Dominique Paul | 📍 CoRL's banner
Dominique Paul | 📍 CoRL's profile picture

Dominique Paul | 📍 CoRL

@DominiqueCAPaul • 9,435 subscribers

Founder of Dream Machines @dm_robots, building ML models for robotic arms. Previous: Stats at @ETH & @NeurIPSconf. I post about RL and VLA post-training.

Shorts

Just came out of an LED panel factory in Guangzhou. Most notable thing after having toured European manufacturers for over a month last year: Nobody minded us taking pictures. In western factories that's taboo, because nobody wants any information about how they produce circulating. I asked the production manager why they don't care here. His answer: "You can see how we do it, but each of these machines costs ¥3m (~€400k) and we run dozens of them." The moat is capital. There's also a default assumption that everything gets copied anyway, so nobody builds their business on production secrets. Another big reason is that showing the line is marketing. About 95% of companies selling LED panels here are trading companies. Middlemen = somebody's taking a cut = you're paying a bad price. Letting you see the factory proves they actually produce, shows the quality of the components, and signals you're getting a fair price. Same with privacy. In Europe, filming workers beyond their hands is a no-go. Here people glanced up at three people filming them and continued working. Try that in a Bavarian SME. Some numbers: > 95% automated: that means machines assemble 95% of components, humans 5% > Factory runs 24/7 on two 12-hour shifts. In Europe this would be 3x 8h > 60h weeks, two days off, just not always the weekend > Guangdong minimum wage is ¥2,680 (€360) per month, so ~€1.40/hour > Employer cost is ¥4,100 though and employee pays ¥700 in taxes. Those are all pension and social contributions. There's no income tax on salaries below ¥5,000 The owner is called Cha-Ming, so he goes by Charming for foreigners. He definitely enjoys leaning into this name for branding.

Just came out of an LED panel factory in Guangzhou. Most notable thing after having toured European manufacturers for over a month last year: Nobody minded us taking pictures. In western factories that's taboo, because nobody wants any information about how they produce circulating. I asked the production manager why they don't care here. His answer: "You can see how we do it, but each of these machines costs ¥3m (~€400k) and we run dozens of them." The moat is capital. There's also a default assumption that everything gets copied anyway, so nobody builds their business on production secrets. Another big reason is that showing the line is marketing. About 95% of companies selling LED panels here are trading companies. Middlemen = somebody's taking a cut = you're paying a bad price. Letting you see the factory proves they actually produce, shows the quality of the components, and signals you're getting a fair price. Same with privacy. In Europe, filming workers beyond their hands is a no-go. Here people glanced up at three people filming them and continued working. Try that in a Bavarian SME. Some numbers: > 95% automated: that means machines assemble 95% of components, humans 5% > Factory runs 24/7 on two 12-hour shifts. In Europe this would be 3x 8h > 60h weeks, two days off, just not always the weekend > Guangdong minimum wage is ¥2,680 (€360) per month, so ~€1.40/hour > Employer cost is ¥4,100 though and employee pays ¥700 in taxes. Those are all pension and social contributions. There's no income tax on salaries below ¥5,000 The owner is called Cha-Ming, so he goes by Charming for foreigners. He definitely enjoys leaning into this name for branding.

312,285 views

Around 3 million Chinese private companies face a generational handover in the next 10 years, and it‘s the founders' kids who grew up in the digital age we should probably be watching. Today, we visited a mattress factory in Foshan where the son is taking over, and he's gone all in on the brand: > built an entire museum of sleep explaining the production process > added AI point-cloud scans to match mattresses to body types > or my favourite: wrote a song about the company's history and sang it himself (yes, this was pre-AI slop; last video). Reminds me of many other new owners on TikTok rethinking online marketing. Next to highly automated consumer lines, they sell handmade mattresses filled with white horsetail hair that go for up to ¥600,000 (~€80k, second pic). Horsehair in mattresses is an old European high-end tradition. Tail hair is longer and thicker than mane, so it springs back better and lasts for decades. White hair is finer and rarer and so in part it’s about selling the idea of luxury that some people care about.

