The meeting line activity setup. Credit score: 2026 LASA EPFL CC-BY-SA.
By Celia Luterbacher
In immediately’s manufacturing environments, upgrading a robotic fleet typically means ranging from scratch – not solely changing {hardware}, but additionally reprogramming duties. Even when two robots are constructed to carry out related jobs, totally different joint preparations or motion limits imply {that a} activity programmed for one robotic typically can’t be used on one other. Enabling expertise to switch instantly between robots may make these techniques extra sustainable and cost-efficient.
To satisfy this problem, researchers within the Studying Algorithms and Techniques Laboratory (LASA) in EPFL’s Faculty of Engineering have developed a brand new robotic management framework referred to as Kinematic Intelligence. The tactic takes a human-demonstrated activity, mathematically converts it right into a basic motion technique, after which adapts it in order that totally different robots can carry out it based mostly on their bodily design. The analysis has been printed in Science Robotics.
“This work addresses a long-standing problem in robotics: learn how to switch a discovered talent throughout robots with totally different mechanical buildings, whereas guaranteeing protected and predictable conduct,” says LASA head Aude Billard. “This strategy may considerably scale back the time and experience wanted to deploy robots in real-world settings.”
Kinematic Intelligence for transferable robotic studying
To construct their framework, the researchers first took human-demonstrated object‑manipulation duties – resembling putting, pushing and throwing – and recorded them utilizing motion-capture know-how. Then, they mathematically transformed these recorded duties into basic motion methods. In addition they developed a scientific classification of the bodily limits of various robotic designs, together with how far their joints can transfer and which positions they need to keep away from to stay steady. The framework then makes use of this classification to routinely tailor the overall motion methods to totally different robotic our bodies, making certain they will perform duties safely inside their mechanical limits.
In an meeting line experiment, a human demonstrated a activity by pushing a picket block off a conveyor belt onto a workbench, putting it on a desk, and at last throwing it right into a basket. By utilizing Kinematic Intelligence, three utterly totally different business robots have been in a position to reproduce this identical sequence safely and reliably.
“Every robotic dealt with totally different steps of the duty, and the system carried out efficiently even when the step allocation was modified,” explains LASA PhD scholar and co-first writer Sthithpragya Gupta. “Every robotic interprets the identical talent in its personal means, however all the time inside protected and possible limits.”
In the direction of scalable and future-ready robotics
The researchers purpose to increase the framework to settings resembling human-robot collaboration and pure language-based interplay. For instance, Kinematic Intelligence may permit an individual to instruct a robotic with easy instructions at dwelling, without having for technical programming. The strategy can also be related for rising robotic platforms, the place fast {hardware} evolution signifies that immediately’s machines might quickly get replaced by newer variations. Enabling seamless switch of expertise throughout such platforms may play a key function in making them sensible and scalable.
“Our objective is to take away the necessity for technical experience whereas nonetheless making certain protected and dependable operation,” summarizes LASA scientist and co-first writer Durgesh Haribhau Salunkhe. “The consumer brings the concept and the specified conduct, and the robotic ought to care for the remaining.”
Reference
Exhibit as soon as, execute on many: Kinematic intelligence for cross-robot talent switch, S Gupta, D H Salunkhe, A Billard, Science Robotics (2026).
EPFL
(École polytechnique fédérale de Lausanne) is a analysis institute and college in Lausanne, Switzerland, that focuses on pure sciences and engineering.
EPFL
(École polytechnique fédérale de Lausanne) is a analysis institute and college in Lausanne, Switzerland, that focuses on pure sciences and engineering.