| 1. |
- Biro, Zoltan, et al.
(författare)
-
Evolution of visually-guided approach behaviour in recurrent artificial neural network robot controllers
- 1998
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- Analysis of internal structures of embodied and situated agents may provide insights into the mechanisms underlying adaptive behaviour. This paper is concerned with the evolution and analysis of visually-guided approach behaviour in a simulated robotic agent controlled by a recurrent artificial neural network, whose connection weights have been evolved using evolutionary algorithms. Analysis of the evolved behaviours and their network-internal mechanisms reveals a behavioural structure and organization resembling a Brooksian subsumption architecture. The task decomposition, as well as the resulting individual behaviours and their integration, however, are realized as network-internal state space dynamics, evolved in the course of agent-environment interaction, i.e. with a minimum of designer intervention.
|
|
| 2. |
- Niklasson, Lars, et al.
(författare)
-
Lärande Datorer : Utopi eller Verklighet?
- 1996
-
Rapport (populärvet., debatt m.m.)abstract
- Denna populärvetenskapliga rapport ger en kort introduktion till självlärande artificiella neurala nätverk, samt sätter dem i relation till den science fiction-version som ges på TV och film.
|
|
| 3. |
- Sharkey, Noel E., et al.
(författare)
-
A consideration of the biological and psychological foundations of autonomous robotics
- 1998
-
Ingår i: Connection science (Print). - Skövde : University of Skövde. - 0954-0091 .- 1360-0494. ; 10:3-4, s. 361-391
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- The new wave of robotics aims to provide robots with the capacity to learn, develop and evolve in interaction with their environments using biologically inspired techniques. This work is placed in perspective by considering its biological and psychological basis with reference to some of the grand theorists of living systems. In particular, we examine what it means to have a body by outlining theories of the mechanisms of bodily integration in multicellular organisms and their means of solidarity with the environment. We consider the implications of not having a living body for current ideas on robot learning, evolution, and cognition and issue words of caution about wishful attributions that can smuggle more into observations of robot behaviour than is scientifically supportable. To round off the arguments we take an obligatory swipe at ungrounded artificial intelligence but quickly move on to assess physical grounding and embodiment in terms of the rooted cognition of the living.
|
|
| 4. |
- Sharkey, Noel E., et al.
(författare)
-
Life, Mind and Robots : The Ins and Outs of Embodied Cognition
- 1999
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- Many believe that the major problem facing traditional artificial intelligence (and the functional theory of mind) is how to connect intelligence to the outside world. Some turned to robotic functionalism and a hybrid response, that attempts to rescue symbolic functionalism by grounding the symbol system with a connectionist hook to the world. Others turned to an alternative approach, embodied cognition, that emerged from an older tradition in biology, ethology, and behavioural modelling. Both approaches are contrasted here before a detailed exploration of embodiment is conducted. In particular we ask whether strong embodiment is possible for robotics, i.e. are robot "minds'' similar to animal minds, or is the role of robotics to provide a tool for scientific exploration, a weak embodiment? We define two types of embodiment, Loebian and Uexküllian, that express two different views of the relation between body, mind and behaviour. It is argued that strong embodiment, either Loebian or Uexküllian, is not possible for present day robotics. However, weak embodiment is still a useful way forward.
|
|
| 5. |
- Ziemke, Tom
(författare)
-
Adaptive Behavior in Autonomous Agents
- 1998
-
Ingår i: Presence - Teleoperators and Virtual Environments. - Skövde : University of Skövde. - 1054-7460 .- 1531-3263. ; 7:6, s. 564-587
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- This paper gives an overview of the bottom-up approach to artificial intelligence (AI), commonly referred to as behavior-oriented AI. The behavior-oriented approach, with its focus on the interaction between autonomous agents and their environments, is introduced by contrasting it with the traditional approach of knowledge-based AI. Different notions of autonomy are discussed, and key problems of generating adaptive and complex behavior are identified. A number of techniques for the generation of behavior are introduced and evaluated regarding their potential for realizing different aspects of autonomy as well as adaptivity and complexity of behavior. It is concluded that in order to realize truly autonomous and intelligent agents, the behavior-oriented approach will have to focus even more on life-like qualities in both agents and environments.
|
|
| 6. |
- Ziemke, Tom, et al.
