Carnegie Mellon University
Software and System Health Management for Autonomous Robotics Mis.pdf (223.07 kB)

Software and System Health Management for Autonomous Robotics Missions

Download (223.07 kB)
journal contribution
posted on 2012-09-04, 00:00 authored by Johann Schumann, Timmy Mbaya, Ole J Mengshoel
Advanced autonomous robotics space missions rely heavily on the flawless interaction of complex hardware, multiple sensors, and a mission-critical software system. This software system consists of an operating system, device drivers, controllers, and executives; recently highly complex AI-based autonomy software have also been introduced. Prior to launch, this software has to undergo rigorous verification and validation (V&V). Nevertheless, dormant software bugs, failing sensors, unexpected hardware-software interactions, and unanticipated environmental conditions—likely on a space exploration mission—can cause major software faults that can endanger the entire mission. Our Integrated Software Health Management (ISWHM) system continuously monitors the hardware sensors and the software in real-time. The ISWHM uses Bayesian networks, compiled to arithmetic circuits, to model software and hardware interactions. Advanced reasoning algorithms using arithmetic circuits not only enable the ISWHM to handle large, hierarchical models that are necessary in the realm of complex autonomous systems, but also enable efficient execution on small embedded processors. The latter capability is of extreme importance for small (mobile) autonomous units with limited computational power and low telemetry bandwidth. In this paper, we discuss the requirements of ISWHM. As our initial demonstration platform, we use a primitive Lego rover. A Lego Mindstorms microcontroller is used to implement a highly simplified autonomous rover driving system, running on the OSEK real-time operating system. We demonstrate that our ISWHM, running on this small embedded microcontroller, can perform fault detection as well as on-board reasoning for advanced diagnosis and root-cause detection in real time.




Usage metrics


    Ref. manager