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

A factored Nonlinear Program (Factored-NLP) explicitly models thedependencies between a set of continuous variables and nonlinear constraints,providing an expressive formulation for relevant robotics problems such asmanipulation planning or simultaneous localization and mapping. When theproblem is over-constrained or infeasible, a fundamental issue is to detect aminimal subset of variables and constraints that are infeasible. Previousapproaches require solving several nonlinear programs, incrementally adding andremoving constraints, and are thus computationally expensive. In this paper, wepropose a graph neural architecture that predicts which variables andconstraints are jointly infeasible. The model is trained with a dataset oflabeled subgraphs of Factored-NLPs, and importantly, can make usefulpredictions on larger factored nonlinear programs than the ones seen duringtraining. We evaluate our approach in robotic manipulation planning, where ourmodel is able to generalize to longer manipulation sequences involving moreobjects and robots, and different geometric environments. The experiments showthat the learned model accelerates general algorithms for conflict extraction(by a factor of 50) and heuristic algorithms that exploit expert knowledge (bya factor of 4).

Learning Feasibility of Factored Nonlinear Programs in Robotic Manipulation Planning