Wevolver and Syntiant are creating a series that explore the work of innovators and the future of pervasive AI. Syntiant is developing ultra-low-power AI processors. Because they believe in the importance of innovation, Syntiant is engaging in these fireside chats with engineers and designers who are on the cutting edge of their field.
The fifth conversation in our Voice Of Innovation series was held between Syntiant CEO Kurt Busch and Rod Mamin, COO of Spacebit. Spacebit is developing the world’s first walking robot that will travel to the moon to explore its surface. In this fascinating conversation, Kurt and Rod discuss the challenges of developing tech for space and outline their visions for more accessible Artificial Intelligence.
Democratizing space research
Space exploration is no longer the domain of large, national institutions. Over the last decade, there has been an explosion of space-related startups making incredible leaps in innovation. Spacebit is no exception. The UK-based company is developing space robotic technology and space data analytics tools for space exploration, including advanced micro-robotics and Artificial Intelligence (AI). Their engineering approach is to deliver lower-cost technology, useful for the exploration of celestial bodies.
Smaller, lighter robots for agile missions
“Right now, most of the robots are quite heavy, and they're super expensive," begins Rod. “The trend for smaller devices is only continuing, and so it makes sense that the same things that happened with computers and smartphones will happen with robotics.” Spacebit's first rover, dubbed 'Asagumo 2.0', is a four-legged walking rover set to fly to the Moon with the NASA Commercial Lunar Payload Services (CLPS) program in 2021 and 2022. Asagumo 2.0 is a semi-autonomous micro rover built on a single-unit CubeSat frame, usually used for microsatellites. The rover weighs just 1.3 kilograms, is solar-powered, and is equipped with four spider-like legs instead of wheels or tracks.
Challenges of rapid robotic innovation
Creating robots on earth has many challenges; these only multiply when you think about putting those same robots first on a journey through space and then on the surface of a planet. “One of the biggest challenges we have is temperature,” explains Rod. “During the flight, there is a huge chance that our robots could freeze because they will be travel through ultra space which has a temperature of around 2.4 Kelvin, and on the moon, our robots would face another issue as temperatures can rise up to to 120 degrees Celsius.”
Semi-autonomous exploration missions
“We pursued a semi-autonomous robot instead of something fully autonomous as our mission is quite critical, and we want to have full control over the robot," explains Rod describing why they didn't push for full autonomy right away. "We’re really worried that fully autonomous robots could do something wrong because terrain conditions on the moon are quite different from the ones we have on earth, and assumptions can go wrong. The mission is quite complicated and really important in the scheme of space exploration history, so we want to have almost complete control over the robot's motion. However, at the same time, the robot needs to make some decisions on its own. For example, if the robot has lost signal, it has to find the way back where it had the signal before.”
A challenge for Spacebit and others in this area is the ability to get enough compute power into small devices. This challenge resonates with Kurt who explained the origin of Syntiant. “When we, started Syntiant, we had this idea of moving machine learning from something that's in the cloud to in the small device, says Kurt. "And eventually, we got to the point of adding the most amount of neural compute into battery-operated devices. So, we often fight with compute issues as well around size, thermal, and power - though we are not operating in any two-degree Kelvin situations, as far as I'm aware of! But the idea of putting as much compute into is as small as possible footprint is in line with much of the things that you're trying to do with your robots.”
The future of space exploration in the hands of all engineers
We really believe that humanity has to go to space because Space has unlimited resources, and having access to space resources could allow us to live sustainably on Earth.
- Rod Mamim
Working on space-related challenges has never been more possible for engineers. "With all of the modern technologies that we have right now, it's possible for almost any engineer who has enough experience to join a space exploration company or to start your own," says Rod. "It's possible to take existing technologies and combine them together and make something valuable and tangible."
The Spacebit Engineering Challenge enables engineers worldwide to contribute to the development of “Asagumo 2.0”. As Spacebit continues its journey developing tiny robots they are calling on engineers in the Wevovler community to contribute knowledge and feedback. The engineering inputs will be assessed and the most valuable contributors will be rewarded by having their name engraved on the Asagumo rover before it launches on its maiden journey to the Moon. Additionally, the winning engineer will be invited to the control room in the UK or US; or, participate in Spacebit's remote Robotic Operations & Control Center (ROCC).
Read more about The Spacebit Engineering Challenge here.
This video is part of a series of fireside chats in which Wevolver and Syntiant partner to engage with global innovators. In previous discussions, we spoke with the Division President of Power & Sensor Systems at Infineon, Andreas Urschitz, Arduino CEO Fabio Violante, Star Wars Animatronic Designer Gustav Hoegen and Fashiontech Designer Anouk Wipprecht. I encourage you to stay tuned and to follow Syntiant's profile for more of these conversations.