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

This paper presents a novel method for accelerating path planning tasks inunknown scenes with obstacles by utilizing Wasserstein Generative AdversarialNetworks (WGANs) with Gradient Penalty (GP) to approximate the distribution ofthe free conditioned configuration space. Our proposed approach involvesconditioning the WGAN-GP with a Variational Auto-Encoder in a continuous latentspace to handle multimodal datasets. However, training a VariationalAuto-Encoder with WGAN-GP can be challenging for image-to-configuration-spaceproblems, as the Kullback-Leibler loss function often converges to a randomdistribution. To overcome this issue, we simplify the configuration space as aset of Gaussian distributions and divide the dataset into several local models.This enables us to not only learn the model but also speed up its convergence.We evaluate the reconstructed configuration space using the homology rank ofmanifolds for datasets with the geometry score. Furthermore, we propose a noveltransformation of the robot's configuration space that enables us to measurehow well collision-free regions are reconstructed, which could be used withother rank of homology metrics. Our experiments show promising results foraccelerating path planning tasks in unknown scenes while generatingquasi-optimal paths with our WGAN-GP. The source code is openly available.

Improving Path Planning Performance through Multimodal Generative Models with Local Critics