Show details
ERL Professional Local Tournament, Nottingham, UK, May 2022
|
The first HEART-MET field campaign will take place at the Cobot Maker Space at the University of Nottingham from May 23 - 27, 2022. The competition is organized by HEART-MET under the METRICS framework, and includes a shared benchmark with the European Robotics League (ERL) Professional competition. HEART-MET targets robots that function in an assistive capacity in a home, or healthcare environment such as a nursing home or hospital. ERL Professional (https://old.eu-robotics.net/robotics_league/erl-professional/about/index.html) is a competition framework for mobile robot assistants in professional settings such as factories, grocery stores, hospitals etc. Typical tasks include locating and transporting items and performing collaborative tasks with humans. Therefore, this competition will benchmark robots on several perception, manipulation and human-robot interaction tasks. ### Important Dates ### 12th April, 2022 - Deadline for submission of expression of interest 25th April, 2022 - Deadline to confirm participation 23nd May, 2022 - Competition start 27th May, 2022 - Competition end ### How to participate ### Teams and individuals from academia and industry are welcome to participate in this competition. Please fill out the online form as an expression of interest by April 12th, 2022. Selected teams will be contacted for further details. Online form: https://docs.google.com/forms/d/e/1FAIpQLSfSn51rQCq7v3PHZYZL7sSk-ofsXw1fHiPlSifge8qHBIVWAg/viewform ### Benchmarks ### Teams can participate in any or all of the following functional (FBM) and task (TBM) benchmarks. Based on the level of interest, some benchmarks may not be conducted during the competition. Each benchmark will be evaluated over multiple trials with several variations of objects, locations, persons, time of day etc. FBMs: - Object detection: The robot should detect a target object on a surface in front of it - Person detection: The robot should detect a person at a known location within an indoor environment - Activity recognition: The robot should recognize an activity performed by a person - Gesture recognition: The robot should recognize a gesture performed by a person - Cluttered Pick [shared with ERL Professional]: The robot should pick an object from a cluttered surface and place it in a container - Handover Object: The robot should hand over an object to a person - Receive Object: The robot should receive an object from a person TBMs: - Assess Activity State: The robot should assess the activity state of a person using both visual activity recognition and by engaging in a dialogue with the person. This TBM will require the robot to navigate within an indoor environment, detect persons, visually recognize activities and engage in a dialogue by speech generation and recognition. - Item Delivery: The robot should navigate to a given location, locate and grasp a target object, transport the object to a person at a given location and hand over the object to the person. Hence, this TBM will require functionalities such as indoor navigation, object detection, grasping, person detection and object handover. The latest rulebook can be found here: https://github.com/HEART-MET/rulebook/ |
|
HEART-MET
Deebul Nair deebul.nair@h-brs.de |
|
Cobot Maker Space, The Nottingham Geospatial Building
Triumph Road NG7 2TU Nottingham United Kingdom |
Login
Stay informed
If you like to be informed by mail when new articles are published, please fill out the following form.