work, which involves the actual 'human-to-human' interaction. In that sense, it’s more exciting than concerning”.
The project is part of South Korea’s growing push into “physical AI,” a sector focused on robots that can perceive, decide, and act in real-world environments.
Just as chatbots such as ChatGPT and Gemini train on vast troves of internet text, AI robots require extensive data on human action to handle advanced physical tasks.
South Korean companies believe they may have an advantage because of the country’s manufacturing base and its large pool of skilled industrial workers, whose expertise can be translated into robot training systems.
The push is part of a wider national effort to turn South Korea’s semiconductor and manufacturing strengths into a stronger position in AI robotics, even as the United States and China continue to lead the field as part of their wider technological rivalry.
The country is stepping up efforts to compete in the humanoid robotics race, with its government recently announcing a $33 million (€28 million) national project aimed at recording the “instinctive know-how and skills” of experienced technicians to help train AI-powered manufacturing robots.
Major corporations are also investing heavily. Hyundai Motor plans to introduce humanoid robots developed by Boston Dynamics at its factories from 2028.
Samsung Electronics says it aims to convert all manufacturing facilities into “AI-driven factories” by 2030 using humanoids and task-specific robots across production lines.
The development has also raised concerns among some labour groups that robots could eventually replace jobs.
However, for Park, who has worked in hospitality for nine years, the innovation is more exciting than worrying.
“If you look at the entire process of preparing for an event in the back-of-house space, we think humanoids might be able to take over about 30% to 40% of that workload,” Park said.
“However, I think it will be difficult for them to replace the remaining 50%, 60%, 70% of the work, which involves the actual 'human-to-human' interaction. In that sense, it’s more exciting than concerning”.
.jpg)
