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

Motion planning is integral to robotics applications such as autonomousdriving, surgical robots, and industrial manipulators. Existing planningmethods lack scalability to higher-dimensional spaces, while recent learningbased planners have shown promise in accelerating sampling-based motionplanners (SMP) but lack generalizability to out-of-distribution environments.To address this, we present a novel approach, Vector Quantized-Motion PlanningTransformers (VQ-MPT) that overcomes the key generalization and scalingdrawbacks of previous learning-based methods. VQ-MPT consists of two stages.Stage 1 is a Vector Quantized-Variational AutoEncoder model that learns torepresent the planning space using a finite number of sampling distributions,and stage 2 is an Auto-Regressive model that constructs a sampling region forSMPs by selecting from the learned sampling distribution sets. By splittinglarge planning spaces into discrete sets and selectively choosing the samplingregions, our planner pairs well with out-of-the-box SMPs, generatingnear-optimal paths faster than without VQ-MPT's aid. It is generalizable inthat it can be applied to systems of varying complexities, from 2D planar to14D bi-manual robots with diverse environment representations, includingcostmaps and point clouds. Trained VQ-MPT models generalize to environmentsunseen during training and achieve higher success rates than previous methods.

Learning Sampling Dictionaries for Efficient and Generalizable Robot Motion Planning with Transformers