Everyone Can Build a Robot: Open Source Embodied AI With Seeed Studio | NVIDIA AI Podcast Ep. 300

What It Covers

Seeed Studio CEO Eric Pan and robotics head Elaine Wu explain how their open-source hardware company, operating since 2008, is democratizing physical AI through affordable robot arms starting at $200, Jetson-powered edge computing, and OpenClaw integration that lets users control robots via text commands.

Key Questions Answered

• •Affordable Entry Point: Seeed Studio's SO-ARM robot arm costs $200 and ships ready to train without programming knowledge. Users teach it tasks by physically guiding its movements several times, sending that motion data to cloud training, then deploying the resulting model back onto the device — reducing onboarding from months to days.
• •Imitation-Based Robot Training: Rather than coding spatial planning algorithms, users now train robot arms the way they train animals — physically demonstrating a task repeatedly, uploading the recorded data for cloud-based model training, then deploying via Jetson. This shifts robot programming from engineering expertise to domain expertise, letting chefs or craftspeople train their own robots.
• •OpenClaw + Jetson Local Deployment: Installing OpenClaw locally on a Jetson device enables natural language robot control — typing "move arm up" or "pick up object" executes physical commands without writing code. Running the Qwen 3.5 model locally means no API tokens or cloud costs, making autonomous robot operation viable for small businesses under $1,000.
• •Modular Robot Architecture Over Humanoids: Rather than building general-purpose humanoid robots, Seeed Studio produces interchangeable components — arms, chassis, hands, torsos, and wheeled bases — that developers combine for specific use cases. This approach lets startups and researchers build domain-specific robots faster, with Seeed providing manufacturing scale-up from prototype to 3,000 shipped units in five months.
• •Sim-to-Real Gap Closing via NVIDIA Isaac Sim: Developers can mirror Seeed robot models inside NVIDIA Isaac Sim to validate and tune robot behavior before physical deployment. As affordable hardware expands the user base, more people contribute real-world training data, accelerating the feedback loop between simulation accuracy and physical performance across diverse environments.