Breakthrough in Human-Robot Juggling: Robot Catches Record Multiplied Fivefold

Jan_R_Peters · x · 2026-08-08

Researchers from TU Darmstadt and other institutions published a new study on human-robot partner juggling, accepted by IROS 2026.

Challenge: Dynamic object exchange is difficult due to perception, timing, and contact-rich interaction uncertainties, requiring precise real-time coordination.
Method: A real-time planning and control architecture integrating predictive tracking, adaptive online trajectory optimization (multiple-shooting), and state-machine logic.
Results: In a user study with 8 participants, the system achieved synchronized three-ball cascades. All beat previous records within 10 minutes; one extended the record 5x to 20 catches, another achieved 40 consecutive catches with a 100% success rate.

More from Embodied