A Scene-Based Episodic Memory System for a Simulated Autonomous Creature

A Scene-Based Episodic Memory System for a Simulated Autonomous Creature

Elisa C. Castro (Department of Computer Engineering and Industrial Automation, University of Campinas, Campinas, SP, Brazil) and Ricardo R. Gudwin (Department of Computer Engineering and Industrial Automation, University of Campinas, Campinas, SP, Brazil)
Copyright: © 2013 |Pages: 33
DOI: 10.4018/jse.2013010102
OnDemand PDF Download:
$37.50

Abstract

In this paper the authors present the development of a scene-based episodic memory module for the cognitive architecture controlling an autonomous virtual creature, in a simulated 3D environment. The scene-based episodic memory has the role of improving the creature’s navigation system, by evoking the objects to be considered in planning, according to episodic remembrance of earlier scenes testified by the creature where these objects were present in the past. They introduce the main background on human memory systems and episodic memory study, and provide the main ideas behind the experiment.
Article Preview

1. Introduction

Tasks such as navigation and planning (LaValle, 2006) have attracted the attention of many researchers in the field of autonomous mobile robots (Siegwart & Nourbakhsh, 2004; Ge & Lewis, 2006; Kolski, 2007), since a long time. Nevertheless, it seems that these issues still have a lot of open questions demanding original solutions under specific constraints. Research in the field of autonomous mobile robots is usually split into two main sub-fields. The first, called here hard robotics, deals with real robots, and is concerned mainly with real world problems, like e.g. noise interference, sensors and actuators and real world robotics tasks. The other subfield deals with simulated robots in simulated environments, and is more concerned with strategies, general algorithms, complexity issues and new techniques applied to the robotics domain. This second sub-field, called here soft robotics is more multi-disciplinary, sometimes running into other fields of research, like e.g. artificial life and cognitive science. In both the hard robotics and soft robotics sub-domains, an approach, which is usually called Cognitive Robotics (Clark & Grush, 1999; Christaller, 1999) tries to associate cognition to robot control. In some cases, this inspiration in cognition is more biological (Webb & Consi, 2001). In other cases, this inspiration is really toward the construction of humanoid robots (Asada et al., 2001).Sometimes, the robotics issue is abstracted, and the robot is treated simply like an agent (Worgotter et al., 2009). A general field of research, Cognitive Systems (Christensen et al., 2009) was created to deal exclusively with these ideas.

An important concept related to cognitive systems research is the concept of a Cognitive Architecture (Langley & Laird, 2009; Franklin et al., 1998). A cognitive architecture is usually a control system for a robot, which comprises a set of modules responsible for the implementation of cognitive capabilities in such control system. Cognitive architectures are mainly inspired by human neuro-cognitive and psychological abilities, where typical human cognitive tasks as perception, learning, memory, emotions, reasoning, decision-making, behavior, language, consciousness, etc. are in some way modeled and used as a source of inspiration in order to enhance the capabilities of autonomous mobile robots. In many situations, robots controlled by a cognitive architecture are called artificial creatures (Balkenius, 1995). Many of such cognitive abilities were reported as very useful in making smarter creatures. Abilities such as emotions, learning, language evolution, action selection and even consciousness, among others, have brought the performance of such creatures to an amazing level.

Nevertheless, there seems to be at least one of such cognitive abilities which has not been so widely explored so far. This ability is what we may refer from now on as episodic memory (Tulving, 2002). Making a historical evaluation on how new cognitive architectures for artificial creatures started to appear on the literature, and how their capabilities started to improve in the newer versions, we realize that the first reported creatures used to live only in the present, sensoring their surroundings and choosing their action based only on the current situation, while subsequent generations of architectures introduced further sophistications in behavior. Next generations of creatures enhanced that situation by living not only on the present, but also with an eye on the future, being able to make plans and create expectations. But few of them were able to refer to their past, just like we do as humans.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 8: 2 Issues (2017)
Volume 7: 2 Issues (2016)
Volume 6: 2 Issues (2015)
Volume 5: 2 Issues (2014)
Volume 4: 2 Issues (2013)
Volume 3: 2 Issues (2012)
Volume 2: 2 Issues (2011)
Volume 1: 2 Issues (2010)
View Complete Journal Contents Listing