Around 3 million Chinese private companies face a generational handover in the next 10 years, and it‘s the founders' kids who grew up in the digital age we should probably be watching. Today, we visited a mattress factory in Foshan where the son is taking over, and he's gone all in on the brand: > built an entire museum of sleep explaining the production process > added AI point-cloud scans to match mattresses to body types > or my favourite: wrote a song about the company's history and sang it himself (yes, this was pre-AI slop; last video). Reminds me of many other new owners on TikTok rethinking online marketing. Next to highly automated consumer lines, they sell handmade mattresses filled with white horsetail hair that go for up to ¥600,000 (~€80k, second pic). Horsehair in mattresses is an old European high-end tradition. Tail hair is longer and thicker than mane, so it springs back better and lasts for decades. White hair is finer and rarer and so in part it’s about selling the idea of luxury that some people care about.

38,672 views

China, day 5 Up early for Guangzhou and the Canton Fair. ~300,000 visitors and a trade show in the most literal sense: export, of every product you can think of. The train from HK to Guangzhou takes 60 minutes. Getting through security at the station took about as long. We did the service robotics hall in 60-90 minutes. It had more relevant robot AI companies than the industrial automation hall, which was mostly task-specific machines and at best components like actuators. I expected more robot AI overall. My guess is it still shows up at the World Robot Conference more than at a show where people come to buy. Much less English on the mainland than in HK. Communication has resorted to mostly hands and Google Translate. Didi is absurdly cheap. 60 minutes from the fair to Foshan cost us 12€. Little reason to take public transport unless it's actually faster. Now joining an organised tour with Bob, a friend of a friend, who's kindly hosting Aurel Arnold and me at his family's house. First evening with the rest of the group done. They live in a gated community owned by Midea (the AC company that bought Kuka a decade ago), like most of this district. Reminds me of Krupp building worker housing and basic infrastructure in the 19th century because otherwise it just wouldn't have existed.

China, day 5 Up early for Guangzhou and the Canton Fair. ~300,000 visitors and a trade show in the most literal sense: export, of every product you can think of. The train from HK to Guangzhou takes 60 minutes. Getting through security at the station took about as long. We did the service robotics hall in 60-90 minutes. It had more relevant robot AI companies than the industrial automation hall, which was mostly task-specific machines and at best components like actuators. I expected more robot AI overall. My guess is it still shows up at the World Robot Conference more than at a show where people come to buy. Much less English on the mainland than in HK. Communication has resorted to mostly hands and Google Translate. Didi is absurdly cheap. 60 minutes from the fair to Foshan cost us 12€. Little reason to take public transport unless it's actually faster. Now joining an organised tour with Bob, a friend of a friend, who's kindly hosting Aurel Arnold and me at his family's house. First evening with the rest of the group done. They live in a gated community owned by Midea (the AC company that bought Kuka a decade ago), like most of this district. Reminds me of Krupp building worker housing and basic infrastructure in the 19th century because otherwise it just wouldn't have existed.

24,756 views

Just visited Tianjin Robotics in Shenzhen as we’re moving into our first deployments and need more robust arms. Tianjin builds 2,000+ arms a month, and every arm sells for about $15k. AGIBot has bought roughly 20,000 of them, which surprised me. I thought they built their own. Skild is a customer too. NVIDIA asked for a custom version with a longer upper arm, which apparently leads to fewer collisions. Two most interesting notes for me today: 1/ Camera cable reliability is an industry-wide problem right now. 2 of our 8 arms had it. I liked routing cables inside the arm because external cables look terrible, and assumed we'd just bought bad ones. If everyone has this problem, the cables belong outside, where you can swap one in a few minutes. 2/ They say customers keep asking for higher precision. A learned policy corrects as it goes, so repeatability should matter less for us. Either I'm missing something or most of their buyers aren't doing robot learning.

Just visited Tianjin Robotics in Shenzhen as we’re moving into our first deployments and need more robust arms. Tianjin builds 2,000+ arms a month, and every arm sells for about $15k. AGIBot has bought roughly 20,000 of them, which surprised me. I thought they built their own. Skild is a customer too. NVIDIA asked for a custom version with a longer upper arm, which apparently leads to fewer collisions. Two most interesting notes for me today: 1/ Camera cable reliability is an industry-wide problem right now. 2 of our 8 arms had it. I liked routing cables inside the arm because external cables look terrible, and assumed we'd just bought bad ones. If everyone has this problem, the cables belong outside, where you can swap one in a few minutes. 2/ They say customers keep asking for higher precision. A learned policy corrects as it goes, so repeatability should matter less for us. Either I'm missing something or most of their buyers aren't doing robot learning.

