| 1. |
- Froese, Tom, et al.
(författare)
-
Enactive artificial intelligence : Investigating the systemic organization of life and mind
- 2009
-
Ingår i: Artificial Intelligence. - : Elsevier. - 0004-3702 .- 1872-7921. ; 173:3-4, s. 466-500
-
Tidskriftsartikel (refereegranskat)abstract
- The embodied and situated approach to artificial intelligence (AI) has matured and become a viable alternative to traditional computationalist approaches with respect to the practical goal of building artificial agents, which can behave in a robust and flexible manner under changing real-world conditions. Nevertheless, some concerns have recently been raised with regard to the sufficiency of current embodied AI for advancing our scientific understanding of intentional agency. While from an engineering or computer science perspective this limitation might not be relevant, it is of course highly relevant for AI researchers striving to build accurate models of natural cognition. We argue that the biological foundations of enactive cognitive science can provide the conceptual tools that are needed to diagnose more clearly the shortcomings of current embodied AI. In particular, taking an enactive perspective points to the need for AI to take seriously the organismic roots of autonomous agency and sense-making. We identify two necessary systemic requirements, namely constitutive autonomy and adaptivity, which lead us to introduce two design principles of enactive AI. It is argued that the development of such enactive AI poses a significant challenge to current methodologies. However, it also provides a promising way of eventually overcoming the current limitations of embodied AI, especially in terms of providing fuller models of natural embodied cognition. Finally, some practical implications and examples of the two design principles of enactive AI are also discussed.
|
|
| 2. |
- Li, Jun
(författare)
-
Learning reactive behaviors with constructive neural networks in mobile robotics
- 2006
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- This thesis investigates a learning system for acquiring robot behaviors by mapping sensor information directly to motor actions. It addresses the integration of three learning paradigms, namely unsupervised learning (UL), supervised learning (SL), and reinforcement learning (RL). The approach is characterized by the use of constructive artificial neural networks (ANNs). The sensor-motor mappings acquired by the learning system form part of a tight "sense-learn-act" cycle, as opposed to "sense-plan-act", thus allowing the robot to learn concepts within its own sensorimotor experience while avoiding anthropomorphic bias.Novel techniques for robot learning using constructive radial basis function (RBF) networks are introduced. This leads to a self-organizing, incremental and local construction of the sensorimotor space for learning different behaviors with the same basic architecture, thus a great simplification of the engineering design process of the ANN's structure. Integration of the different learning paradigms takes place in a two-layer learning architecture.The lower layer with the UL and SL paradigms is used to quickly construct a controller for the required behavior. The upper layer with the RL paradigm is used for tuning and refining of the controller resulting from the lower layer (or a controller obtained from other prior knowledge) to further improve the robustness and performance of the behavior. Both layers apply constructive RBF networks, taking into account the different requirements of the respective learning paradigms.The learning system is verified by a number of experiments on a real robot. We begin our experiments with the lower layer together with a teaching-by-demonstration approach for acquiring different behaviors. The experimental results show that the lower layer can learn a wide range of robot behaviors, thus demonstrating the task non-specific nature of the architecture. We then demonstrate the necessity of the layered learning architecture for more complex behaviors by a docking behavior requiring precise positioning at a goal location. The results obtained show that learning with only the lower layer can not obtain robust performance and optimal trajectories, while learning with only the upper layer is impractical and even infeasible on the real robot due to the slow learning process of the RL paradigm. With layered learning, however, the upper layer is speeded up by bootstrapping from the learnedcontroller in the lower layer, and a robust and time-optimal controller can be obtained.
|
|
| 3. |
- Aktius, Malin, et al.
(författare)
-
A Behavior-Based Model of the Hydra, Phylum Cnidaria
- 2007
-
Ingår i: 9th European Conference, ECAL 2007. - Berlin, Heidelberg : Springer Berlin/Heidelberg. - 9783540749127 ; , s. 1024-1033
-
Konferensbidrag (refereegranskat)abstract
- Behavior-based artificial systems, e.g. mobile robots, are frequently designed using (various degrees and levels of) biology as inspiration, but rarely modeled based on actual quantitative empirical data. This paper presents a data-driven behavior-based model of a simple biological organism, the hydra. Four constituent behaviors were implemented in a simulated animal, and the overall behavior organization was accomplished using a colony-style architecture (CSA). The results indicate that the CSA, using a priority-based behavioral hierarchy suggested in the literature, can be used to model behavioral properties like latency, activation threshold, habituation, and duration of the individual behaviors of the hydra. Limitations of this behavior-based approach are also discussed.
|
|
| 4. |
- Andler, Sten F., et al.
