Related Research

MoMaGen

MoMaGen automatically generates diverse training datasets for bimanual mobile manipulation by solving constrained optimization problems that ensure robot reachability and camera visibility from minimal human demonstrations.

BEHAVIOR Robot Suite

BEHAVIOR Robot Suite (BRS) provides the robot embodiment needed for complex household tasks. Built on a bimanual wheeled robot with a 4-DoF torso, BRS integrates a cost-effective teleoperation interface for data collection and a novel algorithm for learning whole-body visuomotor policies.

Automated Creation of Digital Cousins for Robust Policy Learning

ACDC (Automatic Creation of Digital Cousins) is a method that addresses the limitations of real-world robot training and sim-to-real transfer by introducing "digital cousins" - virtual environments that capture similar geometric and semantic affordances to real scenes without explicitly modeling them.

BEHAVIOR Vision Suite

BEHAVIOR Vision Suite is a synthetic data generator that addresses limitations in current computer vision datasets by providing high-quality, controllable data generation. It offers adjustable parameters at scene, object, and camera levels, enabling researchers to conduct controlled experiments.

BEHAVIOR Series

BEHAVIOR-100

BEHAVIOR-100 is the first generation of BEHAVIOR, a benchmark for embodied AI with 100 activities instantiated in iGibson 2.0.

BEHAVIOR-1K

BEHAVIOR-1K is the latest generation of BEHAVIOR, featuring 1000 household tasks that significantly expand beyond BEHAVIOR-100 in both quantity and diversity, instantiated in OmniGibson with full-length, realistic task complexity.

Gibson Simulation Series

The Gibson series is named after James J. Gibson, the author of Ecological Approach to Visual Perception, 1979. Read a relevant excerpt of JJ Gibson's book here. “We must perceive in order to move, but we must also move in order to perceive” – JJ Gibson.