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

Moving a human body or a large and bulky object can require the strength ofwhole arm manipulation (WAM). This type of manipulation places the load on therobot's arms and relies on global properties of the interaction tosucceed---rather than local contacts such as grasping or non-prehensilepushing. In this paper, we learn to generate motions that enable WAM forholding and transporting of humans in certain rescue or patient care scenarios.We model the task as a reinforcement learning problem in order to provide abehavior that can directly respond to external perturbation and human motion.For this, we represent global properties of the robot-human interaction withtopology-based coordinates that are computed from arm and torso positions.These coordinates also allow transferring the learned policy to other bodyshapes and sizes. For training and evaluation, we simulate a dynamic sea rescuescenario and show in quantitative experiments that the policy can solve unseenscenarios with differently-shaped humans, floating humans, or with perceptionnoise. Our qualitative experiments show the subsequent transporting afterholding is achieved and we demonstrate that the policy can be directlytransferred to a real world setting.

Reinforcement Learning in Topology-based Representation for Human Body Movement with Whole Arm Manipulation