20,457 views

Today I incorporated my startup - and where else than in Germany 🇩🇪 All without leaving my house and getting a German notary appointment in under 24 hours, thanks to the electronic ID. Long Europe 🇪🇺

Today I incorporated my startup - and where else than in Germany 🇩🇪 All without leaving my house and getting a German notary appointment in under 24 hours, thanks to the electronic ID. Long Europe 🇪🇺

115,033 views

Visited Youkai today, one of the biggest laundry pod makers in China. About a billion pods a year, 100,000+ tonnes of detergent, ¥1bn (€130m) revenue, and contract manufacturing for Unilever and hundreds of other brands. 80% of production is white label. Their own brand is growing double digits a year, but they reckon a consumer brand takes 5–10 years to build. The unit economics: a pack sells for ¥18 and costs ¥14 to make. 22% gross margin, single-digit net. Very representative of the Chinese market: Hypercompetitive, super tough for companies, great for consumers, and it forces everyone to get very efficient. Most companies here want to sell abroad though, where they say they make 5–6x the profit. Youkai does roughly 35% of their production for companies abroad. Favourite detail i saw: floor 12 (building has 16 stories in total, 16 is CEOs office) is for livestreaming. I knew livestream shopping was big in China, but I wouldn’t expect people to buy laundry pods like this.

Visited Youkai today, one of the biggest laundry pod makers in China. About a billion pods a year, 100,000+ tonnes of detergent, ¥1bn (€130m) revenue, and contract manufacturing for Unilever and hundreds of other brands. 80% of production is white label. Their own brand is growing double digits a year, but they reckon a consumer brand takes 5–10 years to build. The unit economics: a pack sells for ¥18 and costs ¥14 to make. 22% gross margin, single-digit net. Very representative of the Chinese market: Hypercompetitive, super tough for companies, great for consumers, and it forces everyone to get very efficient. Most companies here want to sell abroad though, where they say they make 5–6x the profit. Youkai does roughly 35% of their production for companies abroad. Favourite detail i saw: floor 12 (building has 16 stories in total, 16 is CEOs office) is for livestreaming. I knew livestream shopping was big in China, but I wouldn’t expect people to buy laundry pods like this.

18,321 views

China, day 7 Highlight today was the LED manufacturer and walking their production floor. Comments under my other post today explained that wages in places like these are well above minimum wage, more like ¥6-8k a month. That puts cost per worker close to the factories I visited in Poland … but with roughly 20 more hours of work per worker per week. The longer I'm here, the more China reminds me of the US in one way: the media covers the extremes, and in everyday life you feel very little of them. Key difference: US has more influence over global media while reporting on china abroad is one-sided with few people setting foot here. Lunch was Cantonese and Beijing food, including Peking duck. Very fatty skin, very good. Like with other dishes here, part of the point is showing how fresh it is, so the duck gets carved in front of you. Three tables = three cooks carving. Then the Foshan hydrogen lab: 140 researchers on fuel cells and ammonia-hydrogen. Nanhai, a district of Foshan, is a hydrogen cluster with 160+ companies. One of their projects is powering robots with hydrogen. They also spin off ~10 companies a year. Interesting learning: Research institutes like this one align their planning with China's 5-year plan. Obvious in hindsight. "5-year plan" sounds very communist, but the more I thought about it I thought that an election cycle isn’t that different, except that the guys doing the 5-year plan think more long term. Evening in Foshan's city centre. A temple, a local hotpot cooked in rice water instead of oil or broth. Then walked around the city centre. Fewer towers than Guangzhou, but a surprising number of high-end stores. Could have been Japan. Prices are the same as in Europe. Contrasted with this morning’s factory wages, I am wondering what the average customer in these stores does for a living.

China, day 7 Highlight today was the LED manufacturer and walking their production floor. Comments under my other post today explained that wages in places like these are well above minimum wage, more like ¥6-8k a month. That puts cost per worker close to the factories I visited in Poland … but with roughly 20 more hours of work per worker per week. The longer I'm here, the more China reminds me of the US in one way: the media covers the extremes, and in everyday life you feel very little of them. Key difference: US has more influence over global media while reporting on china abroad is one-sided with few people setting foot here. Lunch was Cantonese and Beijing food, including Peking duck. Very fatty skin, very good. Like with other dishes here, part of the point is showing how fresh it is, so the duck gets carved in front of you. Three tables = three cooks carving. Then the Foshan hydrogen lab: 140 researchers on fuel cells and ammonia-hydrogen. Nanhai, a district of Foshan, is a hydrogen cluster with 160+ companies. One of their projects is powering robots with hydrogen. They also spin off ~10 companies a year. Interesting learning: Research institutes like this one align their planning with China's 5-year plan. Obvious in hindsight. "5-year plan" sounds very communist, but the more I thought about it I thought that an election cycle isn’t that different, except that the guys doing the 5-year plan think more long term. Evening in Foshan's city centre. A temple, a local hotpot cooked in rice water instead of oil or broth. Then walked around the city centre. Fewer towers than Guangzhou, but a surprising number of high-end stores. Could have been Japan. Prices are the same as in Europe. Contrasted with this morning’s factory wages, I am wondering what the average customer in these stores does for a living.

