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.
Related event: Human-Robot Catch Record Boosted Fivefold(2 posts)→
More from Embodied
- Hironobu Fujiyoshi publishes deck: from AI agents to Agentic Robotics — HirokatuKataoka · 2026-10-16
- CoDA co-evolves simulation and robot policies via shared failure memory, lifting OOD success from 5.3% to 27.6% — PLAN-Lab · 2026-10-16
- Beff Jezos claims rocket Cybertruck will be the first Tesla/SpaceX lunar vehicle — beffjezos · 2026-10-16
- Maglev 6D shuttles levitate under 6mm, hit 5-10µm precision, avoid collisions in firmware — lukas_m_ziegler · 2026-10-16
- Robotic-arm self-shopping cart concept imagines grabbing groceries off the shelf — djcows · 2026-10-16
- ELSFP pain points: >3dB insertion loss, costly PMF, harsh packaging requirements — jwt0625 · 2026-10-16