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 major challenge with off-road autonomous navigation is the lack of maps orroad markings that can be used to plan a path for autonomous robots. Classicalpath planning methods mostly assume a perfectly known environment withoutaccounting for the inherent perception and sensing uncertainty from detectingterrain and obstacles in off-road environments. Recent work in computer visionand deep neural networks has advanced the capability of terrain traversabilitysegmentation from raw images; however, the feasibility of using these noisysegmentation maps for navigation and path planning has not been adequatelyexplored. To address this problem, this research proposes an uncertainty-awarepath planning method, URA* using aerial images for autonomous navigation inoff-road environments. An ensemble convolutional neural network (CNN) model isfirst used to perform pixel-level traversability estimation from aerial imagesof the region of interest. The traversability predictions are represented as agrid of traversal probability values. An uncertainty-aware planner is thenapplied to compute the best path from a start point to a goal point given thesenoisy traversal probability estimates. The proposed planner also incorporatesreplanning techniques to allow rapid replanning during online robot operation.The proposed method is evaluated on the Massachusetts Road Dataset, theDeepGlobe dataset, as well as a dataset of aerial images from off-road provinggrounds at Mississippi State University. Results show that the proposed imagesegmentation and planning methods outperform conventional planning algorithmsin terms of the quality and feasibility of the initial path, as well as thequality of replanned paths.

URA*: Uncertainty-aware Path Planning using Image-based Aerial-to-Ground Traversability Estimation for Off-road Environments