18,373 views

From the outside it looks like an over-futuristic office, but it's a furniture factory. Today we visited Coomo in Houjie, a town in Dongguan which is China's biggest furniture cluster. It’s an example of Chinese manufacturers not just trying to win on price but pushing more into the high-end market. A single armchair costs around €1,500. 6,000+ employees, 14 factories, about 1 million m² of factory floor. The site used to be a shoe factory. COOMO bought the land and built this crazy complex on it. Production happens inside, a few floors are set aside as showrooms, and the roof is terraces and gardens. Some notes i took during our visit: > Work runs 8–12, then a 2-hour lunch, then 2–6. Eight hours a day. > No fixed weekends. Instead everyone gets 4 days off a month to take whenever they like, and can work extra shifts if they want. Common in China, people want to earn more. > they regularly host rooftop parties with jazz bands and barbecues for employees. There was one the week before we came. >They farm vegetables on their rooftop: 200 plant varieties, 6 full-time gardeners, and the vegetables go into the cafeteria. Also a big employee benefit: They help employees get a local hukou. Hukou is China's household registration system. Yours is tied to where your family is registered, usually your hometown, and it decides where you get access to public schools, healthcare and social benefits. A migrant worker in Dongguan can get a residence permit, but without a local hukou their kids face restrictions in local schools and exams. Getting one is slow and conditional. Coomo uses its standing as a large employer to sponsor workers' applications, and in practice the worker's hukou is often held in the company's collective registry. Leaving the job means moving it out, so it's both a real perk and a strong reason to stay. We met two Austrian real estate professionals here. Their take is that some products are more fitting for the Middle East and wouldn’t work for Europe, but the ones that do are extremely high quality and still significantly less expensive compared to their western equivalents.

From the outside it looks like an over-futuristic office, but it's a furniture factory. Today we visited Coomo in Houjie, a town in Dongguan which is China's biggest furniture cluster. It’s an example of Chinese manufacturers not just trying to win on price but pushing more into the high-end market. A single armchair costs around €1,500. 6,000+ employees, 14 factories, about 1 million m² of factory floor. The site used to be a shoe factory. COOMO bought the land and built this crazy complex on it. Production happens inside, a few floors are set aside as showrooms, and the roof is terraces and gardens. Some notes i took during our visit: > Work runs 8–12, then a 2-hour lunch, then 2–6. Eight hours a day. > No fixed weekends. Instead everyone gets 4 days off a month to take whenever they like, and can work extra shifts if they want. Common in China, people want to earn more. > they regularly host rooftop parties with jazz bands and barbecues for employees. There was one the week before we came. >They farm vegetables on their rooftop: 200 plant varieties, 6 full-time gardeners, and the vegetables go into the cafeteria. Also a big employee benefit: They help employees get a local hukou. Hukou is China's household registration system. Yours is tied to where your family is registered, usually your hometown, and it decides where you get access to public schools, healthcare and social benefits. A migrant worker in Dongguan can get a residence permit, but without a local hukou their kids face restrictions in local schools and exams. Getting one is slow and conditional. Coomo uses its standing as a large employer to sponsor workers' applications, and in practice the worker's hukou is often held in the company's collective registry. Leaving the job means moving it out, so it's both a real perk and a strong reason to stay. We met two Austrian real estate professionals here. Their take is that some products are more fitting for the Middle East and wouldn’t work for Europe, but the ones that do are extremely high quality and still significantly less expensive compared to their western equivalents.

11,233 views

Our recent experiments showed us how data diversity beats quantity by lengths. A non-actuated movable base is coming soon, but until then we‘re just creating diversity by moving the table into every room of our office.

Our recent experiments showed us how data diversity beats quantity by lengths. A non-actuated movable base is coming soon, but until then we‘re just creating diversity by moving the table into every room of our office.

