Best Podcast Episodes About Neura Robotics
Everything podcasters are saying about Neura Robotics — curated from top podcasts
Updated: Apr 01, 2026 – 35 episodes
Listen to the Playlist
Ridealong has curated the best and most interesting podcasts and clips about Neura Robotics.
Top Podcast Clips About Neura Robotics
“… cradle with that 98-pin connector, a crunch, and then you connect it with the cable and it would sync. I just think that Wikipedia, by the way, U.S. Robotics bought Palm and then eventually robotics got bought by 3Com. And so you might have been thinking of either 3Com or U.S. Robotics. No, U.S. Robotics is what I was thinking of, the modem company. But they had the right idea and it was a better product. But I don't think anything better exemplifies the dysfunction of what Scully's Apple became than not that the Newton had shortcomings, but that it was such a spiteful silo from the Mac. Like …”
“… Pilot and then come back to your Mac and connect it and sync. And then it would be in whatever your contacts app was on your Mac. And no, it didn't sync automatically because neither device had always on networking. But you put on a terrible little cradle with that 98-pin connector, a crunch, and then you connect it with the cable and it would sync. I just think that Wikipedia, by the way, U.S. Robotics bought Palm and then eventually robotics got bought by 3Com. And so you might have been thinking of either 3Com or U.S. Robotics. No, U.S. Robotics is what I was thinking of, the modem company. But they had the right idea and it was a better product. But I don't think anything better exemplifies the dysfunction of what Scully's Apple became than not that the Newton had shortcomings, but that it was such a spiteful silo from the Mac. Like spitefully unrelated to the Macintosh in any way and in any kind of syncing or anything. I don't think it was spite. I think it was aspiration. It was aspirationally disconnected. They were trying to make the clean break that eventually would come with the phone, but they did it in the wrong way. Well, and there was a story there, a bit of the spite, …”
View more
Ridealong summary
Apple's Newton was a groundbreaking idea that ultimately failed due to internal dysfunction and lack of compatibility with the Macintosh. This was a pivotal moment showcasing the disconnect between teams at Apple, which led to missed opportunities in the tablet market. The story highlights how aspirations clashed with reality, resulting in a product that was isolated from its own ecosystem.
“… team and like as fast as possible. And, um, I knew how to spin up hardware and software. Again, you know, the, the, the key characteristics of robotics, like electric motors, battery systems, uh, you know, control software, embedded systems and sensors. And then, you know, within like electric motors, we build actuators. They have like a rotor and stator and a gearbox and sensors, uh, electronics and wiring and connectors and, uh, multiple sensors inside of there uh and then firmware it lives on the the like say the microcontroller lives inside the on the motor control side uh and then we have …”
“… like basically self-fund a lot of it in the first i the first year i self-funded all of it no kidding yeah and it was a lot i mean we got the business to a million a month of burn in month four and uh but it was like i knew what to do we built a 40 person team and like as fast as possible. And, um, I knew how to spin up hardware and software. Again, you know, the, the, the key characteristics of robotics, like electric motors, battery systems, uh, you know, control software, embedded systems and sensors. And then, you know, within like electric motors, we build actuators. They have like a rotor and stator and a gearbox and sensors, uh, electronics and wiring and connectors and, uh, multiple sensors inside of there uh and then firmware it lives on the the like say the microcontroller lives inside the on the motor control side uh and then we have like thermal characteristics it's hot um and then you gotta all make that work at very like high speeds and high torques meaning motors don't like working when they're not moving motors hate not moving motors want to run on highway speeds okay they love that like whether it's a like a generator like uh something you know an appliance in your home …”
View more
Ridealong summary
Brett Adcock shares his groundbreaking journey in robotics, revealing how he built a humanoid robot capable of walking within just 12 months. In 2022, he founded his company with no precedent in AI or humanoid hardware, facing skepticism and self-funding the project. Against the odds, he assembled a team and developed the first generation of a humanoid robot, achieving a historic milestone in robotics innovation.
