Introducing Autonomy-1: The First Autonomous Space Mission, Powered by Solo

Over the last four years, AstroForge has been working toward a singular mission: to unlock the resources of the Solar System. 

We have systematically knocked out one challenge after another. We’ve taken advantage of excess launch capacity on missions to the Moon to lower the cost of reaching deep space. We’ve built small spacecraft capable of traveling millions of miles from Earth. We’ve developed guidance and navigation algorithms to operate in a regime that has historically been the exclusive domain of governments. 

We’ve solved nearly every constraint except one: dependence on Earth. 

Spacecraft today still rely heavily on teams of people to analyze telemetry, make decisions, and send commands. When spacecraft encounter anomalies, humans diagnose the problem and determine what to do next. For deep space operations, these teams depend on scarce and expensive terrestrial dishes. The farther a spacecraft travels from Earth, the longer those operators must wait for data packets, and the more limited information they have to work with. 

At AstroForge, this model makes up a significant portion of our overall mission costs – nearly one-third – and just as critically, it does not scale. 

We plan to operate fleets of spacecraft throughout the Solar System. We need those spacecraft to be able to respond to problems and continue their mission. And if every spacecraft we launch requires a corresponding mission control team on Earth, as well as continuous access to high-demand ground infrastructure, we have a big problem.

Now, we have found a solution. It meant going after the holy grail of spacecraft engineering: full mission autonomy.

We have developed Solo, a spacecraft intelligence model designed to autonomously coordinate a spacecraft’s onboard functions. Solo works on top of AstroForge’s existing deterministic, physics-based flight software, allowing the spacecraft to make decisions in real time during flight.

Our next mission, DeepSpace-2, will fly Solo in shadow mode. That means Solo will run onboard and process real spacecraft data, but its decisions will not be executed by the vehicle. 

Autonomy-1 will be the first time Solo takes the reins.

Launching aboard the first flight of Stoke Space’s Nova Pathfinder launch vehicle, Autonomy-1 will be the first space mission to complete its entire mission after separation without a single command from the ground. Using Solo, we will remove the human operator from the loop.

Building Solo

Spacecraft autonomy itself is not new. Nearly three decades ago, NASA’s Deep Space 1 demonstrated an onboard AI system called “Remote Agent,” that was capable of planning and executing high-level mission goals. More recently, OSIRIS-REx completed the final descent, touchdown, and material sample completely autonomously.

Our spacecraft already have significant autonomy. DeepSpace-2, for example, will fly with verified, deterministic physics models that will allow the spacecraft to fly unguided by humans for up to a week at a time. But in each of these cases, autonomy has been limited to very specific functions or mission phases while human operators remain responsible for the mission itself. And if there is an anomaly, ground teams intervene. 

Solo takes humans out of the equation. 

Solo is an intelligence layer that sits above the spacecraft’s existing systems. It ingests information about the spacecraft and its current state, identifies if something is off-nominal, then determines what should happen next. Importantly, Solo does not replace the physics-based software and deterministic algorithms underneath it. It uses this information to fly the spacecraft without ground updates, and also to determine if any subsystem is in an off-nominal state. Because Solo has access to much more data than any ground operator would, it will be able to make more informed decisions.

Solo will also be able to ingest and process far more information about the spacecraft than we could ever send back to Earth. The extreme distances and cost of deep space communications severely constrain how much data can be downlinked, leaving human operators with a limited picture of what is happening onboard. In contrast, Solo will be able to access that information at the source, and take action based on a much fuller picture of the spacecraft’s state. 

One of the reasons why AstroForge is uniquely positioned to build Solo is the team and testing infrastructure we’ve assembled over the last four years. Our team includes mathematicians and physicists who have spent years working on some of the hardest problems related to autonomous navigation and spacecraft operation in deep space. 

We’ve also built a world-class testing operation around extensive in-house infrastructure, including full-scale thermal testing of the spacecraft, radio testing in a large anechoic chamber, thruster hot-fire, and hardware-in-the-loop testing. This allows us to speed up our testing intervals and generate enormous amounts of data about how our spacecraft behaves, which we can use to continually improve Solo.

Proving it in space: Autonomy-1

Autonomy-1 will be the first full-scale flight demonstration of Solo.

The mission objective is deliberately straightforward: after Autonomy-1 separates from its launch vehicle, we do not intend to send the spacecraft a single command.

Autonomy-1 will transmit telemetry and science data back to Earth so that we can observe what the spacecraft is doing, understand the decisions Solo makes, and collect science. But that information will only flow one way – from the spacecraft to the ground. 

The spacecraft will also carry COMPASS, a NASA Goddard heliophysics payload. That means in addition to operating the spacecraft fully autonomously; it will also be responsible for a real scientific payload and coordinate the functions required to support that payload’s mission. 

We started building Solo because asteroid mining requires autonomy, but many of the constraints spacecraft operators face are not unique to asteroid mining. 

Every single spacecraft in deep space faces some version of the same problem: constrained communications, expensive ground stations, and the need for specialized teams. This traditional operating model becomes increasingly difficult to scale as the number of spacecraft grows.

As humanity moves farther from Earth – and as the number of spacecraft operating there grows by orders of magnitude – intelligence will have to move with them.

We intend for Solo to be that intelligence.