Latest News

A research robot has to support experiments its designers haven’t thought of yet. Matt Trossen explains why we build our hardware to be changed.

A university research lab is using the Trossen Solo AI kit to teach a robot arm to pick up any manufacturing part, in any orientation, and place it in the right bin from a simple prompt. Ali Beydoun, a researcher focused on physical AI, documented the full journey in a detailed post: Bringing a Robot Arm to Life with Trossen Robotics AI. He covers how he chose an arm, set it up, collected training data and fine-tuned a vision-language-action model. He also notes that his post

Collecting handheld demonstrations is only half the job. The other half is robotics data annotation: turning hours of raw episodes into multimodal training data a team can actually search, review, and train on. Our partners at DecisionFacts just showed what that second half can look like. They built a pipeline that takes episodes captured on TRumi, Trossen Robotics' handheld data collection device, and turns them into annotated, synchronized files that open directly in Foxglo

Two Trossen arms struck a match completely on their own. The demo comes from NAC, research by Ahad Jawaid and Yu Xiang at UT Dallas heading to CoRL 2026, which borrows audio compression tricks to help robots learn precise, coordinated tasks.

Learn what Robot Framework is, how it works, and why teams use it for test automation. Get practical tips to start using robot framework with confidence.

Get started with Robot Framework. Learn how this automation tool works, its key features, and practical tips for writing effective test cases.

Repetitive, dexterous work powers millions of businesses, but much of it has stayed manual because traditional automation was too rigid, expensive, or difficult to deploy. Physical AI is starting to change the equation.

The Trossen Docs MCP Server connects MCP-compatible AI coding assistants to official Trossen Robotics documentation, API references, and demo scripts.

Meet the Trossen SDK, an open-source C++ framework for robotics and physical AI data collection. Record synchronized multimodal data, convert to LeRobot V2, and help shape the roadmap.

Constraint is becoming the defining force in AI and robotics. Compute, energy, supply chains, and talent are tightening, and the era of “just scale it” is colliding with reality. This essay argues we have to shift from gluttony to ROI: build production-grade stacks, optimize across training and inference, and deploy modular, measurable systems that industry can trust. If we do that, AI becomes infrastructure, not theater.

How to stretch your runway, accelerate milestones, and avoid the hidden costs of the wrong hardware partner.

I wanted to make a post to try and help future engineers land their dream job.

Researchers at the Max Planck Institute for Intelligent Systems and ETH Zurich have developed an electrohydraulic musculoskeletal leg

Fireside chat with Remi Cadene, from Hugging Face, and Shantanu Parab, from Trossen Robotics.

We are thrilled to introduce Gravity Compensation for Aloha. With this feature, you can now maintain arm position after releasing your grip.

We are thrilled to announce the launch of the Trossen Robotics Machine Learning Community—a one-stop destination for all things related to r

We are thrilled to announce full support for LeRobot with our Aloha Robotic Machine Learning Kits, now available on Hugging Face!

A list of the most basic tools a mechanical engineer should have on their desk or within arms reach.