Stam: a framework for spatio-temporal affordance maps

Riccio, Francesco, Capobianco, Roberto, Hanheide, Marc and Nardi, Daniele (2016) Stam: a framework for spatio-temporal affordance maps. In: International Workshop on Modelling and Simulation for Autonomous Systems, 15 - 16 June 2016, Rome, Italy.

Full content URL: http://mesas.mscoe.org/images/presentations/150620...

Documents
1607.00354.pdf
[img]
[Download]
[img]
Preview
PDF
1607.00354.pdf - Whole Document

1MB
Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

A�ordances have been introduced in literature as action op-
portunities that objects o�er, and used in robotics to semantically rep-
resent their interconnection. However, when considering an environment
instead of an object, the problem becomes more complex due to the
dynamism of its state. To tackle this issue, we introduce the concept
of Spatio-Temporal A�ordances (STA) and Spatio-Temporal A�ordance
Map (STAM). Using this formalism, we encode action semantics re-
lated to the environment to improve task execution capabilities of an
autonomous robot. We experimentally validate our approach to support
the execution of robot tasks by showing that a�ordances encode accurate
semantics of the environment.

Keywords:mobile robotics, Artificial intelligence
Subjects:G Mathematical and Computer Sciences > G700 Artificial Intelligence
H Engineering > H671 Robotics
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:24851
Deposited On:26 Oct 2016 08:55

Repository Staff Only: item control page