Functionalities, Benchmarking System and Performance Evaluation for a Domestic Service Robot: People Perception, People Following, and Pick and Placing

This paper describes the development of three main functionalities for a domestic mobile service robot and an automatic benchmarking system used for the systematic performance evaluation of the robot’s functionalities. Three main robot functionalities are addressed: (1) People Perception, (2) People...

Full description

Saved in:
Bibliographic Details
Published in:Applied sciences 2022-05, Vol.12 (10), p.4819
Main Authors: Basiri, Meysam, Pereira, João, Bettencourt, Rui, Piazza, Enrico, Fernandes, Emanuel, Azevedo, Carlos, Lima, Pedro
Format: Article
Language:English
Subjects:
benchmarking
Benchmarks
Cameras
domestic service robots
Experiments
human following
human perception
Lasers
Neural networks
Older people
Perception
Performance evaluation
performance evaluation system
pick and placing
Planning
Robotics
Robots
Sensors
Service robots
Software
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper describes the development of three main functionalities for a domestic mobile service robot and an automatic benchmarking system used for the systematic performance evaluation of the robot’s functionalities. Three main robot functionalities are addressed: (1) People Perception, (2) People Following and (3) Pick and Placing, where the hardware and software systems developed for each functionality are described and demonstrated on an actual mobile service robot, with the goal of providing assistance to an elderly person inside the house. Furthermore, a set of innovative benchmarks and an automatic performance evaluation system are proposed and used to evaluate the performance of the developed functionalities. These benchmarks are now made publicly available and is part of the European Robotics League (ERL)-Consumer to systematically evaluate the performance of service robot solutions at different testbeds around Europe.
ISSN:2076-3417
2076-3417
DOI:10.3390/app12104819