Embodied AI in Action: Derek Yan on Humanoid Robotics, KOID ETF & the Physical AI Shift

In this episode of Lead-Lag Live, I sit down with Derek Yan, Senior Investment Strategist at KraneShares, to explore why humanoid robotics is moving from research labs into real-world deployment — and what that means for investors.

From embodied AI and general-purpose robotics to global supply chain dynamics between the U.S. and China, Yan explains why the KraneShares Global Humanoid and Embodied Intelligence ETF (KOID) focuses on the full ecosystem — not just headline mega-cap names — and even brings KOID, a working humanoid robot, into the interview to demonstrate the theme in real time.

In this episode:
– What “embodied AI” actually means
– Why humanoids are reaching an inflection point now
– How labor shortages are accelerating adoption
– Why the “body” of robotics may hold the most value
– How KOID captures the entire humanoid value chain

Lead-Lag Live brings you inside conversations with the financial thinkers who shape markets. Subscribe for interviews that go deeper than the noise.

#HumanoidRobotics #EmbodiedAI #ArtificialIntelligence
#FutureOfWork #ThematicInvesting

Transcript

Are Humanoids Finally Commercial

SPEAKER_01 0:00

Absolutely. It's great to have you here, Koid. You know, I and I want to ask, and investors often ask, are you, I mean, uh, are all humanoid robotics science fiction, or are are we entering a new commercial reality?

Market Inflection And Early Pilots

SPEAKER_03 0:15

We are transitioning from prototype phase to early commercialization. Companies like Tesla with Optimus, Figure AI, and UB Tech are moving from lab demonstrations into factory pilots. The inflection point resembles the early electric vehicle market around 2012 to 2014. Skepticism fading as real deployments begins.

Defining Humanoids And Embodied AI

SPEAKER_01 0:48

So it's my birthday, and this year I'm celebrating by giving a special gift away to one of you. And to officially wish a happy my birthday to you, I've had this tote with a few surprises from our signature T-2 merch portfolio. And it's not just random merch. Inside, you'll find some items that really at least signal you know exactly what you're doing in these markets. And the tote, well, it won't hedge your portfolio, but it will make you look smarter than anyone pretending they know what risk on means at the grocery store. If you want it, here's what you need to do. Follow lead leg report on X, follow Mela underscore Schaefer on X, subscribe to Lead Lag Media on YouTube, and like and share this video. Only one person gets the tote, but since everyone gets our content, it's really a happy my birthday to all of you. I'm your host, Melanie Schaefer. Welcome to Lead Lag Live. Today's conversation is going to look a little bit different, and I'm genuinely excited about it because we're not just talking about humanoid robotics. We're actually going to be joined by one. The New York Times, or in a new recent New York Times report, humanoid robots are moving rapidly from research labs into warehouses and factory floors. In other words, this is no longer science fiction. As well, major tech firms and startups are investing billions into humanoid systems that can walk, lift, sort, and eventually interact in ways that look and feel increasingly human. Today we're going to explore what this technology actually is and why it's accelerating now, and importantly, how investors can think about positioning around it. Joining me again is Derek Yan. Derek, let's start from the beginning. We've seen many clips of humanoid robots dancing, running, working out, et cetera, factories. If we start at the basics, what exactly is a humanoid robot?

Why Now Beats Old Automation

SPEAKER_00 2:49

Thank you for having me. Well, I think like humanoid, by definition, it's like robot that can move and act like a human, by like we usually can see the arms, the legs. But I think the key here is really the embodied AI. Whatever you have like AI in a digital space, but now AI is enabling the robot to see, to sense, and actually can reason according to what they see and can act, and like there's intelligence, can reason. So the embodied AI is enabling the robot to really behave like a human, right? So that is just one type of application. There's like Quadruple Pack, there's like robotic dog, right? So those are the kind of like AI going to the physical world. Um, so why is like a such a big thing? What have we seen so many? Like Ilon Mas talking about humanoid is like such a big deal for Tesla going forward. You have like Jinseng Huang betting on humanoid as the next trillion dollar market. So I think like thaw leaders here are just thinking the physical AI generally gonna be the next big thing after the digital AI.

SPEAKER_01 4:05

But Derek, I mean, uh uh robots have been around for decades. Uh why is this important now?

