Surprisingly Useful AI Article Enhancements
Melbourne-based motion intelligence company SpatioTemporal has been selected as one of seven finalists in Propel-AIR 2026, an AI and robotics sprint program delivered by the ARM Hub AI Adopt Centre.
The company is now competing for the opportunity to work alongside MassRobotics in Boston, a robotics innovation hub, with its motion intelligence software designed for robots and autonomous vehicles operating in shared spaces with people.
Reading Human Intent
SpatioTemporal’s core technology addresses a gap in current autonomy systems. While existing perception systems can detect objects, they struggle to interpret human intent – the kind of social judgement calls that arise constantly when machines operate near people.
Andrew Ballard, Founder and CEO of SpatioTemporal, described the problem the company is trying to solve.
“Humans are not structured environments. We are variable, social and occasionally inconvenient. But that variability is not noise. It carries information,” Ballard explained.
The company builds a software layer that sits between a robot’s perception and planning systems, predicting what people and objects in its environment are about to do.
“Perception can tell a robot there are five people in a room. Planning can chart a route between them,” Ballard added. “But only motion intelligence can help it understand who is stepping aside, who is approaching, who has changed their mind and who the robot should pay attention to.”
The scenarios are familiar: who goes first at a doorway, whether a person leaning forward is about to take a step or simply shifting their weight. As robots and autonomous vehicles move out of laboratory settings and into shared spaces, these judgement calls will occur with increasing frequency. Getting them wrong results in hesitation at best and collision at worst.
Movement As A Language
Rather than analysing pixels or waypoints, SpatioTemporal’s foundation model treats movement as a language. The system models object kinematics as 10,000 discrete motion tokens and reads intent from the transitions between them.
The approach is designed to give machines the ability to anticipate human behaviour rather than simply react to it, bridging the gap between detecting that a person is present and understanding what that person is about to do.
Simulation Results
SpatioTemporal has run more than 500,000 simulated robot-human proximity encounters in Nvidia Cosmos, an AI stack used for autonomy applications.
In the company’s most difficult test scenario, the baseline autonomy system recorded near-collisions in 24 per cent of runs. Adding SpatioTemporal’s motion intelligence signals reduced that figure to 2 per cent, with robots yielding earlier, moving more smoothly and making fewer unstable changes of direction.
Market Scope
The potential market for the technology spans any machine that operates near people, including humanoid robots, autonomous vehicles and warehouse automation systems.
SpatioTemporal’s advisory network includes Professor Alan Duffy, Pro Vice-Chancellor for Flagship Initiatives at Swinburne University, connecting the company into Australia’s research ecosystem as it looks to scale.
Funding And Growth
SpatioTemporal is raising a pre-seed round to fund what it describes as a nine-month sprint focused on three objectives: proving its motion intelligence on a live use case, formalising intent-aware benchmarks and converting that proof into partnership and licensing conversations across the AI, robotics and automotive sectors.
Related: Best Business Laptops for work & school
Related: Best Gaming Laptops
Related: Best Portable Laptop
The Prize
The Propel-AIR program is designed to accelerate Australian robotics and AI companies by providing business development tools, guidance and networks. The program culminates in a virtual pitch to an international panel of experts.
The winner will receive a one-month residency at MassRobotics in Boston, with access to robotics companies and institutions including MIT and Harvard.
Last Updated on July 23, 2026 by Nick Ross
