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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The problem of autonomous transportation in industrial scenarios is receivinga renewed interest due to the way it can revolutionise internal logistics,especially in unstructured environments. This paper presents a novelarchitecture allowing a robot to detect, localise, and track (possiblymultiple) pallets using machine learning techniques based on an on-board 2Dlaser rangefinder only. The architecture is composed of two main components:the first stage is a pallet detector employing a Faster Region-basedConvolutional Neural Network (Faster R-CNN) detector cascaded with a CNN-basedclassifier; the second stage is a Kalman filter for localising and trackingdetected pallets, which we also use to defer commitment to a pallet detected inthe first stage until sufficient confidence has been acquired via a sequentialdata acquisition process. For fine-tuning the CNNs, the architecture has beensystematically evaluated using a real-world dataset containing 340 labeled 2Dscans, which have been made freely available in an online repository. Detectionperformance has been assessed on the basis of the average accuracy over k-foldcross-validation, and it scored 99.58% in our tests. Concerning palletlocalisation and tracking, experiments have been performed in a scenario wherethe robot is approaching the pallet to fork. Although data have been originallyacquired by considering only one pallet as per specification of the use case weconsider, artificial data have been generated as well to mimic the presence ofmultiple pallets in the robot workspace. Our experimental results confirm thatthe system is capable of identifying, localising and tracking pallets with ahigh success rate while being robust to false positives.

Detection, localisation and tracking of pallets using machine learning techniques and 2D range data