A Deployment Framework for Formally Verified Human-Robot Interactions

In the future, assistive robots will spread to everyday settings and regularly interact with humans. This paper introduces a deployment approach for assistive robotic applications where human-robot interaction is the main element. The deployment infrastructure hinges on a model-to-code transformatio...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access Vol. 9; pp. 136616 - 136635
Main Authors: Lestingi, Livia, Askarpour, Mehrnoosh, Bersani, Marcello M., Rossi, Matteo
Format: Journal Article
Language:English
Published: Piscataway IEEE 2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Automata
Codes
Human engineering
Human-robot interaction
Middleware
model-driven approach
Peer-to-peer computing
Robot control
robot deployment
Robotics
Robots
service robots
Simulation
Statistical models
Stochastic processes
Virtual environments
Virtual reality
ISSN:2169-3536, 2169-3536
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In the future, assistive robots will spread to everyday settings and regularly interact with humans. This paper introduces a deployment approach for assistive robotic applications where human-robot interaction is the main element. The deployment infrastructure hinges on a model-to-code transformation technique and a ROS-based middleware layer and enables deployment in real life or simulation in a virtual environment. The approach fits into a model-driven framework for the formal verification of interactive scenarios. At design-time, the application analyst estimates the most likely outcome of the robotic mission through Statistical Model Checking of a Stochastic Hybrid Automata network modeling the scenario. We introduce an innovative approach to convert a specific subset of Stochastic Hybrid Automata into executable code to control the robot and respond to human actions. Deploying or simulating the application allows analysts to validate the results obtained at design time or to refine the formal model based on runs in the real or the virtual scene. The methodology's effectiveness is tested via simulation of use cases from the healthcare setting, which can significantly benefit from this kind of approach thanks to its innovative features related to human physiology and autonomous behavior.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2021.3117852