04b Atto di convegno in volume

Enforcing Constraints over Learned Policies via Nonlinear MPC: Application to the Pendubot

In recent years Reinforcement Learning (RL) has achieved remarkable results. Nonetheless RL algorithms prove to be unsuccessful in robotics applications where constraints satisfaction is involved, e.g. for safety. In this work we propose a control algorithm that allows to enforce constraints over a...
An online learning procedure for feedback linearization control without torque measurements

By exploiting an a priori estimate of the dynamic model of a manipulator, it is possible to command joint torques which ideally realize a Feedback Linearization (FL) controller. The exact cancellation may nevertheless not be achieved due to model uncertainties and possible errors in the estimation...
Cyber-attacks and threats for healthcare - A multi-layer thread analysis

Due to the advent of novel technologies and digital opportunities allowing to simplify user lives, healthcare is increasingly evolving towards digitalization. This represent a great opportunity on one side but it also exposes healthcare organizations to multiple threats (both digital and not) that...
V-DOOR: A Real-Time Virtual Dressing Room Application Using Oculus Rift

In recent years and with its accessibility, the use of online shopping for clothing has increased. Virtual Dressing Rooms (VDRs) represent an effective way to enact the ability to "try before buying, thus removing an important obstacle for online shopping. While most of the VDR tools that have been...
Two-Stage Technique for LTLf Synthesis Under LTL Assumptions

In synthesis, assumption are constraints on the environments that rule out certain environment behaviors. A key observation is that even if we consider system with LTLf goals on finite traces, assumptions need to be expressed considering infinite traces, using LTL on infinite traces, since the...
On Time-Optimal Control of Elastic Joints under Input Constraints

We highlight the equivalence between the motion of an elastic joint and the two-body problem in classical mechanics. Based on this observation, a change of coordinates is introduced that reduces the two-body problem to a pair of decoupled one-body problems. This allows to treat the rest-to-rest...
Detection and isolation of actuator faults and collisions for a flexible robot arm

This paper presents a unified approach to detection and isolation of both actuator faults and unexpected collisions for a two-link robot with a flexible forearm. The proposed approach is sensorless, i.e., no dedicated exteroceptive sensors are considered, and is based on the design of residuals to...
Learning Feedback Linearization Control Without Torque Measurements

Feedback Linearization (FL) allows the best control performance in executing a desired motion task when an accurate dynamic model of a fully actuated robot is available. However, due to residual parametric uncertainties and unmodeled dynamic effects, a complete cancellation of the nonlinear...
HRI Users' Studies in the Context of the SciRoc Challenge: Some Insights on Gender-Based Differences
Auto-SEIA: Simultaneous optimization of image processing and machine learning algorithms