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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Human motion prediction is essential for the safe and smooth operation ofmobile service robots and intelligent vehicles around people. Commonly usedneural network-based approaches often require large amounts of completetrajectories to represent motion dynamics in complex semantically-rich spaces.This requirement may complicate deployment of physical systems in newenvironments, especially when the data is being collected online from onboardsensors. In this paper we explore a data-efficient alternative using maps ofdynamics (MoD) to represent place-dependent multi-modal spatial motionpatterns, learned from prior observations. Our approach can perform efficienthuman motion prediction in the long-term perspective of up to 60 seconds. Wequantitatively evaluate its accuracy with limited amount of training data incomparison to an LSTM-based baseline, and qualitatively show that the predictedtrajectories reflect the natural semantic properties of the environment, e.g.the locations of short- and long-term goals, navigation in narrow passages,around obstacles, etc.

A Data-Efficient Approach for Long-Term Human Motion Prediction Using Maps of Dynamics