“… be an astronaut and it turns out i'm not an astronaut, that's okay. But we, along the way, especially when I was running the previous company, Open Robotics, I took every opportunity to work with NASA. Like any time that our friends and colleagues at NASA called and said, hey, we've got this like crazy research project. You guys want to help out with it? I was like, yes, every time. Yes. Just because I think there's such, like there's just such inherent virtue in space exploration that it's always worth doing. And And one of the projects that folks at NASA Ames did was they built what's called the …”
“… wear a like jumpsuit the whole week and you know kind of learn a lot about the space program kind of pretend to be an astronaut in a lot of ways that was fantastic you know at that point like every kid who had that experience i thought i'm going to be an astronaut and it turns out i'm not an astronaut, that's okay. But we, along the way, especially when I was running the previous company, Open Robotics, I took every opportunity to work with NASA. Like any time that our friends and colleagues at NASA called and said, hey, we've got this like crazy research project. You guys want to help out with it? I was like, yes, every time. Yes. Just because I think there's such, like there's just such inherent virtue in space exploration that it's always worth doing. And And one of the projects that folks at NASA Ames did was they built what's called the Astro-B. It's a cube-shaped robot that's like 18 inches on a side. And they've got, I think, three of them inside the International Space Station. They've got fans on each side, and they free-fly around inside the space station. And they help astronauts to do their work. They can do some kind of surveillance tasks inside the space station measuring …”
View more
Ridealong summary
Brian Gerkey, CTO of Intrinsic, reveals how robotics software he helped create powers the Astro-B robots on the International Space Station. These cube-shaped robots assist astronauts by performing surveillance tasks and providing real-time data to mission control. Gerkey envisions expanding this technology beyond manufacturing to revolutionize space and ocean exploration.
“… makes sense last question from my side then we'll let you go did you have any takeaways or kind of ideas around the diffusion of physical AI and robotics. Did anything stand out? Do you have a strong opinion there? Right now, it feels like we've entered this sort of software singularity, but we just had Kaser from Applied Intuition on, and we're talking with him about how autonomy and AI is diffusing through the physical world, but I'm curious if you had any takeaways. Yeah, I mean, look, I think that, you know, One thing sometimes people don't quite understand is that large language models and …”
“… know one might say people gang up on NVIDIA that's the occupational hazard of being the leader right I think they'll deal with it I mean I don't think it's a winner takes all market by the way I think that you know there'll be space for others yeah that makes sense last question from my side then we'll let you go did you have any takeaways or kind of ideas around the diffusion of physical AI and robotics. Did anything stand out? Do you have a strong opinion there? Right now, it feels like we've entered this sort of software singularity, but we just had Kaser from Applied Intuition on, and we're talking with him about how autonomy and AI is diffusing through the physical world, but I'm curious if you had any takeaways. Yeah, I mean, look, I think that, you know, One thing sometimes people don't quite understand is that large language models and the transformer architecture that underpins them is super consequential for lots of applications, not just chatbots. And so robotics is being improved by this technology. And I fully expect to see a huge breakthrough over the next two or three years with the capability of robotics.”
View more
Ridealong summary
Expect major advancements in robotics driven by AI within the next two to three years. The integration of large language models and transformer architecture is enhancing robotics, moving beyond just chatbots. This evolution marks a pivotal moment in the diffusion of AI into the physical world.
“… And then I began to get into things like building and manufacturing for building ships or submarines, injecting the same kind of tech and robotics and software there because we have the most data about the health and the material science of the world. And so applying it for actually building and welding. And then the Navy side, what we're doing there is helping to achieve readiness. 80% readiness is the Secretary Phelan's objective. And right now it's about two out of five ships are stuck in dry dock somewhere, and that's a global issue. And so our technology allows for us to be able to …”
“… company was build tech for the people in the environment And so that led us to oil and gas Next we could apply the same kind of technology to diagnose the health of structures that make the oil and gas assets go And then it was mining and metal manufacturing. And then I began to get into things like building and manufacturing for building ships or submarines, injecting the same kind of tech and robotics and software there because we have the most data about the health and the material science of the world. And so applying it for actually building and welding. And then the Navy side, what we're doing there is helping to achieve readiness. 80% readiness is the Secretary Phelan's objective. And right now it's about two out of five ships are stuck in dry dock somewhere, and that's a global issue. And so our technology allows for us to be able to make up that difference by getting so much information, in some cases, two, three, four months faster to be able to get these ships out of dry dock in time and then begin to plan it for the future. It's just like idea of if you always had a living, breathing understanding of the health of these sorts of assets, my goodness, maybe you'd never have to …”
View more
Ridealong summary
A tech company is transforming industries like oil and gas by developing robotics that diagnose asset health in real-time, potentially saving millions. By building technology directly in the field rather than in labs, they aim to enhance operational efficiency and reduce downtime for critical assets like naval ships. This innovative approach challenges traditional methods and could reshape how capital-intensive sectors operate.
