Movement Intelligence for Physical AI
We capture the physics of human motion at population scale—the Ground Truth layer for humanoid robotics, world models, and predictive health.
Vision
Research in Sensing and Embodiment Lab (RISE)
RISE Lab pioneers Movement Intelligence — Unlocking the physics of human motion to power embodied AI. Every step captures rich, real-world data on gait dynamics, terrain adaptation, and physiological signals. We bridge human biomechanics to robotics, enabling safer, more adaptive systems for the physical world.
The sim-to-real gap limits physical AI
Robots trained in sim produce conservative, unnatural movement
World models lack physics
grounding
VLA architectures need multimodal data at scale
three core products
RISE Motion
Curated multimodal datasets for robotics training
- Population-scale ecological data (not lab-constrained)
- Formatted for major physics engines and RL frameworks
RISE World
Terrain datasets for sim-to-real transfer
- Surface properties cameras can't capture (friction, compliance, stability)
- 100+ terrain types mapped with ground interaction data
- Physics priors for world models and synthetic data validation
RISE Health
Foundation models for disease prediction
- "The Sixth Vital Sign" (gait predicts mortality)
- Pre-symptomatic detection: neurodegeneration, cardiovascular, frailty
- Edge-to-cloud deployment options
AREAS
Gait &
Balance
Quantify asymmetry, stability, and recovery for fall prevention and robot bipedality
Foot Pose & Terrain
Map ground interactions across 100+ surfaces, informing sim-to-real transfer
Cardiovascular Signals
Pair heart rate with motion for fatigue detection and load response
Edge
Cases
Annotated slips, perturbations, and adaptations from real-world steps
Powering breakthroughs in humanoid robotics, clinical gait analysis, and synthetic data calibration.
Every step is Ground Truth
RISE Lab collaborates on dataset access, joint publications, and co-research. Ideal for robotics, biomechanics, and health AI groups.