Meet Casa Agevole, a built in home in Fondazione Santa Lucia, Rome.


Designed by architect Fabrizio Vescovo, this 60m2 house includes several rooms -dinne room, kitchen, two bathrooms, two dorms and a main room- and has been designed to allow a person driving a wheelchair to move inside via a millimetric planning of the layout of the different elements.

This house have been deployed as a testing place for assistive technologies for projects in cooperation with FSL and it has already been successfully used in several EU projects. At the moment, it includes several ultrasonic localization sensors, a zigbee sensor network and a KNX-EIB installation, all connected to a gateway PC.

Eran Gat proposed one of the best known and most popular approaches to hybrid control: the Three Tier Architecture (3T) (Kortenkamp, 1998). As most hybrid control paradigms, 3T has a behavior layer, a sequencer and a deliberative layer. In 3T, algorithms are split into three categories: no memory, state-reflecting memory or state-based prediction alforithms, from more reactive to more deliberative components. Their function is the following:

-Memoriless algorithms inhabit the control components (skills)
-Memory-based algorithms inhabit the sequencer
-Predictive algorithms inhabit the deliberator

The main differences between 3T implementations lies in who really rules the system: reactive or deliberative layer (sequencer is always arbitrating :P). Dad, mom and kid in any combination! :D:D

Autonomous navigation initially followed the so called sense-plan-act scheme (SPA) [Albus91], that work with a model of the environment. SPA has some well known drawbacks like strong dependence on a correct model of the environment and high latency. Reactive control architectures [Brooks86], instead, create simple behaviours by coupling sensor readings and actions and complex ones by combining several basic behaviours running concurrently. Reactive behaviours are fast, quite robust against sensor errors and noise and can easily adapt to changes in hardware or tasks. Yet, emergent behaviours are unpredictable, not necessarily efficient and prone to fall into local traps. Hybrid schemes like the well known 3T control architecture [Bonasso97] solve the aforementioned problems by combining both reactive and deliberative paradigms to achieve the best possible performance.