The existence of cortical hierarchies has long since been established and the advantages of hierarchical encoding of sensor-motor data for control, have long been recognized. Less well understood are the developmental processes whereby such hierarchies are constructed and subsequently used. This paper presents a new algorithm for encoding sequential sensor and actuator data in a dynamic, hierarchical neural network that can grow to accommodate the length of the observed interactions. The algorithm uses a developmental robotics methodology as it extends the Constructivist Learning Architecture, a computational theory of infant cognitive development. This paper presents experimental data demonstrating how the extended algorithm goes beyond the original theory by supporting goal oriented control. The domain studied is the encoding and reproduction of tactile gestures in humanoid robots. In particular, we present results from using a Programming by Demonstration approach to encode a stroke gesture. Our results demonstrate how the novel encoding enables a Nao humanoid robot with a touch sensitive fingertip to successfully encode and reproduce a stroke gesture in the presence of perturbations from internal and external forces.

No abstract

Low-cost robots with a large number of degrees of freedom are becoming increasingly popular, nevertheless their programming is still a domain for experts. This paper introduces the Kouretes Motion Editor (KME), a freely-available interactive software tool for designing complex motion patterns on robots with many degrees of freedom using intuitive means.

The Human-Robot Cloud has previously been introduced as a framework for the creation of distributed, ondemand, reconfigurable human-machine cognitive systems [1]. These systems are made up of sensing, processing, and actuation components that are not limited to a specific type of application and potentially can be extended to multiple domains and may cover spatially smaller or larger areas. In this paper, we revisit the Human-Robot Cloud architecture and present its pilot deployment on the campus of NCSR Demokritos, a research institution in Greece. In particular, our concrete deployment aims to be demonstrated in three specific application scenarios; namely, Human-Aware Smart Buildings with Energy Optimization, Security and Surveillance, and Smart Tour Guide System. In this paper, we present in detail an example implementation of the Smart Buildings scenario: a real-world application with immediate benefits in energy optimization and energy savings. Environmentally sensitive issues, such as the ground-up development of energy efficient buildings or reducing the environmental impact of the existing infrastructure, has received much attention in the past. However, the traditionally offered solutions are central, nontransferable to other infrastructure, non-scalable and suffer from single points of failure. On the contrary, in this work, which is based on a specialization of the generic Human-Robot Cloud architecture, we attempt to move beyond the industrially available solutions to meet the requirements for scalable, reconfigurable and redistributable sensory, processing, and actuation units within buildings. A set of cameras, laser range finders, and other sensors, together with a number of processing and actuation elements, including face detection, expression recognition, and people trackers, are transformed to a prototypical reconfigurable distributed extended cognitive system, which can support multiple applications in the future.