"The Gemini Robotics-ER 1.6 model announced on April 14 performs as a 'high-level reasoning model for a robot' that can plan and execute tasks, according to Google DeepMind."
"Such inspection duties require 'complex visual reasoning' to interpret the multiple needles, liquid levels, container boundaries and tick marks, along with text, in various instruments."
"The agentic vision capability reportedly helps to boost robotic performance on instrument reading tasks from 23 percent in the older Gemini Robotics-ER 1.5 model to 98 percent."
Boston Dynamics' Spot robot can now read analog thermometers and pressure gauges due to Google DeepMind's Gemini Robotics-ER 1.6 model. This model enhances robotic capabilities for embodied reasoning, allowing robots to plan and execute tasks. It enables accurate reading of complex gauges and visual inspections through sight glasses. The model features 'agentic vision,' which combines visual reasoning with code execution, significantly improving performance on instrument reading tasks from 23% to 98%. Boston Dynamics is testing these robots in various industrial settings, including automotive factories owned by Hyundai Motor Group.
Read at Ars Technica
Unable to calculate read time
Collection
[
|
...
]