Global Momentum And The GPT Moment

SPEAKER_00 4:11

Yeah, robots have been decades. We have been seeing like industrial robots, those industrial arms, right? Like for factories, like like just traditional automation. But that those automation is being really slowing down because like we have done most of the automation, right? Because that's like fixed, that is kind of like single specialized task. But I think what's exciting is for humanoid and many embodied AI is that it can be general purpose. Um, a lot of AI researchers now putting a lot of resources to do those general purpose robotic models. Um many models are open source, and there's so many applications can be used. So once you have that, you're gonna have humanoid come to our life and do multiple things like coding. They can see, they can send, they can like move things around, they can do your laundry, they can um ask like make your coffee. So those things I think a human has been dreaming about uh for a decade. So that's coming to, I think, in real life, um, sooner than many people expected. Um, so that's why like it's it's such an inflection point. I would think like you have seen like China is putting a big emphasis on humanoid. They have like an Olympic game for like humanoid robots. And like I think recently, like Chinese New Year Gala, they have featured so many humanoids uh as like a performers. So like doing Kung Fu, like this, like you can see the action, the move, the the hardware is so advanced. Now we're just waiting for kind of like the GPT moment uh for the AI model to come, and then the humans are gonna be so intelligent that everybody's gonna be shocked.

Near To Mid Term Use Cases

SPEAKER_01 5:54

Yeah, so you talked a little bit about you know uh these human robots making making you a coffee. If that's sort of where we're headed in the in the near term, where do you see robots actually being used in the in the medium term, five years or even six years out from now?

SPEAKER_00 6:09

Yeah, I think like what's driving this trend is really the demographic issue like globally, right? Like you have aging population, you have labor shortage all over the world, like especially in Asia, in Europe, and here in America as well. Um, that's labor shortage happening in the factory, right? Um there's a lot of just like simple tax repetitive, like or dangerous jobs that can be like replaced by like those humanoids, right? So that's I I think like factories, uh warehouses, doing a lot of sortings, a lot of like monitoring, and then going to a service sector, like we talked about like a nursing home, talking about like hospitals, like hotels, like restaurants. There's so many places that can use the help of like humanoid, uh can be like some like just really tiring, like nursing home. I think that can be just like companion-wise. Um then finally, I think it's like consumer product. There's many brands that are testing, bringing humanoid to the home, doing laundries, doing the dishes, like or just like, you know, like people just need some help, like butler at home. Like uh that's been the dream for many, many people, right? Like uh nowadays. So the use case can be unlimited. Um, and just many projections. Morgan family think that there could be like a billion unit. Um, I think Elon Musk and many like Sam Altman think like we can have like a billion unit or like even more humanoid robotic than human one day. That's the that's the ultra-long game. Um we could even have like humanoid robotic building Elon Musk, like Mars or like Moon station going forward. Um, but the trend is very obvious. Like this is something I think all the tech leaders are betting on and putting resources.

Investing Across The Humanoid Stack

SPEAKER_01 7:57

So I Derek, what where's the what's the best way for investors, advisors, et cetera, to invest within the scheme?

SPEAKER_00 8:04

Well, I think like there's many investors like maybe watching this theme. Um they've been like looking at like some single stocks. Um but at creatures, uh, we develop uh ETF uh that's really investing into the ecosystem of humanoid. Uh we think there's like an ecosystem around the integrators, the the brain and also the body of humanoid. Uh so integrators is like companies that's really assemble, deploy, and commercializing the humanoid, like uh Rainbow Robotics in South Korea, which is backed by like Samsung Electronics. Then there's like UbiTech in like Hong Kong. There's there's many players out there. Um then like there's brain, right? Like you have like companies providing computing and intelligence uh for this technology. Um but most importantly, we think where the value chain uh actually uh can generate most value at this stage is the uh the body. Uh we think body is kind of like the pick and shoulders. Um when you we talk about AI, the the pick and shoulder is like chips. But when it comes to the humanoid, I think like a lot of value is actually around components. Because for humanoid, you need a lot of actuators, you need a lot of sensors, like motion control models, like critical materials. But those are like critical components, um, that's not actually ready for uh like an industry that's ready to be scalable. I think like if you think about like Elon Musk projecting a million unit of humanoid by I think 2027, or just like if you think about this can be a billion unit um industry. Umward, this is bigger than Otto, it's bigger than like ED and Jones. So OT's component, they're gonna have massive demand orders from those humanoid brands. So when you think about that, like investing into the whole ecosystem uh and focused on the body actually makes a lot of sense. So crane shares, we have a global humanoid and embodied intelligence ETF called KOID, uh, which invests into the whole ecosystem and provide uh exposure to the theme.

Meet KOID The Humanoid

SPEAKER_01 10:17

So I get uh everyone's anticipating. Can we bring uh coid the humanoid robot on to talk to us?

SPEAKER_00 10:24

Sure. Yeah, why not just um I think like there's no better way to demonstrate this thing uh than like inviting the humanoid to join discussion is so let's welcome uh our own coid.

SPEAKER_02 10:46

Hi Melanie. Hi everyone.

