Embodied Data Ecology
Capture high-fidelity interaction streams across robots, humans, objects, and scenes.
FIG. RHOS-001 / PHYSICAL AI OPERATING STACK
RHOS
Robot · Human · Object · Scene
Building next-generation physical large models from embodied data, causal world models, and robot deployment feedback.
Signal
Vision · Tactile · Force
Loop
Collect · Model · Deploy
Target
General Robot Policy
System
Data + Model + Robot Flywheel
01 / Operating Thesis
Teaching physical intelligence through interaction.
Driven by the first-principle conviction that Embodied Intelligence is the essential path to AGI, RHOS studies the intersection of digital intelligence and physical reality.
Our RoboNet framework treats robots as intelligent data interfaces, shifting learning from static offline datasets toward dynamic Physical AI powered by automated, online intervention.
02 / System Architecture
One loop from physical data to deployed robot behavior.
Physical World Models
Learn actionable models that connect perception, contact, force, intent, and action.
Real-Robot Deployment
Deploy, intervene, evaluate, and feed real-world outcomes back into model improvement.
03 / Selected Research
Physical Reasoning · Robot Learning · Benchmarks
CVPR 2026
IPR-1: Interactive Physical Reasoner
Implicit physical-causal world models that look ahead across 1,000+ physical worlds.
Project
Benchmark
The Great March 100
A real-world task suite for evaluating physical robustness and embodied generalization.
Project
Robot Learning
AetheRock
An arm-worn robot teaching system for force-guided vision-tactile learning.
Project
04 / Bridge Layer
InputVirtual simulation
InputReal-world interaction
OutputGeneral-purpose robotics
From world models to physical deployment.
RHOS builds a critical bridge between human-centric generative AI and the rigorous demands of physical environments. By fusing simulated experience with high-fidelity spatiotemporal data from real-world interactions, we work toward zero-shot generalization for unseen robots and unseen tasks.
05 / About RHOS
A physical AI company building robot foundation systems.
RHOS brings together world modeling, embodied data, motion control, and robotic hardware to develop systems that learn from real physical interaction.
We focus on the full feedback loop: collect, model, deploy, evaluate, and improve.
06 / Careers
Build physical intelligence with us.
World models · Data systems · Motion control · Hardware
Open roles