“That's right, everybody. You just wanted a laundry bot, but we got so much more. Yeah, so Figure Robotics just launched a new version of their Helix O2 model, which is their kind of model that drives their robots. This allows autonomous cleanup of a living room. And, Kevin, I feel like robots are kind of like in the maybe even GPT-3 era right now or even GPT-2 where it's like, oh, that's so cute. They can do X, Y, and Z. You can see it. You see the promise. It's on the horizon. Yeah. And what's interesting is like this robot in this video, if …”
“That's right, everybody. You just wanted a laundry bot, but we got so much more. Yeah, so Figure Robotics just launched a new version of their Helix O2 model, which is their kind of model that drives their robots. This allows autonomous cleanup of a living room. And, Kevin, I feel like robots are kind of like in the maybe even GPT-3 era right now or even GPT-2 where it's like, oh, that's so cute. They can do X, Y, and Z. You can see it. You see the promise. It's on the horizon. Yeah. And what's interesting is like this robot in this video, if you're not watching the video, is basically on its own cleaning up a very nice modern living room and going through it. It's going very slow, but this is a step because it's autonomous, right? And we've talked about many of these robot videos are driven by people behind the scenes in a different country, like kind of driving a thing. This is the robot …”
View more
Ridealong summary
A new robot from Figure Robotics can autonomously clean your living room, showcasing human-like behaviors that are both amusing and impressive. This robot not only wipes surfaces with flair but also demonstrates unique problem-solving skills, like throwing pillows back onto the couch. It's a glimpse into the future of household robotics that feels both familiar and oddly charming.
Ridealong summary
Overhead robotic chargers are transforming how electric vehicles are charged in Chinese parking garages. These innovative units run on ceiling tracks, allowing multiple parking bays to share a single power source, effectively turning every spot into a charging station. This technology not only saves space but also enhances safety and efficiency in busy car parks.
“… sharing a house in London with some friends who, like her, grew up in Romania, and these friends all had day jobs, but they also had a passion for robotics. The house itself was a kind of typical old British house. And every time we were away, there was nothing at the time on the market to be able to monitor the home, apart from having a full-on British CCTV system that you have the hard wire to the walls and everything else. So the initial idea that we had was like, what if we actually can make a camera on wheels that can move around and provide check-ins and security for the house so you're no …”
“… the best minds in the sector and in the field and learn from them while you go through that journey. That experience at Pixel and then Google Home Devices came in handy on a new project, one she could call in part her own. About a decade ago, Oana was sharing a house in London with some friends who, like her, grew up in Romania, and these friends all had day jobs, but they also had a passion for robotics. The house itself was a kind of typical old British house. And every time we were away, there was nothing at the time on the market to be able to monitor the home, apart from having a full-on British CCTV system that you have the hard wire to the walls and everything else. So the initial idea that we had was like, what if we actually can make a camera on wheels that can move around and provide check-ins and security for the house so you're no longer connected to one room, one wall, and you can actually drive that around from a remote control through an app and see your home. So we started with a security angle and very quickly from there, we actually thought, OK, what if we actually made this a bit taller and you can also put a screen on it so you can also interact with people if they …”
View more
Ridealong summary
AI is transforming warehouse jobs by upskilling workers into data analysts, demonstrating that automation enhances human roles rather than eliminating them.
