Google has introduced two innovative robotics models, Gemini Robotics 1.5 and ER 1.5, designed to enhance robotic capabilities in complex environments. These models integrate advanced reasoning with motor execution, enabling robots to efficiently tackle multi-step tasks. Gemini Robotics 1.5 processes visual data and instructions, allowing robots to think, act, and explain their reasoning before executing actions. In contrast, Gemini Robotics-ER 1.5 functions as a high-level planner that utilizes tools like Google Search to support decision-making. Together, they create an ‘agentic’ framework, enhancing generalisation across diverse settings and facilitating the completion of semantically complex tasks. Gemini Robotics-ER 1.5 is now available to developers via the Gemini API in Google AI Studio, while Robotics 1.5 is accessible to select partners. These advancements significantly bolster robots’ reasoning abilities, spatial awareness, and multitasking skills, marking a significant step in the evolution of robotics and AI technologies.
Source link
Share
Read more