English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Grasping objects under uncertainty remains an open problem in roboticsresearch. This uncertainty is often due to noisy or partial observations of theobject pose or shape. To enable a robot to react appropriately to unforeseeneffects, it is crucial that it continuously takes sensor feedback into account.While visual feedback is important for inferring a grasp pose and reaching foran object, contact feedback offers valuable information during manipulation andgrasp acquisition. In this paper, we use model-free deep reinforcement learningto synthesize control policies that exploit contact sensing to generate robustgrasping under uncertainty. We demonstrate our approach on a multi-fingeredhand that exhibits more complex finger coordination than the commonly usedtwo-fingered grippers. We conduct extensive experiments in order to assess theperformance of the learned policies, with and without contact sensing. While itis possible to learn grasping policies without contact sensing, our resultssuggest that contact feedback allows for a significant improvement of graspingrobustness under object pose uncertainty and for objects with a complex shape.

Leveraging Contact Forces for Learning to Grasp