Perception under partial observability
Developing perception systems that integrate RGB-D, audio, motion, tactile, and proprioceptive signals to enhance reliability in dynamic, partially observable environments.
ResearchResearch driven by
Research driven by
real-world deployment
Robgence operates at the intersection of robotics research and large-scale data operations. All our initiatives revolve around the core challenges of Physical AI, like perception, manipulation, teleoperation, world models, and sim-to-real transfer. Every research project is based on the data collected from real-world environments.
Learning from human demonstrations
Exploring imitation learning, teleoperation, and human demonstration datasets for training embodied AI systems to perform complex tasks in the real world.
Closing the reality gap
Building pipelines which utilize synthetic data, digital twins, and high-fidelity real-world datasets to reduce the reality gap.
Foundation models for embodied intelligence
Investigating large-scale egocentric and multimodal datasets that power VLA models, and next-generation robotics foundation models.
Our Vision
We’re not just building data infrastructure. We’re building toward embodied intelligence.
Robgence began by solving one of the most fundamental challenges in Physical AI: access to high-quality real-world data. However, data collection is only the beginning.
Every environment we capture, every interaction we record, and every dataset we deliver contributes to a larger mission — extending our research into the core challenges that will define the next generation of embodied intelligence.
The Frontiers We’re Building Toward
Hover or focus a card
Humanoid Robotics
Full-body sensorimotor learning for humanoid platforms — gait, balance, and dexterous bimanual manipulation in the environments humans share.
World Models
Predictive models of the physical world that let policies plan, simulate, and reason across long horizons before acting.
Manipulation Learning
Dexterous policies for grasping, tool use, and contact-rich tasks, learned from real-world demonstrations across diverse objects.
Autonomous Decision-Making
Closed-loop planning under uncertainty — agents that perceive, reason, and act in dynamic, partially observable environments.
By combining large-scale data operations with applied robotics research, we’re helping build the foundations for systems that can understand, adapt to, and operate within the physical world with greater capability and autonomy.
Selected Publications
Recent work
- 2026ICRATactile-conditioned policies for unstructured manipulation
- 2025CoRLDistribution-aware data scaling for Physical AI
- 2025RSSOperator-in-the-loop imitation learning from active manufacturing facilities
- 2024NeurIPS WorkshopSynthetic + real curriculum for multi-finger grasping