Losing touch with a space ship at landing can cause serious issues that can even result in losing the spacecraft. Hardware components are more likely to deteriorate while in space, probably because they are more exposed to cosmic radiation than inside Earth's atmosphere.
The situation is increasingly complicated, as hardware engineers don't usually travel with spare components for the computers installed aboard, in order to keep the load to a minimum. That is why a group of scientists at the University of Arizona, led by researcher Ali Akoglu, are working now on a new hybrid hardware/software system that is alleged to allow computers to heal themselves.
According to Akoglu, the group is using Field Programmable Gate Arrays (FPGA) technologies, blending software and hardware in an extremely flexible infrastructure, able to be reconfigured at the chip level. In short, the software will be trained to mimic the behavior of a certain piece of hardware.
The scientist claims that general purpose systems are able to run a wide range of software applications, but they're still slower than a hardwired system. On the other hand, hardwired systems are tied to a single purpose, such as a computer running a single type of operating system, and no other hardware applications.
"In that case, you have an extremely fast system, but it's not adaptable. When new, and better software comes along, you have to go back into the design cycle and start building hardware from scratch", Akoglu explained. "What we need is something in the middle that is the best of both worlds, and that's what I'm trying to come up with using Field Programmable Arrays", he continued.
The project was first started in 2006, and has now reached the second development phase. The researchers are now working on the SCARS (Scalable Self-Configurable Architecture for Reusable Space Systems) technology. The group is also testing five hardware units linked altogether via a wireless setup, allegedly representing a combination of five landers and rovers on Mars.
"When we create a test malfunction, we try to recover in two ways", he explained. "First, the unit tries to heal itself at the node level by reprogramming the problem circuits.", he added.
If the unit's hardware resources cannot take over the functionality of the affected circuitry, then an SOS message is broadcast at network level and all the affected tasks are routed to the nearest unit available. "The second unit reconfigures itself so it can carry out both its own tasks and the critical tasks from the broken unit", Akoglu explained.
|
No user comments yet.
Be the first to express your opinion using the form below!
