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

Ground robots which are able to navigate a variety of terrains are needed inmany domains. One of the key aspects is the capability to adapt to the groundstructure, which can be realized through movable body parts coming along withadditional degrees of freedom (DoF). However, planning respective locomotion ischallenging since suitable representations result in large state spaces.Employing an additional abstract representation---which is coarser,lower-dimensional, and semantically enriched---can support the planning.  While a desired robot representation and action set of such an abstractrepresentation can be easily defined, the cost function requires large tuningefforts. We propose a method to represent the cost function as a CNN. Trainingof the network is done on generated artificial data, while it generalizes wellto the abstraction of real world scenes. We further apply our method to theproblem of search-based planning of hybrid driving-stepping locomotion. Theabstract representation is used as a powerful informed heuristic whichaccelerates planning by multiple orders of magnitude.

Towards Learning Abstract Representations for Locomotion Planning in High-dimensional State Spaces