Program
The workshop will be held in conjunction with the 20th Conference of the Italian Association for Artificial Intelligence (AI*IA 2021), the 30 of November 2021
14:00 – Introduction
14:05 – Sessione 1: Collaborative and Social Robotics
14:10 Towards an ontological core for cognitively justified robots
Stefano Borgo, Roberta Ferrario, Claudio Masolo and Daniele Porello
14:25 The role of intelligent telepresence robots for continuously caring elderly people at home
Gloria Beraldo, Riccardo De Benedictis, Rami Reddy Devaram, Amedeo Cesta and Gabriella Cortellessa
14:40 Trust Metrics for Task Assignment in Cooperative Teams of Robots
Alberto Grillo, Carmine Recchiuto, Stefano Carpin and Antonio Sgorbissa
14:55 Cloud Services for Social Robots and Artificial Agents
Lucrezia Grassi, Carmine Recchiuto and Antonio Sgorbissa
15:10 A GAN-based Approach for Generating Culture-Aware Co-Speech Gestures
Ariel Gjaci, Carmine Recchiuto and Antonio Sgorbissa
15:25 – Break
15:30 – Session 2: Robot Planning and Learning
15:35 Multi-robot Sanitization of Railway Stations Based on Deep Q-Learning
Riccardo Caccavale, Vincenzo Calà, Mirko Ermini, Alberto Finzi, Vincenzo Lippiello and Fabrizio Tavano
15:50 A first approach to AGI-based Robot Task Planning
Michele Thiella, Elisa Tosello and Enrico Pagello
16:05 Exploiting Different Levels of Abstractions for Sample Efficient Reinforcement Learning
Roberto Cipollone, Giuseppe De Giacomo, Marco Favorito, Luca Iocchi and Fabio Patrizi
16:20 Learning environment properties in Partially Observable Monte Carlo Planning
Maddalena Zuccotto, Alberto Castellini, Marco Piccinelli, Enrico Marchesini and Alessandro Farinelli
16:35 – Break
16:40 – Session 3: Mobile Robotics
16:45 Predicting Performance of SLAM Algorithms
Matteo Luperto, Valerio Castelli, Fabio Bonsignorio and Francesco Amigoni
17:00 People-aware navigation: AI-driven approaches to enhance the robot’s navigation capabilities
Gloria Beraldo, Alberto Bacchin and Emanuele Menegatti
17:15 – Session 4: Keynote
17:15 Safe Reinforcement Learning for Intelligent Robotic Systems
Alessandro Farinelli
Intelligent Robotic Systems are a critical asset in several application scenarios, ranging from agile manufacturing, to environmental monitoring and logistics. A crucial element for Intelligent Robotic Systems to be successfully deployed in such scenarios is the ability to adapt their behaviours to changes in the operational environments, and Reinforcement Learning is a widely used approach to achieve this. In the last years, Reinforcement Learning (and Deep RL) achieved ground-breaking successes in several scenarios (e.g., Games and Video-Games). However, the adoption of RL techniques for robotics is still challenging. In this talk we will consider two key aspects related to RL for Intelligent Robotic Systems. Specifically, we will focus on formal verification approaches for Deep RL, describing a novel approach (i.e., ProVe) that is based on interval algebra and that is designed to verify behavioural properties of a DRL agent Moreover, we will present an approach for identifying and shielding unexpected decisions in Partially Observable Monte-Carlo Planning. This approach is based on Satisfiability Modulo Theory (SMT) and is designed to analyse POMCP policies by inspecting their traces. For both aspects we will present recent results, current challenges and future directions, highlighting application scenarios where these techniques can have a key impact.