“… the physical world. And they've had to focus on operational efficiencies to scale. So in 2012, Amazon bought Kiva Systems, which turned into Amazon Robotics. And that's a big risk to buying a big company. And we think that, you know, if this turns into, if this $100 billion fund turns into sort of a private equity roll-up, you're going to ask the question, can Bezos buy a company for $1 billion, $5 billion, $10 billion, $50 billion, who knows, and operate it and scale it and actually continue to deliver value? And he certainly did that with Kiva Robotics, which turned into Amazon Robotics. which …”
“… never really had the zero marginal cost luxuries afforded to other pure play internet founders. Amazon's just always interfaced with the physical world. So it's been, even though it's a software company and a tech company, it's always interfaced with the physical world. And they've had to focus on operational efficiencies to scale. So in 2012, Amazon bought Kiva Systems, which turned into Amazon Robotics. And that's a big risk to buying a big company. And we think that, you know, if this turns into, if this $100 billion fund turns into sort of a private equity roll-up, you're going to ask the question, can Bezos buy a company for $1 billion, $5 billion, $10 billion, $50 billion, who knows, and operate it and scale it and actually continue to deliver value? And he certainly did that with Kiva Robotics, which turned into Amazon Robotics. which delivered over a million robots that are deployed across the operations network. So from fulfillment centers, warehouse automation, inventory flow, last mile delivery, all of these require tight integration between hardware and software to run smoothly. Bezos clearly loves this stuff. And you can actually see it when you look at his face, whenever he …”
View more
Ridealong summary
Jeff Bezos's obsession with technology and the physical world positions him uniquely to leverage a $100 billion AI manufacturing fund effectively.
Ridealong summary
Imagine a Mars rover that can adapt like a living creature instead of being pre-programmed. David Eagleman argues that our approach to technology should mimic biological flexibility, allowing machines to learn and adapt in real-time. This shift could revolutionize how we build robots and explore other planets.
Ridealong summary
If Huawei had access to TSMC's advanced chips, they might have surpassed NVIDIA as the leader in AI technology. With their history of innovation and vast resources, Huawei could leverage their strengths in software and hardware to dominate the market. This scenario underscores the shifting landscape of AI and the potential for unexpected players to rise to the top.
Ridealong summary
Oracle's recent quarter signals a pivotal shift in the software industry, as it takes a stand against what's being called the 'AI ghost trade.' This term describes the disconnect in tech investments where companies like Salesforce and ServiceNow are positioned to thrive, despite the market's uncertainty. By addressing these challenges, Oracle is setting a new course for resilience in the tech landscape.
Ridealong summary
In just a few years, robots could be seamlessly integrated into our daily lives, taking on complex tasks with minimal guidance. This shift mirrors the rapid evolution of mobile technology before the iPhone, where the unimaginable became reality almost overnight. As companies invest in intelligent machines, expect practical applications like self-driving cars and advanced mining robots to emerge, transforming industries and everyday experiences.
“… it. And it is just astonishing what you're actually able to do with just those things. I really think that this guy could go around to various robotics companies like the robot vacs that are adding arms and legs and just talk about like, what if we didn't make robot vacs look stupid? Or like the humanoid robots that we saw at CES where, you know, the one Allison saw that punched itself in the face and then knocked itself out. Like, what if the fundamental law of robotics, forget Asimov, was don't do anything stupid? One of the things was just like of course if a Furby hears another Furby why …”
“… and somehow under featured so they They just stripped everything out that wasn't relevant, which essentially left you with ears that move to express emotion, eyes that move to express emotion, and a mouth that moves to express communication. And that's it. And it is just astonishing what you're actually able to do with just those things. I really think that this guy could go around to various robotics companies like the robot vacs that are adding arms and legs and just talk about like, what if we didn't make robot vacs look stupid? Or like the humanoid robots that we saw at CES where, you know, the one Allison saw that punched itself in the face and then knocked itself out. Like, what if the fundamental law of robotics, forget Asimov, was don't do anything stupid? One of the things was just like of course if a Furby hears another Furby why would they not be like it would break that immersion and remind you that this thing had flaws and was a toy that wasn programmed to do certain things It's very philosophical. It really is. It's really fascinating. The thoughts of Furby and like what life is and how living things should act, which is, you know, you look at Furby and you wouldn't …”
View more
Ridealong summary
Furby isn't just a toy; it’s an 'inference machine' designed to mimic life through unique language and emotional responses. With its made-up language, Furbish, and the ability to learn from interactions, Furby was engineered to feel alive and unpredictable, challenging traditional robotic designs. This deep thought behind its development reveals how much personality can be infused into even the simplest toys.