(författare)
-
Connectionist Models for the Detection of Oil Spills from Doppler Radar Imagery
- 1995
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- This paper reports on the results of a project investigating the potential of applying artificial neural networks to the problem of detecting oil spills on basis of the radar backscatter signals from a sea clutter environment illuminated by a Doppler radar. Recurrent backpropagation models which were found to exhibit satisfactory performance, superior to that of feed-forward networks, are discussed and analysed in particular.
|
|
| 7. |
- Ziemke, Tom, et al.
(författare)
-
Oil Spill Detection : A Case Study of Recurrent Artificial Neural Networks
- 1997
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- This paper summarizes and analyzes the results of a case study of artificial neural networks for the detection of oil spills from radar imagery, which has been carried as a joint project between the Connectionist Research Group, University of Skövde, and Ericsson Microwave Systems AB, Mölndal, Sweden.
|
|
| 8. |
- Ziemke, Tom, et al.
(författare)
-
Oil Spill Detection from Doppler Radar Imagery using Artificial Neural Networks
- 1995
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- This paper reports on results of an ongoing project investigating the application of artificial neural networks (ANNs) to the classification/ cartography of sea clutter environments, and in particular the detection of oil spills, on the basis of their radar backscatter signals.
|
|
| 9. |
- Ziemke, Tom
(författare)
-
Radar Image Segmentation using Recurrent Artificial Neural Networks
- 1996
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- This paper discusses the application of artificial neural networks to the segmentation of Doppler radar images, in particular the detection of oil spills within sea environments, based on a classification of radar backscatter signals. Best results have been achieved with recurrent backpropagation networks of an architecture similar to that of Elman's Simple Recurrent Network. The recurrent networks are shown to be very robust to variations in both sea state (weather conditions) as well as illumination distance, and their performance is analysed in further detail.
|
|
| 10. |
- Ziemke, Tom
(författare)
-
Radar Image Segmentation using Second-Order Recurrent Networks
- 1996
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- A second-order recurrent artificial neural network architecture for the segmentation and integration of radar images is introduced in this paper. This architecture consists of two sub-networks: a function network that classifies radar measurements into four different categories of objects in sea environments (water, oil spills, land and boats), and a context network that dynamically computes the function network's input weights. It is shown that this mechanism allows networks to learn to solve the task through a dynamic adaptation of their weighting of different radar measurements.behaviour.
|
|
| 11. |
- Ziemke, Tom
(författare)
-
Radar Image Segmentation using Self-Adapting Recurrent Networks
- 1997
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- This paper presents a novel approach to the segmentation and integration of (radar) images using a second-order recurrent artificial neural network architecture consisting of two sub- networks: a function network that classifies radar measurements into four different categories of objects in sea environments (water, oil spills, land and boats), and a context network that dynamically computes the function network's input weights. It is shown that in experiments (using simulated radar images) this mechanism outperforms conventional artificial neural networks since it allows the network to learn to solve the task through a dynamic adaptation of its classification function based on its internal state closely reflecting the current context.
|
|
| 12. |
- Ziemke, Tom
(författare)
-
Recurrent Artficial Neural Networks for the Detection of Oil Spills from Doppler Radar Imagery
- 1995
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- This paper discusses the application of artificial neural networks (ANNs) to the detection of oil spills in sea clutter environments from the classification of radar backscatter signals. A comparison and evaluation of different network architectures regarding reliability of dection and robustness to varying sea states/wind conditions shows that for this problem best results are achieved with a recurrent architecture similar to that of Elman's SRN.
|
|
| 13. |
- Ziemke, Tom
(författare)
-
Remembering how to behave : Recurrent neural networks for adaptive robot behavior
- 1999
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- This paper discusses the use of recurrent neural networks for control of and learning in robots and autonomous agents. In particular the use of feedback in both first- and higher-order recurrent network architectures for the realization of adaptive robot behavior is investigated. Two experiments, in which controller network weights are evolved to solve tasks requiring robots to exhibit context- or state-dependent behavior, are used to demonstrate and analyze different recurrent control architectures.
|
|
| 14. |
- Ziemke, Tom
(författare)
-
Rethinking Grounding
- 1999
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- The grounding problem is, generally speaking, the problem of causally connecting an artificial agent with its environment such that the agent's (internal) mechanisms and behaviour can be intrinsic and meaningful to itself, rather than dependent on an external designer or observer. This paper briefly reviews Searle's and Harnad's analyses of the grounding problem are and evaluates cognitivist and enactivist approaches to solving it. It is argued that, although the two categories of grounding approaches differ in their nature and the problems they have to face, both, so far, fail to provide fully grounded systems. Further it is argued here that the reason the problem is somewhat underestimated lies in the notions of situatedness and embodiment in modern AI, which goes beyond purely computational systems, but fails to acknowledge the historically grounded nature of the relation between living systems and their environments.
