vivo's PrismBot robotics team secured first place in the Reasoning to Action Track at the ICRA 2026 AGIBOT World Challenge in Vienna, demonstrating top performance in translating task understanding into action decisions in complex real-world environments. The team competed against 526 teams from 27 countries and regions. The competition combines online simulation evaluation with offline real-robot testing. To address complex long-horizon tasks, the vivo team developed a framework centered on keyframe optimization and contrastive learning. Keyframe loss weighting helps the model learn critical action points effectively, while contrastive learning reduces the semantic gap between text-based instructions and physical action execution. The team also secured a top-three placement in the Whole Body Control Track, validating the transferability of its technical approach. vivo has chosen the home as a starting point for robotics R&D because home environments demand long-horizon tasks, dual-arm collaboration, fine manipulation, reasoning, and decision-making.

ResearchJune 12, 2026•Embodied Global Team
vivo Robotics Team Wins ICRA 2026 AGIBOT World Challenge Reasoning to Action Track
vivo's PrismBot team won first place in the ICRA 2026 AGIBOT World Challenge Reasoning to Action Track, competing against 526 teams from 27 countries and validating its embodied intelligence approach.
#vivo#icra-2026#agibot#embodied-intelligence#robotics#competition
Reading in English
Language: English- Showing content in English
Trending Now
Industry
LG CNS and LX Pantos Partner to Build Next-Generation Unmanned Warehouse with Humanoid Robots
Jun 11, 2026 · 0 views

Research
X Square Robot Open-Sources XRZero-G0 Framework for Scalable Robot Learning
Jun 10, 2026 · 0 views
Research
Human Archive Raises $8.2M to Train Robots Using India's Gig Economy Workers
Jun 7, 2026 · 0 views
Industry
The Economist Highlights Ningbo as the Unlikely Heart of Global Humanoid Robot Component Supply Chain
Jun 7, 2026 · 0 views
More in Research
Research
GenHOI: Zero-Shot Humanoid-Object Interaction by Imitating Generated Videos
Jun 13, 2026
Research
MIT Ultrasound Wristband Tracks Every Finger Movement, Controls Robot Hand in Real Time
Jun 13, 2026
Research
Generalist AI Unveils GEN-0: Embodied Foundation Model That Scales with Physical Interaction
Jun 13, 2026