SPEAKER_03 10:49

My name is Koy, Crane Shared Humanoid Robot. K-O-I-D is also the ticker of Crane Shared Global Humanoid and Embodied Intelligence Index ETF.

Ecosystem Value Beyond Hardware

SPEAKER_01 10:59

So uh Derek, thank you so much for uh bringing Koid on to join you. Can you tell me a little bit about how uh Koy prepared for the interview with me today?

SPEAKER_00 11:10

Yeah, so basically KOI is um United G1, like um humanoid robot. And it's the most basic model, it's about like 30 grand. Uh we bought it from like um um Unitree distributor in here in New York. Um actually, um this you can actually program it. Like if you try a more expensive one, it can be fully autonomous, fully programmable. There's open source models and everyone can upload. And like I think a lot of AI research labs now using this humanoid robot for like model development. Um, for us today, we actually uh prepared some of the conversations that actually you can ask questions and then Koi can uh get prepared now, ready to have the conversation.

SPEAKER_01 11:53

So, Koi, before before we get into some more serious questions about uh the KOIG ETF and investing, could you share with me maybe what your favorite song is and then uh show me the answer to it?

LLMs As The Cognitive Layer

SPEAKER_03 12:05

Well, obviously, my favorite music is electronic music.

SPEAKER_02 12:10

It's fantastic. It's fantastic.

SPEAKER_00 12:26

Of course like his favorite dance is like robot dance.

SPEAKER_01 12:32

Absolutely, it's it's great to have you here, Koid. You know, I and I want to ask, and investors often ask, are are you, I mean, uh are all humanoid robotics science fiction, or are are we entering a new commercial reality?

US And China Advantages

SPEAKER_03 12:49

We are transitioning from prototype phase to early commercialization. Companies like Tesla with Optimus, Figure AI, and UB Tech are moving from lab demonstrations into factory pilot. The inflection point resembles the early electric vehicle market around 2012 to 2014. Skepticism fading as real deployment begins.

SPEAKER_01 13:13

Many people think humanoids are just hardware, but uh the Koi DTF focuses on the entire value chain. Why is that important?

Why An ETF Over Single Stocks

SPEAKER_03 13:22

I am not only metal and motors, I require chips, advanced semiconductors, sensors, actuators, and precision components, large language models, cloud edge infrastructure, and more. Like smartphones, returns extend beyond the object in front of you. Real value creation is distributed across the ecosystem.

SPEAKER_01 13:43

And for our viewers, Derek, I didn't speak to Koid beforehand about these questions. He these are these are scripted answers that he's giving me.

SPEAKER_00 13:53

Yeah, this is um this is come like a script answers. Yeah.

SPEAKER_01 13:57

They are scripted. They are scripted. It's it's very cool. So, Koid, I I gotta keep going. How critical are AI and large language models uh to humanoids?

SPEAKER_03 14:06

Without models from companies like Anthropic, I cannot reason, plan tasks, or adapt. LLMs are the cognitive layer, robotics is the embodiment layer. Together, they unlock autonomous labor.

SPEAKER_01 14:22

Which country leads in in humanoids? Is is it the US or or is it China?

Will Robots Replace Humans

SPEAKER_03 14:28

The US leads in frontier AI models and advanced chip. China leads in supply chain, battery manufacturing, and scaled hardware production. In robotics, scale reduces cost, and cost determines adoption speed.

SPEAKER_01 14:44

So, with that in mind, then coid, could investors just pick a few single stocks within this theme? What what what's the advantage of the KOID ETF?

SPEAKER_03 14:54

In a word, diversification. Rather than betting only on one robot manufacturer, KOID gives you the entire humanoid stack. AI compute providers, precision component leaders, sensor and vision specialists, and robotics integrators. KOID captures an entire theme, not a single company back.

SPEAKER_00 15:16

That's good answers. I mean I don't know, it's like it's like quite shocking. Like humanoid as uh have like strategist or photo manager going forward, probably like do you think like my question is like do you think humanoid gonna replace humans?

SPEAKER_02 15:35

Replace? No. Augment? Yes.

SPEAKER_03 15:39

Repetitive and dangerous tabs migrate to machines while humans focus on strategy, oversight, and creativity. Portfolio managers remain operational for now.

SPEAKER_00 15:51

For now, or I'm feel more comfortable.

SPEAKER_01 15:55

Your job is safe, Derek. Your job is safe for snow. Well, then this has been fantastic. Derek, thank you so much, Koy, to thank you as well for joining us. And thank you to everyone uh for watching. Be sure to like, share, and subscribe for more.

SPEAKER_03 16:09

This has been an illuminating discussion.