A Perspective on Lifelong Open-Ended Learning Autonomy for Robotics through Cognitive Architectures.

This paper addresses the problem of achieving lifelong open-ended learning autonomy in robotics, and how different cognitive architectures provide functionalities that support it. To this end, we analyze a set of well-known cognitive architectures in the literature considering the different components they address and how they implement them. Among the main functionalities that are taken as relevant for lifelong open-ended learning autonomy are the fact that architectures must contemplate learning, and the availability of contextual memory systems, motivations or attention. Additionally, we try to establish which of them were actually applied to real robot scenarios. It transpires that in their current form, none of them are completely ready to address this challenge, but some of them do provide some indications on the paths to follow in some of the aspects they contemplate. It can be gleaned that for lifelong open-ended learning autonomy, motivational systems that allow finding domain-dependent goals from general internal drives, contextual long-term memory systems that all allow for associative learning and retrieval of knowledge, and robust learning systems would be the main components required. Nevertheless, other components, such as attention mechanisms or representation management systems, would greatly facilitate operation in complex domains.

An Approach for the Customized High-Dimensional Segmentation of Remote Sensing Hyperspectral Images.

This paper addresses three problems in the field of hyperspectral image segmentation: the fact that the way an image must be segmented is related to what the user requires and the application; the lack and cost of appropriately labeled reference images; and, finally, the information loss problem that arises in many algorithms when high dimensional images are projected onto lower dimensional spaces before starting the segmentation process. To address these issues, the Multi-Gradient based Cellular Automaton (MGCA) structure is proposed to segment multidimensional images without projecting them to lower dimensional spaces. The MGCA structure is coupled with an evolutionary algorithm (ECAS-II) in order to produce the transition rule sets required by MGCA segmenters. These sets are customized to specific segmentation needs as a function of a set of low dimensional training images in which the user expresses his segmentation requirements. Constructing high dimensional image segmenters from low dimensional training sets alleviates the problem of lack of labeled training images. These can be generated online based on a parametrization of the desired segmentation extracted from a set of examples. The strategy has been tested in experiments carried out using synthetic and real hyperspectral images, and it has been compared to state-of-the-art segmentation approaches over benchmark images in the area of remote sensing hyperspectral imaging.

Perceptual Generalization and Context in a Network Memory Inspired Long-Term Memory for Artificial Cognition.

In the framework of open-ended learning cognitive architectures for robots, this paper deals with the design of a Long-Term Memory (LTM) structure that can accommodate the progressive acquisition of experience-based decision capabilities, or what different authors call "automation" of what is learnt, as a complementary system to more common prospective functions. The LTM proposed here provides for a relational storage of knowledge nuggets given the form of artificial neural networks (ANNs) that is representative of the contexts in which they are relevant in a configural associative structure. It also addresses the problem of continuous perceptual spaces and the task- and context-related generalization or categorization of perceptions in an autonomous manner within the embodied sensorimotor apparatus of the robot. These issues are analyzed and a solution is proposed through the introduction of two new types of knowledge nuggets: P-nodes representing perceptual classes and C-nodes representing contexts. The approach is studied and its performance evaluated through its implementation and application to a real robotic experiment.

Open-Ended Learning: A Conceptual Framework Based on Representational Redescription.

Reinforcement learning (RL) aims at building a policy that maximizes a task-related reward within a given domain. When the domain is known, i.e., when its states, actions and reward are defined, Markov Decision Processes (MDPs) provide a convenient theoretical framework to formalize RL. But in an open-ended learning process, an agent or robot must solve an unbounded sequence of tasks that are not known in advance and the corresponding MDPs cannot be built at design time. This defines the main challenges of open-ended learning: how can the agent learn how to behave appropriately when the adequate states, actions and rewards representations are not given? In this paper, we propose a conceptual framework to address this question. We assume an agent endowed with low-level perception and action capabilities. This agent receives an external reward when it faces a task. It must discover the state and action representations that will let it cast the tasks as MDPs in order to solve them by RL. The relevance of the action or state representation is critical for the agent to learn efficiently. Considering that the agent starts with a low level, task-agnostic state and action spaces based on its low-level perception and action capabilities, we describe open-ended learning as the challenge of building the adequate representation of states and actions, i.e., of redescribing available representations. We suggest an iterative approach to this problem based on several successive Representational Redescription processes, and highlight the corresponding challenges in which intrinsic motivations play a key role.

A Framework for the Development of Context-Adaptable User Interfaces for Ubiquitous Computing Systems.

This paper addresses the problem of developing user interfaces for Ubiquitous Computing (UC) and Ambient Intelligence (AmI) systems. These kind of systems are expected to provide a natural user experience, considering interaction modalities adapted to the user abilities and preferences and using whatever interaction devices are present in the environment. These interaction devices are not necessarily known at design time. The task is quite complicated due to the variety of devices and technologies, and the diversity of scenarios, and it usually burdens the developer with the need to create many different UIs in order to consider the foreseeable user-environment combinations. Here, we propose an UI abstraction framework for UC and AmI systems that effectively improves the portability of those systems between different environments and for different users. It allows developers to design and implement a single UI capable of being deployed with different devices and modalities regardless the physical location.

UniDA: uniform device access framework for human interaction environments.

Human interaction environments (HIE) must be understood as any place where people carry out their daily life, including their work, family life, leisure and social life, interacting with technology to enhance or facilitate the experience. The integration of technology in these environments has been achieved in a disorderly and incompatible way, with devices operating in isolated islands with artificial edges delimited by the manufacturers. In this paper we are presenting the UniDA framework, an integral solution for the development of systems that require the integration and interoperation of devices and technologies in HIEs. It provides developers and installers with a uniform conceptual framework capable of modelling an HIE, together with a set of libraries, tools and devices to build distributed instrumentation networks with support for transparent integration of other technologies. A series of use case examples and a comparison to many of the existing technologies in the field has been included in order to show the benefits of using UniDA.