“… same logic is going to apply to more advanced robots as well. That's why developing perception and visual understanding is critical for next wave of robotics. And it's a top priority for a lot of research labs as it's the next frontier. And there is no other way to improve video generation without visual understanding. Roughly, it takes around, I think people like to say that in one minute, we can read 200 words. One minute of the video can be described with maybe 10,000, 60,000 words. There is just so much going on. If you and I were having coffee after this episode, I'd certainly pull up my phone …”
“… it's still unclear if that's sort of the path to AGI, although that's definitely a path to advanced robotic systems. Like, I think Elon proved to the whole world that self-driving cars can work really well through just cameras. And I think the same logic is going to apply to more advanced robots as well. That's why developing perception and visual understanding is critical for next wave of robotics. And it's a top priority for a lot of research labs as it's the next frontier. And there is no other way to improve video generation without visual understanding. Roughly, it takes around, I think people like to say that in one minute, we can read 200 words. One minute of the video can be described with maybe 10,000, 60,000 words. There is just so much going on. If you and I were having coffee after this episode, I'd certainly pull up my phone and say, look what I tried this week. It changed how my tea works. This is what I do all the time To share these kinds of things that don fit into the podcast I started my own newsletter Every week I write about AI tools strategies and experiments I running in my own business with real numbers real results templates that you can use and also honest …”
View more
Ridealong summary
In the next decade, interactive media will redefine how we experience content, merging games and videos into a single adventure. This shift, driven by advancements in AI and robotics, will enhance marketing strategies and customer engagement. As creators harness these new tools, the landscape of social media will transform, focusing on short-form content and immersive experiences.
“… we kind of get the details worked out. But for example, this is an ideal and just high level for people that maybe don't know is that anything in robotics. Right. You are going to have some sort of compute for that AI inference piece. And that can be like an NVIDIA Jetson that can be a Thor or it can be something like a GB10. Right. So, you know, where we kind of see this is, you know, you mentioned developers as having kind of a quote unquote kit, right, where you have like something like a GB10 or some sort of RTX powered device that allows you to run kind of the local models, compute …”
“… bit about that compute piece. Right. You kind of mentioned kind of Dell and NVIDIA in there. And I know that we're working on some stuff. I mean, obviously can't talk about it now because we're not finalized. You know, we'll do another episode whenever we kind of get the details worked out. But for example, this is an ideal and just high level for people that maybe don't know is that anything in robotics. Right. You are going to have some sort of compute for that AI inference piece. And that can be like an NVIDIA Jetson that can be a Thor or it can be something like a GB10. Right. So, you know, where we kind of see this is, you know, you mentioned developers as having kind of a quote unquote kit, right, where you have like something like a GB10 or some sort of RTX powered device that allows you to run kind of the local models, compute inference, you know, wirelessly off it, where you're able to kind of create and then ultimately deploy onto the Rishi Mini. So tell us a little bit about the the demo where Jetson kind of showed up at GTC.”
View more
Ridealong summary
The Rishi Mini stands out as a wireless AI robot that offers fun and interactive capabilities, unlike its Lite counterpart. With a battery life of one to two hours, it allows users to take it anywhere, making it ideal for hobbyists and AI builders who want to experiment with local applications. This flexibility and ease of use set the Rishi Mini apart in the growing world of robotics.
“… China going to be better at this? Partly it's state backing. The state is, you know, has a lot of economic leverage and it's decided that humanoid robotics are a key part of its future industrial strategy. So they're throwing a lot of money behind it. They're putting in a lot of orders and they can soak up a lot of redundancy in terms of, you know, units being produced that aren't necessarily useful, but that help a company develop their technology. The other thing is that these Chinese companies are where all these components are coming from anyway. You know, you look at any company, any robot …”
“… Europe's not really in the conversation to be honest. US is the second place here, definitely. China is on outpace to outstrip America in this by the end of this century, no doubt at all. There's a number of different factors involved here. Why is China going to be better at this? Partly it's state backing. The state is, you know, has a lot of economic leverage and it's decided that humanoid robotics are a key part of its future industrial strategy. So they're throwing a lot of money behind it. They're putting in a lot of orders and they can soak up a lot of redundancy in terms of, you know, units being produced that aren't necessarily useful, but that help a company develop their technology. The other thing is that these Chinese companies are where all these components are coming from anyway. You know, you look at any company, any robot that's built in the US, sorry, and the vast majority of the components will be Chinese. These Chinese companies, they're all next door to each other. This really helps with prototyping. If you have a robot that you're trying to develop and you're like, ah, this part doesn't quite work. I need to do this. Rather than waiting two, three weeks for those …”
View more
Ridealong summary
China is set to dominate the robotics industry by the end of the century, thanks to state backing and a robust supply chain. In contrast, the US excels in software quality and user experience, but this may not be enough to compete with China's mass production capabilities. Analysts liken this competition to an industrial Cold War, where the first country to master humanoid robotics could control the global economy.
