Short Seminars by prospective young researches at Computer Science and Engineering - DEIB
Modeling indoor environments for autonomous mobile robots
Matteo Luperto
Research Assistant at the Applied Intelligent System Laboratory (AISLab)
Dip. di Informatica Giovanni Degli Antoni, Università degli Studi di Milano
Politecnico di Milano, this seminar will be held online
September 23rd, 2020
5.00 pm
Matteo Luperto
Research Assistant at the Applied Intelligent System Laboratory (AISLab)
Dip. di Informatica Giovanni Degli Antoni, Università degli Studi di Milano
Politecnico di Milano, this seminar will be held online
September 23rd, 2020
5.00 pm
Sommario
Autonomous mobile robots can perform many different tasks to help humans during their activities or to replace them in hazardous environments and in simple routine operations. When we consider indoor tasks, robots have to interact with human-made environments that are specifically designed for human activities, buildings. Buildings are strongly structured environments that are organized in regular patterns. For instance, rooms typically have a geometrical structure that is characterized by features, such as walls perpendicular to the floor, symmetries, and by a layout that can be, in most cases, approximated by a box-like model. The dynamics of the environment can also be subject to different temporal patterns (daily, weekly, monthly), as in the case of working hours in a 9-to-5 daily schedule. Our main research interest moves from the consideration that the identification and modeling of the underlying structure of buildings could be exploited to increase the autonomy of robots when operating in indoor environments. We consider floors of buildings as a single entity by identifying relations between different (and potentially unconnected) parts, such as walls and rooms. These relations are used to model the building structure, to better understand the known parts of the building, and to infer the possible structure of unobserved ones by completing missing observations. Long-term data collected through robot operational use and the integration of heterogeneous knowledge are used to model cyclic environmental temporal patterns and, ultimately, to adapt the robots’ behavior accordingly. These findings show how a deeper understanding of indoor environments could increase the performance and long-term autonomy of autonomous mobile robots towards their widespread adoption.
Biografia
Matteo Luperto is Research Assistant at the Applied Intelligent System Laboratory (AISLab), Dipartimento di Informatica Giovanni Degli Antoni, Università degli Studi di Milano, since November 2016. His main research interests are in semantic mapping for autonomous mobile robots and social assistive mobile robotics.
The seminar will be held online. Please follow the instructions below:
Meeting number: 121 725 5828
Password: JDxRmeRZ783
https://politecnicomilano.webex.com/
Join by video system
Dial 1217255828@politecnicomilano.webex.com
You can also dial 62.109.219.4 and enter your meeting number.
Join by phone
+44-20-7660-8149 United Kingdom Toll
Access code: 121 725 5828
The seminar will be held online. Please follow the instructions below:
Meeting number: 121 725 5828
Password: JDxRmeRZ783
https://politecnicomilano.webex.com/
Join by video system
Dial 1217255828@politecnicomilano.webex.com
You can also dial 62.109.219.4 and enter your meeting number.
Join by phone
+44-20-7660-8149 United Kingdom Toll
Access code: 121 725 5828