NVIDIA invited SpatioTemporal to put Cosmos 3 through its paces. We tested whether our Motion Intelligence foundation model could help it better understand a moving world. In controlled benchmarks using real motion trajectories, Cosmos identified the actors that mattered with 8× greater accuracy.
Léo Morillon, who writes about the emerging robotics stack, described a robot brain being divided by latency: “Rent the plan, not the reflex.” The premise is straightforward. Some parts of a robot’s intelligence can move to the cloud. Others physically cannot.
Trust, selective cognition and the reflexive intelligence robots need around humans
Robots can already see, navigate and plan. So why aren’t they everywhere?
Introducing World State Vectors for Physical AI.
A controlled experiment using NVIDIA Cosmos suggests that explicit behavioural state can materially change how a robot acts around people. In a controlled crossing experiment using NVIDIA Cosmos-Reason2-8B, the proportion of encounters entering a defined collision envelope fell from 24% to 2% when Motion Intelligence-derived behavioural information was available to the planner.