Evrim Yazgin
Cosmos science journalist
Engineers are looking for better ways of dealing with equipment failures on autonomous spacecraft to make them safer.
Autonomous spacecraft, sometimes costing billions of dollars to design and produce, are a now staple of human attempts to explore outer space. These uncrewed vehicles have to traverse millions of kilometres. While they’re up there, there’s very little that can be done when things go wrong.
Equipment failures can be costly. Two main methods are used to try and deal with potential problems.
One is having a “safe mode”. This allows the spacecraft to operate while doing the least amount of damage to itself while engineers on the ground look at the data, diagnose the problem and work out solutions.
The other is equipping autonomous vehicles with redundant systems. For example, if a thruster malfunctions, it is turned off and a back-up thruster used.
But if dangerous faults happen with little warning, there may not be enough time for space-to-ground communications. Redundant systems can kick in here but add expense and weight to the already pricey craft.
Experiments conducted at the Jet Propulsion Laboratory (JPL) managed for NASA by the California Institute of Technology (Caltech) aim to give autonomous spacecraft the means to resolve problems themselves using new algorithms.
Spacecraft with these algorithms would be able to diagnose and safely respond to issues, such as encounters with other objects in space, in real time.
“Having redundant systems is not always practical,” says project supervisor Fred Hadaegh. “It means the spacecraft has to be bigger, heavier, and more expensive than it would be otherwise. So, the idea here is that when a spacecraft encounters a problem, it can figure out what’s not working and correct or adapt to that specific fault.”
The Caltech research is published in the journal Science Robotics.
Researchers tested the algorithm using Caltech’s multispacecraft dynamics simulator which uses air bearings to move across the floor with near zero friction.
“At rest, it seems to be floating, and if you push it in one direction, it will keep going until it hits something, which is what space dynamics are like,” says lead author James Ragan.
The simulator was fitted with the s-FEAST (Safe Fault Estimation via Active Sensing Tree Search) algorithm.
“Our s-FEAST algorithm rapidly ‘dreams’ about numerous possible futures that could result from actions it takes now,” Ragan explains.
“Because the system is noisy, these futures are uncertain. There are multiple possible outcomes, which leads to a tree of possible branching futures. Each branch represents one possible way the future might happen, based on things the spacecraft controls—the test actions it selects—and also things it doesn’t, such as observations coming from faulty sensors.”
Ragan explains that the s-FEAST-fitted spacecraft deals with unexpected data “similar to how you might carefully test your muscles when you feel an unexpected pain, and you want to figure out just what hurts and how to avoid actions that might further injure you.”
Simultaneously testing multiple possibilities, the algorithm then decides which course of action will most likely diagnose the problem and avoid danger.
“The key idea here is that s-FEAST isn’t replacing all spacecraft operations. It’s your emergency response,” Ragan says.
The researchers say the same principles could be used on Earth as well.
“Space systems make autonomous operations necessary since we cannot grab and fix spacecraft and Mars helicopters operating in a world far away from us,” says senior author Soon-Jo Chung. “Space is our ultimate ‘proving ground’ for any autonomy research we do for Earth-based vehicle systems.”
