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

We present an approach for mobile robots to learn to navigate in dynamicenvironments with pedestrians via raw depth inputs, in a socially compliantmanner. To achieve this, we adopt a generative adversarial imitation learning(GAIL) strategy, which improves upon a pre-trained behavior cloning policy. Ourapproach overcomes the disadvantages of previous methods, as they heavilydepend on the full knowledge of the location and velocity information of nearbypedestrians, which not only requires specific sensors, but also the extractionof such state information from raw sensory input could consume much computationtime. In this paper, our proposed GAIL-based model performs directly on rawdepth inputs and plans in real-time. Experiments show that our GAIL-basedapproach greatly improves the safety and efficiency of the behavior of mobilerobots from pure behavior cloning. The real-world deployment also shows thatour method is capable of guiding autonomous vehicles to navigate in a sociallycompliant manner directly through raw depth inputs. In addition, we release asimulation plugin for modeling pedestrian behaviors based on the social forcemodel.

Socially Compliant Navigation through Raw Depth Inputs with Generative Adversarial Imitation Learning