Space: GPU-based robots target Mars exploration
It’s second nature for us to follow an airplane across the sky, or to walk around a rock we see in our path. It’s not so easy for robots – you just have to watch $16,000 robots play football to realise how hard it is for them to kick a rolling ball. In contrast, our brains handle streams of visual information seamlessly, picking out obstacles and navigating us around them.
So how do we make robot brains more like ours? One way might be to change the type of processor they use. Until now, robots have always been fitted with central processing units (CPUs), just like most PCs. Such units are very good at crunching small streams of data fast, but they can only do one thing at a time.
In contrast, graphics processing units (GPUs), which are heavily used in supercomputers and gaming, can handle larger data sets more quickly, and deal with several of them at once. This is how the human brain works, and even though we process some tasks millions of times more slowly than does a computer, the amount of information our brains can handle is vast. But until quite recently, GPUs have been too big and expensive to use in robots.
Now a neuroscience and robotics start-up called Neurala in Cambridge, Massachusetts, has built robot brains using GPUs. It says they run roughly 10 times as fast as those built on CPUs.
I watched a software simulation at the Neuromorphics Lab at Boston University. A virtual rover is given a basic route across the surface of a digital Mars and it sets off without hesitation, spotting the rocks in its way as it goes.
The robot’s brain processes visual information in real time, enabling it to do more than simply navigate from one spot to another. This means robots could one day be trusted to make their own decisions when navigating changing terrain on Mars.
Mark Motter of NASA’s Langley Research Center in Hampton, Virginia, says Neurala’s approach highlights the difference between automation – in which a detailed, prescribed plan is executed by a machine – and autonomy, where a machine is free to make its own decisions on how to reach its goal. Neurala aims to mimic how human brains recognise objects, accumulate experience and make judgements, Motter says. “This is an interesting approach to autonomy.”
Neurala’s robot vision system also mimics a trick the human eye uses, called foveation. The fovea is a region of the retina that is thickly populated with visual receptors, and gives you very clear central vision. In a similar way, the robot’s vision system focuses on specific points of the scene to build up a picture of its environment instead of trying to process everything it sees through the camera all at once. This still results in a large amount of data but reduces the overall load on the robot’s brain.
That ability to process visual information in real time means Neurala’s brain can do more than just guide a robot from one spot to another. On its way, it could be carrying out basic science, classifying the rocks it sees and flagging unusual ones for further investigation, for example, or searching for signs of water and minerals.
There is a reason why the most advanced rover currently in existence, Curiosity, is rigidly controlled by NASA operators: space equipment in general is fiendishly expensive, so the agency has to be sure the chances of anything going wrong are tiny.
“If I’m going to send a rocket that costs billions of dollars, I want to be sure that every millimetre I travel is gonna be safe,” says Max Versace, Neurala’s CEO and head of Boston’s Neuromorphics Lab. But as commercial space flight heats up and costs go down, he thinks the future lies in swarms of low-cost robots (see “Termite robots build castles with no human help”). “We need similar machinery to the biological brain to do that,” Versace says.
Syndicated content: Hal Hodson, New ScientistTags: GPU, Neurala