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

Sampling-based path planning algorithms play an important role in autonomousrobotics. However, a common problem among the RRT-based algorithms is that theinitial path generated is not optimal and the convergence is too slow to beused in real-world applications. In this paper, we propose a novel image-basedlearning algorithm (CBAGAN-RRT) using a Convolutional Block AttentionGenerative Adversarial Network with a combination of spatial and channelattention and a novel loss function to design the heuristics, find a betteroptimal path, and improve the convergence of the algorithm both concerning timeand speed. The probability distribution of the paths generated from our GANmodel is used to guide the sampling process for the RRT algorithm. We train andtest our network on the dataset generated by \cite{zhang2021generative} anddemonstrate that our algorithm outperforms the previous state-of-the-artalgorithms using both the image quality generation metrics like IOU Score, DiceScore, FID score, and path planning metrics like time cost and the number ofnodes. We conduct detailed experiments and ablation studies to illustrate thefeasibility of our study and show that our model performs well not only on thetraining dataset but also on the unseen test dataset. The advantage of ourapproach is that we can avoid the complicated preprocessing in the state space,our model can be generalized to complicated environments like those containingturns and narrow passages without loss of accuracy, and our model can be easilyintegrated with other sampling-based path planning algorithms.

CBAGAN-RRT: Convolutional Block Attention Generative Adversarial Network for Sampling-Based Path Planning