Singularities are a real headache for robotic arms – Jacobi Robotics tries to solve them


It’s easy to lose sight that robotics is as much a software problem as it is a hardware problem. Programming is understandably overshadowed by the allure of mechatronics, but without the right software solution you have little more on your hands than an expensive paperweight. The path to widespread adoption of robotics is fraught with unexpected pitfalls that may ultimately hinder its real-world use. The problems encountered when looking for software solutions are numerous.

Jacobi Robotics was founded in 2022 with a specific problem in mind: singularities. Confusingly, the word means something completely different for robotics than it does in Ray Kurzweil’s world of advanced AI projection.

In the land of robots, the concept is much more subtle, while requiring real knowledge of the category to fully understand it. It’s the kind of term you rarely encounter outside of research papers. However, this is a very real problem with real-world implications.

“Singularities are the Achilles heel of industrial robots,” notes Jacobi. “In repetitive tasks, where the robot follows the same movements repeatedly and blindly, robots can be programmed to avoid singularities through weeks of tedious manual adjustment of robot trajectories. But for many robotic applications, the robot’s trajectories must be changed periodically due to small changes in materials or thermal expansion.

If you’re familiar with robotic hardware, you’ve probably heard the term “degrees of freedom” referring to, for example, a robotic arm that has six or seven degrees of freedom. These are the joints of the system and the axes along which these joints are able to move. Singularities are points in space where the robot cannot move. When this happens, a human usually has to step in to get things back up and running.

Jacobi Robotics takes its name from the Jacobian matrix, which, in turn, refers to the pioneering 19th century German mathematician Carl Jacobi. In the world of robotics, the concept refers to the relationship between joint and end effector velocities. To further simplify something I’ve already oversimplified, the concept and the company that bears its name are concerned with planning the robot’s trajectory.

Jacobi Robotics was founded by a quartet of UC Berkeley robotics students, along with Professor Ken Goldberg. In addition to being the company’s chief scientist, Goldberg is also a co-founder of package sorting robotics company Ambi Robotics, so he’s been to this rodeo before.

For starters, the team is focusing almost exclusively on issues related to singularities, which can stop a robot dead in its tracks at unpredictable times. In the world of robotic arms, this poses a big problem for key applications, like package sorting, palletizing – more or less the key things we talk about when we talk about industrial robots.

Jacobi participated in pilot projects with selected partners. That list includes automation deployment company Formic, as well as a larger consumer electronics company that the company isn’t yet ready to name (you know how this stuff goes in the world of automation). ‘business). According to Formic, Jacobi’s approach to attacking singularities has significantly reduced deployment times, even at this early stage. It’s certainly in the best interest of a startup like Formic to resolve as many potential issues during the deployment process, rather than having to send in technicians after the fact.

Alongside Goldberg, the company’s founders include CEO Max Cao, CPO Yahav Avigal, chief architect Lars Berscheid, and chief roboticist Jeff Ichnowski (who is also an assistant professor at CMU’s Robotics Institute ). Jacobi closed a $1 million pre-seed in early 2023 and is currently focused on growing a suitable seed as it seeks to commercialize its solution. Current investors include Swift Ventures and Berkeley SkyDeck, the UC Berkely accelerator, which included the startup as part of the recent demo day.

The software currently supports a number of the largest robotic weapon suppliers, including ABB, Fanu, Universal and Yaskawa.


Leave a Comment

Your email address will not be published. Required fields are marked *