(författare)
-
Information Fusion from Databases, Sensors and Simulations : A Collaborative Research Program
- 2005
-
Ingår i: Proceedings. - : IEEE Computer Society. - 0769523064 ; , s. 234-241
-
Konferensbidrag (refereegranskat)abstract
- This paper provides an overview of a collaborative research program in information fusion from databases, sensors and simulations. Information fusion entails the combination of data from multiple sources, to generate information that cannot be derived from the individual sources. This area is of strategic importance for industry and defense, as well as public administration areas such as health care, and needs to be pursued as an academic subject. A large number of industrial partners are supporting and participating in the development of the area. The paper describes the program’s general approach and main research areas, with a particular focus on the role of information fusion in systems development
|
|
| 5. |
- Billing, Erik, 1981-
(författare)
-
Cognition reversed : Robot learning from demonstration
- 2009
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The work presented in this thesis investigates techniques for learning from demonstration (LFD). LFD is a well established approach to robot learning, where a teacher demonstrates a behavior to a robot pupil. This thesis focuses on LFD where a human teacher demonstrates a behavior by controlling the robot via teleoperation. The robot should after demonstration be able to execute the demonstrated behavior under varying conditions. Several views on representation, recognition and learning of robot behavior are presented and discussed from a cognitive and computational perspective. LFD-related concepts such as behavior, goal, demonstration, and repetition are defined and analyzed, with focus on how bias is introduced by the use of behavior primitives. This analysis results in a formalism where LFD is described as transitions between information spaces. Assuming that the behavior recognition problem is partly solved, ways to deal with remaining ambiguities in the interpretation of a demonstration are proposed. A total of five algorithms for behavior recognition are proposed and evaluated, including the dynamic temporal difference algorithm Predictive Sequence Learning (PSL). PSL is model-free in the sense that it makes few assumptions of what is to be learned. One strength of PSL is that it can be used for both robot control and recognition of behavior. While many methods for behavior recognition are concerned with identifying invariants within a set of demonstrations, PSL takes a different approach by using purely predictive measures. This may be one way to reduce the need for bias in learning. PSL is, in its current form, subjected to combinatorial explosion as the input space grows, which makes it necessary to introduce some higher level coordination for learning of complex behaviors in real-world robots. The thesis also gives a broad introduction to computational models of the human brain, where a tight coupling between perception and action plays a central role. With the focus on generation of bias, typical features of existing attempts to explain humans' and other animals' ability to learn are presented and analyzed, from both a neurological and an information theoretic perspective. Based on this analysis, four requirements for implementing general learning ability in robots are proposed. These requirements provide guidance to how a coordinating structure around PSL and similar algorithms should be implemented in a model-free way.
|
|
| 6. |
|
|
| 7. |
|
|
| 8. |
- Boström, Henrik, et al.
(författare)
-
On the Definition of Information Fusion as a Field of Research
- 2007
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- A more precise definition of the field of information fusion can be of benefit to researchers within the field, who may use uch a definition when motivating their own work and evaluating the contribution of others. Moreover, it can enable researchers and practitioners outside the field to more easily relate their own work to the field and more easily understand the scope of the techniques and methods developed in the field. Previous definitions of information fusion are reviewed from that perspective, including definitions of data and sensor fusion, and their appropriateness as definitions for the entire research field are discussed. Based on strengths and weaknesses of existing definitions, a novel definition is proposed, which is argued to effectively fulfill the requirements that can be put on a definition of information fusion as a field of research.
|
|
| 9. |
- Buason, Gunnar, et al.
(författare)
-
Brains, Bodies and Beyond : Competitive Co-Evolution of Robot Controllers, Morphologies and Environments
- 2005
-
Ingår i: Genetic Programming and Evolvable Machines. - : Springer. - 1389-2576 .- 1573-7632. ; 6:1, s. 25-51
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents a series of simulation experiments that incrementally extend previous work on neural robot controllers in a predator-prey scenario, in particular the work of Floreano and Nolfi, and integrates it with ideas from work on the ‘co-evolution’ of robot morphologies and control systems. The aim of these experiments has been to further systematically investigate the tradeoffs and interdependencies between morphological parameters and behavioral strategies through a series of predator-prey experiments in which increasingly many aspects are subject to self-organization through competitive co-evolution. Motivated by the fact that, despite the emphasis of the interdependence of brain, body and environment in much recent research, the environment has actually received relatively little attention, the last set of experiments lets robots/species actively adapt their environments to their own needs, rather than just adapting themselves to a given environment.
|
|
| 10. |
- Federici, Diego, et al.
(författare)
-
Why are evolved developing organisms also fault-tolerant?
- 2006
-
Ingår i: FROM ANIMALS TO ANIMATS 9, PROCEEDINGS. - : Springer Berlin/Heidelberg. - 3540386084 ; , s. 449-460
-
Konferensbidrag (refereegranskat)abstract
- It has been suggested that evolving developmental programs instead of direct genotype-phenotype mappings may increase the scalability of Genetic Algorithms. Many of these Artificial Embryogeny (AE) models have been proposed and their evolutionary properties are being investigated. One of these properties concerns the fault-tolerance of at least a particular class of AE, which models the development of artificial multicellular organisms. It has been shown that such AE evolves designs capable of recovering phenotypic faults during development, even if fault-tolerance is not selected for during evolution. This type of adaptivity is clearly very interesting both for theoretical reasons and possible robotic applications. In this paper we provide empirical evidence collected from a multicellular AE model showing a subtle relationship between evolution and development. These results explain why developmental fault-tolerance necessarily emerges during evolution.
|
|
