KTH Researchers Give Robots Context on Human Movement So They Can Stop Getting in the Way

Clever computer vision system provides context, allowing robots arms to dodge human colleagues rather than simply halt when blocked.

A pair of researchers at the KTH Royal Institute of Technology have come up with a new approach to help robots and humans collaborate safely and efficiently, by providing the robots with more context on what their human colleagues may be doing.

“Under the ISO standard and technical specification," first author Hongyi Liu explains of the paper's inspiration, referring to a standard from the International Organization for Standards (ISO) which introduces new requirements for collaborative robot safety, "when a human approaches a robot it slows down, and if he or she comes close enough it will stop. If the person moves away it resumes. That’s a pretty low level of context awareness. It jeopardizes efficiency. Production is slowed and humans cannot work closely to robots."

The solution: Giving robots better context on what humans are doing around them "In this paper, the authors present a context awareness-based collision-free human-robot collaboration system that can provide human safety and assembly efficiency at the same time," the researchers write. "The system can plan robotic paths that avoid colliding with human operators while still reach target positions in time. Human operators’ poses can also be recognised with low computational expenses to further improve assembly efficiency.

"To support the context-aware collision-free system, a complete collision sensing module with sensor calibration algorithms is proposed and implemented. An efficient transfer learning-based human pose recognition algorithm is also adapted and tested. Two experiments are designed to test the performance of the proposed human pose recognition algorithm and the overall system. The results indicate an efficiency improvement of the overall system."

In one of the tests, a human suddenly blocked the path of a robot arm in motion. Under a strict interpretation of the ISO safety standard, the robot would have immediately halted until the obstruction was cleared; using the new system, the robot was able to predict the trajectory of the hand and adjust its own movement to avoid it without stopping.

"This is safety not just from the technical point of view in avoiding collisions, but being able to recognize the context of the assembly line," Liu claims of the work. "This gives an additional layer of safety."

The paper has been published under closed-access terms in the journal Robotics and Computer-Integrated Manufacturing.

Gareth Halfacree
Freelance journalist, technical author, hacker, tinkerer, erstwhile sysadmin. For hire: freelance@halfacree.co.uk.
Latest articles
Sponsored articles
Related articles
Latest articles
Read more
Related articles