18,085 views

Time to get used to teleoperation on an upgraded hardware stack! Thank you Jannik Grothusen for building such an insane arm! 👊

Time to get used to teleoperation on an upgraded hardware stack! Thank you Jannik Grothusen for building such an insane arm! 👊

44,583 views

We‘re gonna be doing DAgger style data collection soon. But the leader arms can’t carry their own weight and would need to follow the leaders at all time. That feels messy, so Aurel Arnold implemented a teleop setup with the Quest in the last 1.5 days. First configuration is working now, but not feeling 100% natural yet. Hard to describe why.

We‘re gonna be doing DAgger style data collection soon. But the leader arms can’t carry their own weight and would need to follow the leaders at all time. That feels messy, so Aurel Arnold implemented a teleop setup with the Quest in the last 1.5 days. First configuration is working now, but not feeling 100% natural yet. Hard to describe why.

19,940 views

This figure from HIL-SERL is one of the clearest visualisations of how RL learns differently from imitation learning. The difference comes down to this: imitation learning treats each (state, action) pair as independent. A correction at timestep 20 teaches nothing about timestep 19 or 21. RL propagates reward backward through time. One successful insertion updates the value estimate of every state along the trajectory. So RL builds a full map of "which states lead to success"; imitation learning just memorizes individual snapshots. Setup: a robot inserting a RAM stick into a motherboard slot. Each dot is an end-effector position (Y = lateral, Z = height). Starting position is randomized. Left to right = training progressing. Top row (RL): the policy builds a funnel. Broad at the top, narrowing into the target. It systematically fills in the state space, learning which paths lead to success from many different starting positions. Bottom row (imitation learning / HG-DAgger, same human data): sparse, diffuse, no funnel. The policy only learns near states the human demonstrated. Both have access to the same data, including human corrections, but a completely different structure emerges.

This figure from HIL-SERL is one of the clearest visualisations of how RL learns differently from imitation learning. The difference comes down to this: imitation learning treats each (state, action) pair as independent. A correction at timestep 20 teaches nothing about timestep 19 or 21. RL propagates reward backward through time. One successful insertion updates the value estimate of every state along the trajectory. So RL builds a full map of "which states lead to success"; imitation learning just memorizes individual snapshots. Setup: a robot inserting a RAM stick into a motherboard slot. Each dot is an end-effector position (Y = lateral, Z = height). Starting position is randomized. Left to right = training progressing. Top row (RL): the policy builds a funnel. Broad at the top, narrowing into the target. It systematically fills in the state space, learning which paths lead to success from many different starting positions. Bottom row (imitation learning / HG-DAgger, same human data): sparse, diffuse, no funnel. The policy only learns near states the human demonstrated. Both have access to the same data, including human corrections, but a completely different structure emerges.

24,433 views

First day designing and experimenting with new grippers

First day designing and experimenting with new grippers

11,634 views

Videos

DominiqueCAPaul's profile picture

China, day 7 Highlight today was the LED manufacturer and walking their production floor. Comments under my other post today explained that wages in places like these are well above minimum wage, more like ¥6-8k a month. That puts cost per worker close to the factories I visited in Poland … but with roughly 20 more hours of work per worker per week. The longer I'm here, the more China reminds me of the US in one way: the media covers the extremes, and in everyday life you feel very little of them. Key difference: US has more influence over global media while reporting on china abroad is one-sided with few people setting foot here. Lunch was Cantonese and Beijing food, including Peking duck. Very fatty skin, very good. Like with other dishes here, part of the point is showing how fresh it is, so the duck gets carved in front of you. Three tables = three cooks carving. Then the Foshan hydrogen lab: 140 researchers on fuel cells and ammonia-hydrogen. Nanhai, a district of Foshan, is a hydrogen cluster with 160+ companies. One of their projects is powering robots with hydrogen. They also spin off ~10 companies a year. Interesting learning: Research institutes like this one align their planning with China's 5-year plan. Obvious in hindsight. "5-year plan" sounds very communist, but the more I thought about it I thought that an election cycle isn’t that different, except that the guys doing the 5-year plan think more long term. Evening in Foshan's city centre. A temple, a local hotpot cooked in rice water instead of oil or broth. Then walked around the city centre. Fewer towers than Guangzhou, but a surprising number of high-end stores. Could have been Japan. Prices are the same as in Europe. Contrasted with this morning’s factory wages, I am wondering what the average customer in these stores does for a living.

Dominique Paul

18,373 views • 29 days ago

No more content to load