<div class="csl-bib-body">
<div class="csl-entry">Valls Mascaro, E., & Lee, D. (2024, October 1). <i>Know your limits! Optimize the robot’s behavior through self-awareness</i> [Poster Presentation]. 17th International Workshop on Human-Friendly Robotics (HFR 2024), Lugano, Switzerland. http://hdl.handle.net/20.500.12708/209813</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/209813
-
dc.description.abstract
As humanoid robots transition from labs to realworld environments, it is essential to democratize robot control for non-expert users. Recent human-robot imitation algorithms focus on following a reference human motion with high precision, but they are susceptible to the quality of the reference motion and require the human operator to simplify its movements to match the robot’s capabilities. Instead, we consider that the robot should understand and adapt the reference motion to its own abilities, facilitating the operator’s task. For that, we introduce a deep-learning model that anticipates the robot’s performance when imitating a given reference. Then, our system can generate multiple references given a highlevel task command, assign a score to each of them, and select the best reference to achieve the desired robot behavior. Our Self-AWare model (SAW) ranks potential robot behaviors based on various criteria, such as fall likelihood, adherence to the reference motion, and smoothness. We integrate advanced motion generation, robot control, and SAW in one unique system, ensuring optimal robot behavior for any task command. For instance, SAW can anticipate falls with 99.29% accuracy.
en
dc.description.sponsorship
European Commission
-
dc.language.iso
en
-
dc.subject
deep learning
en
dc.subject
reinforcement learning
en
dc.subject
bipedal robots
en
dc.subject
autonomous robots
en
dc.subject
self-awreness
en
dc.title
Know your limits! Optimize the robot’s behavior through self-awareness
en
dc.type
Presentation
en
dc.type
Vortrag
de
dc.relation.grantno
H2020-MSCA-ITN-2019
-
dc.type.category
Poster Presentation
-
tuw.project.title
PErsonalized Robotics as SErvice Oriented applications
-
tuw.researchTopic.id
I3
-
tuw.researchTopic.name
Automation and Robotics
-
tuw.researchTopic.value
100
-
tuw.publication.orgunit
E384-03 - Forschungsbereich Autonomous Systems
-
tuw.author.orcid
0000-0003-1897-7664
-
tuw.event.name
17th International Workshop on Human-Friendly Robotics (HFR 2024)
en
tuw.event.startdate
30-09-2024
-
tuw.event.enddate
01-10-2024
-
tuw.event.online
On Site
-
tuw.event.type
Event for scientific audience
-
tuw.event.place
Lugano
-
tuw.event.country
CH
-
tuw.event.institution
Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI.
