WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe • Jul 9, 2026 • Session details

How I built my own intelligent Robot Arm from Scratch

Iulia Feroli

Building an intelligent robot arm from scratch no longer requires a robotics PhD. Ditch text-based hype and merge affordable microcontrollers with open-source AI for real-world physical automation.

Pause
Mute Enter Fullscreen
#1 about 3 min

Moving from AI software buzzwords to building actual robots

Transitioning from purely software-based language models to accessible physics projects provides a refreshing approach to artificial intelligence.

#2 about 3 min

Defining physical AI and multimodal robotics generation capabilities

Deploying multimodal AI models on physical bodies replaces complex inverse kinematics for simpler movement generation.

#3 about 3 min

Breaking down the core components of a robot arm

Identifying the necessary entry-level microcontroller brains and servo motors helps lower the barrier to robotics.

#4 about 3 min

Constructing the robot body from cardboard to 3D printing

Progressing from cheap household materials to 3D-printed joints creates a stable foundation for the robotic actuator.

#5 about 3 min

Writing microcontroller code and demoing the basic robot arm

Writing basic Python sequences on hardware-specific IDEs translates digital commands into physical object manipulation.

#6 about 3 min

Exploring the open-source Hugging Face LeRobot teleoperation project

Adopting a dual-controller setup with open-source parts enables leader-follower teleoperation for sophisticated remote tasks.

#7 about 2 min

Training robots autonomously through imitation learning data sets

Recording manual teleoperation movements to build visual datasets trains intelligent models for completely autonomous robotic manipulation.

#8 about 3 min

Navigating hardware failure and evolving physical AI model trends

Addressing the risks of circuit failure and shifting model paradigms emphasizes the chaotic but educational nature of hardware learning.

#9 about 3 min

Overcoming software challenges and future computer vision project integrations

Planning integrations with local language models and computer vision helps bypass frustrating software dependencies in traditional operating systems.

#10 about 2 min

Audience questions on teleoperation scaling and hardware building timeframes

Leveraging available robotics SDKs permits controlling larger industrial hardware and accelerates the entry ramp for eager developers.

Matching moments

2:22 min

Introduction to physical AI and the physical world

Moe Sani Moe Sani · World Congress 2026 Europe

2:44 min

Embodying artificial intelligence within physical robotic hardware platforms

Zaid Zaim Zaid Zaim +1 · World Congress 2026 Europe

1:20 min

Shifting focus from large language models to physical AI

Sergio Perez Sergio Perez · World Congress 2026 Europe

3:46 min

Transitioning from rigid machines to autonomous AI robots

Teresa Conceicao · World Congress 2022

1:37 min

Transitioning from digital AI agents to physical AI

Alexander Schwarz Alexander Schwarz · World Congress 2025

7:01 min

Executing AI in the loop on robotic test hardware

Falk Langer Falk Langer +1 · World Congress 2023

More from World Congress 2026 Europe

Building the Nervous System of AI - Michael Kagan (NVIDIA) thumbnail
29:17
3 months ago

Building the Nervous System of AI - Michael Kagan (NVIDIA)

Michael Kagan, Sead Ahmetović

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote thumbnail
19:41
3 months ago

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote

Christian Heilmann

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend thumbnail
32:06
3 months ago

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

David vonThenen

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes thumbnail
35:13
3 months ago

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes

Irina Branovic

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬 thumbnail
24:23
3 months ago

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬

Jeremy Murray

Angstfreude - AI and Corporate Culture - The Thrill and the Threat thumbnail
30:26
3 months ago

Angstfreude - AI and Corporate Culture - The Thrill and the Threat

Axel Ebert, Karin Krobath

Related videos

Robots Among us: Advances in AI for Everyday Androids thumbnail
29:51
World Congress 2026 Europe • 3 months ago

Robots Among us: Advances in AI for Everyday Androids

Florian Gather, Thomas Endres

Robots 2.0: When artificial intelligence meets steel thumbnail
28:19
World Congress 2025 • about 1 year ago

Robots 2.0: When artificial intelligence meets steel

Thomas Tomow

How Robots Learn to be Robots thumbnail
24:48
World Congress 2025 • about 1 year ago

How Robots Learn to be Robots

Alexander Schwarz

From Perception to Autonomy: Building Agentic Edge AI Robots with ROS 2 thumbnail
25:50
World Congress 2026 Europe • 3 months ago

From Perception to Autonomy: Building Agentic Edge AI Robots with ROS 2

Moe Sani

Physical AI: The Era of Intelligent Machines thumbnail
30:12
World Congress 2026 Europe • 3 months ago

Physical AI: The Era of Intelligent Machines

Clemens Wasner, Dr. Ramin Hasani, Vinesh Sukumar, Zohar Fox

Physical AI for the Next Wave of Industrial Digitalisation thumbnail
29:11
World Congress 2026 Europe • 3 months ago

Physical AI for the Next Wave of Industrial Digitalisation

Sergio Perez

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.