General in-hand object rotation with vision and touch
We introduce Rotateit, a system that enables fingertip-based object rotation along multiple
axes by leveraging multimodal sensory inputs. Our system is trained in simulation, where it …
axes by leveraging multimodal sensory inputs. Our system is trained in simulation, where it …
Where2explore: Few-shot affordance learning for unseen novel categories of articulated objects
Articulated object manipulation is a fundamental yet challenging task in robotics. Due to
significant geometric and semantic variations across object categories, previous …
significant geometric and semantic variations across object categories, previous …
Robot synesthesia: In-hand manipulation with visuotactile sensing
Executing contact-rich manipulation tasks necessitates the fusion of tactile and visual
feedback. However, the distinct nature of these modalities poses significant challenges. In …
feedback. However, the distinct nature of these modalities poses significant challenges. In …
Robot learning in the era of foundation models: A survey
X **
Dexterous gras** aims to produce diverse gras** postures with a high gras**
success rate. Regression-based methods that directly predict gras** parameters given the …
success rate. Regression-based methods that directly predict gras** parameters given the …
3d diffusion policy
Imitation learning provides an efficient way to teach robots dexterous skills; however,
learning complex skills robustly and generalizablely usually consumes large amounts of …
learning complex skills robustly and generalizablely usually consumes large amounts of …
Vividex: Learning vision-based dexterous manipulation from human videos
In this work, we aim to learn a unified vision-based policy for multi-fingered robot hands to
manipulate a variety of objects in diverse poses. Though prior work has shown benefits of …
manipulate a variety of objects in diverse poses. Though prior work has shown benefits of …