<\/p>\n
| Item<\/th>\n | Value<\/th>\n<\/tr>\n<\/thead>\n |
|---|---|
| Publisher<\/td>\n | Microsoft Research<\/td>\n<\/tr>\n |
| Published<\/td>\n | 2026-09-24<\/td>\n<\/tr>\n |
| Source type<\/td>\n | Primary source (the publisher itself)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n Values determined by this site’s code at collection time. Dates are JST.<\/em><\/p>\n <\/p>\n Microsoft Research proposes a method to improve robot performance, battery life, and scalability by offloading physical AI robot inference from onboard GPUs to edge or cloud GPUs, rather than relying solely on the robot’s onboard GPU. Investigations using mobile manipulation workloads demonstrated that offloading inference contributes to improved task success rates, the use of larger AI models, and reduced battery consumption.<\/p>\n According to measurements presented by the authors, offloading physical AI inference to GPUs external to the robot offers significant advantages in task performance, battery life, and cost.<\/p>\n It was shown that when the robot’s onboard GPU lacks sufficient memory or performance, task execution capabilities drop significantly. The authors’ evaluation reported the following results:<\/p>\n Additionally, data in Figure 4 shows that offloading inference improves success rates in handover tasks where robot arms pass objects to each other.<\/p>\n Power consumption by the onboard GPU directly affects robot operating time. In the authors’ comparative experiments, the onboard GPU was replaced with a Raspberry Pi-5, and a configuration was adopted where all data was sent to an offloaded GPU. As a result, the following impact was confirmed:<\/p>\n Based on these results, it is concluded that offloading inference is extremely important to operate large models and achieve long battery-powered runtimes.<\/p>\n In this research and the verification of the proposed method, the following conditions were indicated:<\/p>\n Developers may be able to build an inference offloading environment by using the “Physical AI Toolchain” released by Microsoft. The documentation describes the following contents:<\/p>\n This documentation does not clarify the following details:<\/p>\n |