A software fault tolerance experiment for space applications

The aim of the experiment described was to implement and assess fault-tolerant software within an industrial framework. Another significant aspect was to adapt the classical software engineering life cycle to this type of project. Two complementary techniques are considered: fault avoidance through the use of higher level language and strict development process; and fault tolerance by using techniques based on design diversity, such as N-version programming and recovery blocks, and exception handling. Starting from the specification of an existing spacecraft orbit and attitude control system, a 3-version software was developed, coded in Ada, and assessed in a fault-tolerant experimental testbed. The authors describe the experiment development and the main study results (on development efforts, observed diversity, and methodology aspects).<<ETX>>