LATIDIA · Investigación

Inferencia descargada para robótica de IA física del mundo real

Los robots son cada vez más inteligentes, pero ¿cómo puede su hardware adaptarse a ese crecimiento? Los nuevos hallazgos de Microsoft Research muestran que trasladar la inferencia de IA más allá del robot puede mejorar el éxito de las tareas, aumentar la eficiencia y respaldar un mayor avance

La noticia

At a glance Challenges a core assumption in robotics AI: Our research shows that running physical AI inference exclusively on onboard GPUs can limit robot performance, battery life, and scalability, and that offloading inference to edge or cloud GPUs can offer significant advantages. Demonstrates measurable benefits of inference offloading: Across representative mobile manipulation workloads, offloading improved task success rates, enabled larger AI models, and helped robots respond more effectively in dynamic, real-world environments. Extends robot operating time: Replacing power-hungry onboard AI compute with lightweight onboard hardware and remote inference can substantially improve battery life, enabling robots to operate longer between charges. Introduces a new capability in the Physical AI Toolchain: