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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Object shaping by grinding is a crucial industrial process in which arotating grinding belt removes material. Object-shape transition models areessential to achieving automation by robots; however, learning such a complexmodel that depends on process conditions is challenging because it requires asignificant amount of data, and the irreversible nature of the removal processmakes data collection expensive. This paper proposes a cutting-surface-awareModel-Based Reinforcement Learning (MBRL) method for robotic grinding. Ourmethod employs a cutting-surface-aware model as the object's shape transitionmodel, which in turn is composed of a geometric cutting model and acutting-surface-deviation model, based on the assumption that the robot actioncan specify the cutting surface made by the tool. Furthermore, according to thegrinding resistance theory, the cutting-surface-deviation model does notrequire raw shape information, making the model's dimensions smaller and easierto learn than a naive shape transition model directly mapping the shapes.Through evaluation and comparison by simulation and real robot experiments, weconfirm that our MBRL method can achieve high data efficiency for learningobject shaping by grinding and also provide generalization capability forinitial and target shapes that differ from the training data.

Learning to Shape by Grinding: Cutting-surface-aware Model-based Reinforcement Learning