No abstract

In this paper we propose a hybrid solution to ensure results correctness when deploying several applications with different safety requirements on a single multi-core-based system. The proposed solution is based on lightweight hardware redundancy, implemented using smart watchdogs and voter logic, combined with software redundancy. Two techniques of software redundancy are used: the first one is software temporal triple modular redundancy, used for those tasks with low criticality and no real-time requirement. The second software redundancy technique is triple module redundancy for tasks with high criticality and real-time requirements, assisted by a hardware voter. A hypervisor is used to separate each task in the system in an independent resource partition, thus ensuring that no functional interference is occurring. The proposed solution has been evaluated through hardware and software fault injection on two hardware platforms, featuring a dual-core processor and a quad-core processor respectively. Results show a high fault tolerance achieved using the proposed architecture.

One of the main challenges in automatic target tracking applications is represented by the need to maintain a low computational footprint, especially when dealing with real-time scenarios and the limited resources of embedded environments. In this context, significant results can be obtained by using forward-looking infrared sensors capable of providing distinctive features for targets of interest. In fact, due to their nature, forward-looking infrared (FLIR) images lend themselves to being used with extremely small footprint techniques based on the extraction of target intensity profiles. This work proposes a method for increasing the computational efficiency of template-based target tracking algorithms. In particular, the speed of the algorithm is improved by using a dynamic threshold that narrows the number of computations, thus reducing both execution time and resources usage. The proposed approach has been tested on several datasets, and it has been compared to several target tracking techniques. Gathered results, both in terms of theoretical analysis and experimental data, showed that the proposed approach is able to achieve the same robustness of reference algorithms by reducing the number of operations needed and the processing time.

Commercial-off-the-shelf devices are often advocated as the only solution to the increasing performance requirements in space applications. This paper presents the solutions developed in the frame of the European Space Agency's HiRel program, concluded in December 2014, in which a number of techniques proposed in the past 10 years have been used to design a highly reliable system, which has been selected for forthcoming space missions. The paper presents the system architecture, describes performed evaluations and discusses the results.

No abstract