Safe Exploration for Reinforcement Learning in Real Unstructured Environments
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F15%3A00230205" target="_blank" >RIV/68407700:21230/15:00230205 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Safe Exploration for Reinforcement Learning in Real Unstructured Environments
Original language description
In USAR (Urban Search and Rescue) missions, robots are often required to operate in an unknown environment and with imprecise data coming from their sensors. However, it is highly desired that the robots only act in a safe manner and do not perform actions that could probably make damage to them. To train some tasks with the robot, we utilize reinforcement learning (RL). This machine learning method however requires the robot to perform actions leading to unknown states, which may be dangerous. We develop a framework for training a safety function which constrains possible actions to a subset of really safe actions. Our approach utilizes two basic concepts. First, a "core" of the safety function is given by a cautious simulator and possibly also by manually given examples. Second, a classifier training phase is performed (using Neyman-Pearson SVMs), which extends the safety function to the states where the simulator fails to recognize safe states.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JD - Use of computers, robotics and its application
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/GA14-13876S" target="_blank" >GA14-13876S: Perception methods for long-term autonomy of mobile robots</a><br>
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2015
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
CVWW 2015: Proceedings of the 20th Computer Vision Winter Workshop
ISBN
978-3-85125-388-7
ISSN
—
e-ISSN
—
Number of pages
9
Pages from-to
85-93
Publisher name
Graz University of Technology
Place of publication
Graz
Event location
Seggau
Event date
Feb 9, 2015
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—