|
|
| 15. |
- Ziemke, Tom
(författare)
-
The 'Environmental Puppeteer' Revisited : A Connectionist Perspective on 'Autonomy'
- 1997
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- Today's `autonomous´robots only have very limited autonomy and are in fact very much under the control of the `environmental puppeteer', i.e their behaviour is determined, via virtual strings, by environmental conditions. Hence, it has been stated as the goal of modern scientific robotics to "cut the strings and give the robot its autonomy''. Different notions of autonomy in artefacts and living systems are examined in this paper, and different aspects/dimensions of autonomy are identified and illustrated with examples from connectionist robot control. A connectionist architecture is introduced that aims to increase robotic autonomy through integration of connectionist self-organisation/learning with the enactive view of structural coupling between environment and agent. In the resulting robot control architecture it is the environment that is pulling the strings, but the agent that develops them and dynamically decides which of them to use in a particular situation. Hence, the notion of autonomy advocated here is not `independence of environment' (a `freedom' most artefacts have), but rather an agent's capacity to actively embed itself in its environment and flexibly utilize it as a resource.
|
|
| 16. |
- Ziemke, Tom
(författare)
-
Towards Adaptive Behaviour System Integration using Connectionist Infinite State Automata
- 1996
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- A higher order recurrent connectionist architecture for adaptive control of autonomous robots is introduced in this paper. This architecture, inspired by Pollack's Sequential Cascaded Network, consists of two sub-networks: a function network for the coupling between sensory inputs and motor outputs, and a context network, which dynamically adapts the function network in order to allow a flexible mapping from percepts to actions. The approach taken here is compared to dynamics and algorithmic approach to autonomous robot control, and it is argued that the above architecture allows an integration of (a) the complex structure and control typical for the algorithmic approach, (b) the capacity to utilize systematically continuous state spaces, and (c) the self- organizing learning capacity of connectionist systems with a simple, but powerful mechanism for context-dependent adaptation of behaviour.
|
|
| 17. |
- Ziemke, Tom
(författare)
-
Towards Adaptive Perception in Autonomous Robots using Second-Order Recurrent Networks
- 1996
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- In this paper a higher-order recurrent connectionist architecture is used for learning adaptive behaviour in an autonomous robot. This architecture consists of two sub-networks in a master-slave relationship: a function network for the coupling between sensory inputs and motor outputs, and a context network, which dynamically adapts the sensory input weights in order to allow a flexible, context-dependent mapping from percepts to actions. The capabilities of this architecture are demonstrated in a number of action selection experiments with a simulated Khepera robot, and it is argued that the general approach of generically dividing the overall control task between sequentially cascaded context and function learning offers a powerful mechanism for autonomous long- and short-term adaptation of behaviour.
|
|
| 18. |
- Ziemke, Tom
(författare)
-
Towards Autonomous Robot Control via Self-Adapting Recurrent Networks
- 1996
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- In this paper a higher-order recurrent connectionist architecture is used for learning adaptive behaviour in an autonomous robot. This architecture consists of two sub-networks in a master-slave relationship: a function network for the coupling between sensory inputs and motor outputs, and a context network, which dynamically adapts the sensory input weights in order to allow a flexible, context-dependent mapping from percepts to actions. The capabilities of this architecture are demonstrated in a number of action selection experiments with a simulated Khepera robot, and it is argued that the general approach of generically dividing the overall control task between sequentially cascaded context and function learning offers a powerful mechanism for autonomous long- and short-term adaptation of behaviour
|
|
| 19. |
- Åström, Emil, et al.
(författare)
-
Robot Navigation using the Connectionist Navigational Map
- 1997
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- The `grounding problem' poses the question of how the function and internal mechanisms of a machine, natural or artificial, can be intrinsic to the machine itself, i.e. independent of an external designer or observer. Searle's and Harnad's analyses of the grounding problem are briefly reviewed as well as different approaches to solving it, based on the cognitivist and the enactive paradigms in cognitive science. It is argued that, although the two categories of grounding approaches differ in their nature and the problems they have to face, both, so far, fail to provide fully grounded systems for similar reasons: Only isolated parts of systems are grounded, whereas other, essential, parts are left ungrounded. Hence, it is further argued that grounding should instead be understood and approached as radical bottom-up development of complete robotic agents in interaction with their environment.
|
|
