Autonomous rovers for moon exploration

When it comes to studying the surface of moons and planets, robot explorers called “rovers” are the gold standard. They can travel into space far more easily than a human astronaut, traverse new terrains quickly, and collect mountains of useful data.

In the past, most rovers were operated by humans. University of Adelaide researcher Professor Tat-Jun Chin from the Australian Institute of Machine Learning (AIML) says this approach is full of challenges.

“Rovers that land on the moon can’t be controlled in real-time since the speed at which the signal travels from Earth is too slow for real-time communication. There is a lag of about 2.5 seconds in the visuals we see from the rovers, which can easily lead to accidents,” he says.

The solution to this problem is to create autonomous rovers that can “think” for themselves and plan their own routes based on how they perceive their environment.

A team of students from the University’s Faculty of Engineering, Computer and Mathematical Sciences have developed code that could be used by NASA’s Artemis human spaceflight program, which aims to send people to the Moon by 2024, to make their rovers more autonomous.

They completed this work as part of the NASA Space Robotics Challenge, a virtual competition which aims to advance robotic software and autonomous capabilities for space exploration missions.

“We started out with a simulated moon environment,” Professor Chin says. “Then, the students designed algorithms that told the robots how to move around on that surface and complete a range of different tasks.”

“The simulated environment replicated the Southern Pole of the moon – where NASA is exploring for resources. It’s a particularly challenging area to work in due to its specific shadows and lighting.”

The University of Adelaide team was the only Australian group to participate in the Challenge, and were awarded third place for their efforts.

What’s next?

While the work conducted by the University of Adelaide team has made great strides towards the development of better autonomous rovers, Associate Professor John Culton, Director of the Andy Thomas Centre for Space Resources, says there are many other potential applications as well.

“While NASA hopes to use the cutting-edge capabilities of this code on the Moon and Mars, the code could also be used on Earth for autonomous mining operations, disaster response and recovery, robotic agriculture, construction, and other applications,” he says.