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

Recently, there has been tremendous interest in industry 4.0 infrastructureto address labor shortages in global supply chains. Deploying artificialintelligence-enabled robotic bin picking systems in real world has becomeparticularly important for reducing stress and physical demands of workerswhile increasing speed and efficiency of warehouses. To this end, artificialintelligence-enabled robotic bin picking systems may be used to automate orderpicking, but with the risk of causing expensive damage during an abnormal eventsuch as sensor failure. As such, reliability becomes a critical factor fortranslating artificial intelligence research to real world applications andproducts. In this paper, we propose a reliable object detection andsegmentation system with MultiModal Redundancy (MMRNet) for tackling objectdetection and segmentation for robotic bin picking using data from differentmodalities. This is the first system that introduces the concept of multimodalredundancy to address sensor failure issues during deployment. In particular,we realize the multimodal redundancy framework with a gate fusion module anddynamic ensemble learning. Finally, we present a new label-free multi-modalconsistency (MC) score that utilizes the output from all modalities to measurethe overall system output reliability and uncertainty. Through experiments, wedemonstrate that in an event of missing modality, our system provides a muchmore reliable performance compared to baseline models. We also demonstrate thatour MC score is a more reliability indicator for outputs during inference timecompared to the model generated confidence scores that are oftenover-confident.

MMRNet: Improving Reliability for Multimodal Object Detection and Segmentation for Bin Picking via Multimodal Redundancy