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

We present a learning-enabled Task and Motion Planning (TAMP) algorithm forsolving mobile manipulation problems in environments with many articulated andmovable obstacles. Our idea is to bias the search procedure of a traditionalTAMP planner with a learned plan feasibility predictor. The core of ouralgorithm is PIGINet, a novel Transformer-based learning method that takes in atask plan, the goal, and the initial state, and predicts the probability offinding motion trajectories associated with the task plan. We integrate PIGINetwithin a TAMP planner that generates a diverse set of high-level task plans,sorts them by their predicted likelihood of feasibility, and refines them inthat order. We evaluate the runtime of our TAMP algorithm on seven families ofkitchen rearrangement problems, comparing its performance to that ofnon-learning baselines. Our experiments show that PIGINet substantiallyimproves planning efficiency, cutting down runtime by 80% on problems withsmall state spaces and 10%-50% on larger ones, after being trained on only150-600 problems. Finally, it also achieves zero-shot generalization toproblems with unseen object categories thanks to its visual encoding ofobjects. Project page https://piginet.github.io/.

Sequence-Based Plan Feasibility Prediction for Efficient Task and Motion Planning