An Optimization Method for Autonomous Robot Software Platform

More and more autonomous robots adapt multi-kernel based software platform. Multiple operating system's kernels run on the same hardware via virtualization to process the various tasks. The microkernel is suitable to be the cornerstone of the virtualization function because of its stability and security. However, the general boot process of the microkernel based hypervisor does not fit the automotive system, which needs quick startup. The reason is that guest operating systems require different features. The real-time OS needs a fast response, and others need plenty of resources, such as memory and devices. To make such a system boot quickly, we proposed Asymmetric Init, which uses different strategies to boot components quickly. After the development and experiment in the seL4 hypervisor, the system boot time is reduced to several seconds.