“We just talked about robotics and whether we're on the verge of a chat GPT moment. What about you talk about science and scientific research towards the end. How close do you think we are to waking up tomorrow and being like, oh, we just cured Alzheimer's? Maybe that's that's too. But like, how close do you think we are to seeing real scientific breakthroughs because of this AI era? Yeah, I think we're already there. They're happening every day. My favorite fact about this, …”
“We just talked about robotics and whether we're on the verge of a chat GPT moment. What about you talk about science and scientific research towards the end. How close do you think we are to waking up tomorrow and being like, oh, we just cured Alzheimer's? Maybe that's that's too. But like, how close do you think we are to seeing real scientific breakthroughs because of this AI era? Yeah, I think we're already there. They're happening every day. My favorite fact about this, people don't realize that without AlphaFold or maybe it was an earlier version of AlphaFold, which is the protein folding model created by DeepMind, you would not have the COVID mRNA vaccine. It was the speed of that rollout was uniquely enabled by that. Like you cannot go to one of these scientific conferences and not see thousands, tens of …”
View more
Ridealong summary
AI is already revolutionizing scientific breakthroughs, enabling advancements like the COVID mRNA vaccine thanks to innovations such as AlphaFold. This technology is not only foundational for molecular medicine but is also paving the way for future pharmaceutical developments. However, the application of AI raises concerns about its use in surveillance and control, highlighting the need for a balance between innovation and ethics.
“… 它是这个clustering这种就是聚类 就是发现这有一堆点云 它可以聚到一块 它是通过这样的方式去判断这有没有障碍物 那后来逐渐变成了神经网络去做这个推理 所以它的就是说整体的自动驾驶 在18年的技术架构和08年的技术架构没区别 但是这一套技术架构的底层逻辑不是AI的 它的底层逻辑是Robotics的 就是Robotics的底层逻辑 在我的观察我的认识上不一定对 它是做系统拆分 然后呢关注corner case 正是因为他关注corner case 所以他要把这个系统分成一个一个可解释的模块 然后在这个可解释的模块里边去解决这些case的问题 AI的方法论不是这样 AI的方法论是追求数据驱动 然后端到端 然后呢AI不太擅长解决一个两个具体的case 但是它特别擅长的是我从整体上提升benchmark的性能 我在一个大的benchmark之前是80 我一波优化干到90 再一波优化干到95 那这里边90到95肯定我有相当多的case变好了 不排除有部分的case变差了 所以这个就是我们看到当时看到就是Robotics driven的这个技术架构 是分模块感知对控定位 然后离线建图 但是AI的底层逻辑其实不是这个 AI的底层逻辑就是端到端 然后呢 同时间其实18、19、20年那会儿 就是特斯拉开始去做自动驾驶 而且是用AI的方式推端到端的 他最早做端到端是什么呢 是把这个感知先统一 …”
“… 和08年那会儿的自动驾驶的大的技术架构框架 其实都一样 没没区别 08年的paper里面已经说清楚了 这事分感知分这个定位 然后离线做好箭图 然后感知定位之后在这个地图里边做这个规控 然后呢 感知做的好一些规控 这边就可以做更好的这个避让动作 做判别 然后规控里边先是决策 再是规划 然后是控制 大的paper08年就是这个样子 只不过呢 后来随着AI技术的成熟 尤其是在CV领域的成熟 把很多感知部分的模块替换成了这个AI的算法驱动的 比如说最早的就是这个激光雷达 最早激光雷达是什么 它是这个clustering这种就是聚类 就是发现这有一堆点云 它可以聚到一块 它是通过这样的方式去判断这有没有障碍物 那后来逐渐变成了神经网络去做这个推理 所以它的就是说整体的自动驾驶 在18年的技术架构和08年的技术架构没区别 但是这一套技术架构的底层逻辑不是AI的 它的底层逻辑是Robotics的 就是Robotics的底层逻辑 在我的观察我的认识上不一定对 它是做系统拆分 然后呢关注corner case 正是因为他关注corner case 所以他要把这个系统分成一个一个可解释的模块 然后在这个可解释的模块里边去解决这些case的问题 AI的方法论不是这样 AI的方法论是追求数据驱动 然后端到端 然后呢AI不太擅长解决一个两个具体的case 但是它特别擅长的是我从整体上提升benchmark的性能 我在一个大的benchmark之前是80 我一波优化干到90 再一波优化干到95 那这里边90到95肯定我有相当多的case变好了 不排除有部分的case变差了 所以这个就是我们看到当时看到就是Robotics driven的这个技术架构 是分模块感知对控定位 然后离线建图 但是AI的底层逻辑其实不是这个 AI的底层逻辑就是端到端 然后呢 同时间其实18、19、20年那会儿 就是特斯拉开始去做自动驾驶 而且是用AI的方式推端到端的 他最早做端到端是什么呢 是把这个感知先统一 当时他就是这个感知的就是一个模型解决所有的感知问题 那同期其实Wemo是怎么干的 感知里边就可能有几十个模型 真的是几十个模型 这个detection可能是有一两个 detection完了之后呢 要做这个tracking tracking里边有一些小的classifier 然后去做一些类别的判断 tracking完了之后形成了track 然后再去判断做classification 每一类classification 可能pedestrian什么这个 这个vehicle都有个自己的classifier 然后这些弄完了之后 再在thin这个level thin understanding 再做一些这个什么分类器 所以你说看整个的感知 就有几十个模型 然后再是这个规划 规划里面当时还是 …”
