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

Safe and efficient crowd navigation for mobile robot is a crucial yetchallenging task. Previous work has shown the power of deep reinforcementlearning frameworks to train efficient policies. However, their performancedeteriorates when the crowd size grows. We suggest that this can be addressedby enabling the network to identify and pay attention to the humans in thecrowd that are most critical to navigation. We propose a novel networkutilizing a graph representation to learn the policy. We first train a graphconvolutional network based on human gaze data that accurately predicts humanattention to different agents in the crowd. Then we incorporate the learnedattention into a graph-based reinforcement learning architecture. The proposedattention mechanism enables the assignment of meaningful weightings to theneighbors of the robot, and has the additional benefit of interpretability.Experiments on real-world dense pedestrian datasets with various crowd sizesdemonstrate that our model outperforms state-of-art methods by 18.4% in taskaccomplishment and by 16.4% in time efficiency.

Robot Navigation in Crowds by Graph Convolutional Networks with Attention Learned from Human Gaze