Search papers, labs, and topics across Lattice.
JoyAI-RA is introduced as a vision-language-action (VLA) foundation model for robotic manipulation, addressing limitations in data diversity and cross-embodiment generalization. The model is trained using a multi-source multi-level pretraining framework that integrates web data, egocentric human videos, simulation trajectories, and real-robot data, with explicit action-space unification. JoyAI-RA demonstrates superior performance over existing methods in both simulated and real-world robotic tasks, particularly those requiring generalization.
Bridging the gap between human manipulation and robotic control, JoyAI-RA unlocks enhanced cross-embodiment behavior learning through multi-source pretraining.
Robotic autonomy in open-world environments is fundamentally limited by insufficient data diversity and poor cross-embodiment generalization. Existing robotic datasets are often limited in scale and task coverage, while relatively large differences across robot embodiments impede effective behavior knowledge transfer. To address these challenges, we propose JoyAI-RA, a vision-language-action (VLA) embodied foundation model tailored for generalizable robotic manipulation. JoyAI-RA presents a multi-source multi-level pretraining framework that integrates web data, large-scale egocentric human manipulation videos, simulation-generated trajectories, and real-robot data. Through training on heterogeneous multi-source data with explicit action-space unification, JoyAI-RA effectively bridges embodiment gaps, particularly between human manipulation and robotic control, thereby enhancing cross-embodiment behavior learning. JoyAI-RA outperforms state-of-the-art methods in both simulation and real-world benchmarks, especially on diverse tasks with generalization demands.