View more
Ridealong summary
Chinese robotics companies have a unique edge over their American counterparts due to their superior data acquisition capabilities. While U.S. firms struggle to obtain quality data, Chinese startups can swiftly gather and utilize real-world data, essential for developing advanced robotic models. This systemic advantage allows them to innovate faster and more effectively in the robotics field.
“… The interesting thing is actually you would think A.I. is the main thing. And I guess there's crossover here. But the really big thing this year is robotics. Right. Everyone's got robots doing something. And obviously there is the A.I. like sort of angle there. But it's it's not the same in terms of like how they hype it up. Like I remember a few years ago, every company wanted to be a metaverse company or a blockchain company. And I said this last year on the show that that seems to be dead. And it seems like that's the case. It's just that Trump coming back in crypto, coming back in terms of …”
“… that. Which also I don't think the rest of CES has got that message based on all the A.I. everything everywhere. Matt, you've been you went to CES and bailed yesterday. Yes. Do you see anything interesting? Anything that. Well, I mean, everything. The interesting thing is actually you would think A.I. is the main thing. And I guess there's crossover here. But the really big thing this year is robotics. Right. Everyone's got robots doing something. And obviously there is the A.I. like sort of angle there. But it's it's not the same in terms of like how they hype it up. Like I remember a few years ago, every company wanted to be a metaverse company or a blockchain company. And I said this last year on the show that that seems to be dead. And it seems like that's the case. It's just that Trump coming back in crypto, coming back in terms of these guys making all their money through insider training on crypto does not seem to have translated over back to the tech world. There is no. Do you see any crypto stuff? No, I've not seen any. Nope. Not even blockchain is usually the way these tech companies try to like get their hold on that space. And I've seen nothing. None of seen any prediction …”
View more
Ridealong summary
Wearable technology is making a strong comeback at CES 2024, with innovative devices that record conversations and even a controversial wearable targeting intimate areas. This shift highlights a departure from last year's hype surrounding AI and crypto, as attendees noticed a lack of groundbreaking announcements. As the tech landscape evolves, the focus on robotics and wearables signals a new direction for the industry.
Top Podcasts About Neura Robotics
TBPN
6 episodes
张小珺Jùn｜商业访谈录
2 episodes
Better Offline
2 episodes
The Talk Show With John Gruber
1 episode
The Shawn Ryan Show
1 episode
The Neuron: AI Explained
1 episode
AI For Humans: Weekly AI News, Tools & Trends
1 episode
EV News Daily - Technology and Business of EVs
1 episode
Stories Mentioning Neura Robotics
Best Podcasts on Bezos's AI Manufacturing Fund
Jeff Bezos is reportedly considering launching a $100 billion investment fund focused on AI manufacturing. This move could significantly impact the AI industry by providing substantial capital to develop advanced manufacturing technologies. The fund aims to accelerate innovation and maintain competitive advantage in the rapidly evolving AI sector.
Jeff Bezos