Search papers, labs, and topics across Lattice.
8
0
6
10
Integration of diverse robot policies can be streamlined from hours to minutes, revolutionizing how we deploy and evaluate robotic systems.
The data pyramid framework reveals how the interplay of diverse data sources can unlock new capabilities in embodied agents, highlighting critical gaps in current methodologies.
RoboDojo reveals that integrating simulation and real-world tasks can significantly enhance the evaluation of robot manipulation policies, bridging the gap between theoretical performance and practical deployment.
Achieving 86.4% grasp stability and 83.3% real-world success, SynManDex bridges the gap between human dexterity and robotic manipulation.
The hardest AI tasks remain largely unsolved, with current models achieving only a 2.6% success rate on economically valuable workflows.
Generating realistic human interactions with objects and scenes is now possible even with limited data, thanks to a clever training strategy that combines synthetic and real data.
Forget painstakingly creating 3D assets for robot training - ManiTwin automates the process, turning single images into simulation-ready objects at scale.
Finally, a robot can reliably pick out that specific shirt from a messy pile, thanks to a new vision-language pipeline that reasons about garment affordances.
