Results 1 - 10
of
25
Sensory channel grouping and structure from uninterpreted sensor data
- in 2004 NASA/DoD Conference on Evolvable Hardware
, 2004
"... In this paper we focus on the problem of making a model of the sensory apparatus from raw uninterpreted sensory data as defined by Pierce and Kuipers (Artificial Intelligence 92:169-227, 1997). The method relies on generic properties of the agent’s world such as piecewise smooth effects of movement ..."
Abstract
-
Cited by 37 (16 self)
- Add to MetaCart
In this paper we focus on the problem of making a model of the sensory apparatus from raw uninterpreted sensory data as defined by Pierce and Kuipers (Artificial Intelligence 92:169-227, 1997). The method relies on generic properties of the agent’s world such as piecewise smooth effects of movement on sensory features. We extend a previously described algorithm with an information-theoretic distance metric that can find informational structure not found by the original algorithm. We also use the method to create metric projections of the sensory and motor systems of a robot. Data from a real robot show that the metric projections for example can be used to distinguish the vision sensors from all other sensors and also to find their functional layout. Finally we present an application of the method where the real layout of the vision sensors is found from scrambled vision data. 1.
Organization of the information flow in the perception-action loop of evolved agents
- In 2004 NASA/DoD Conference on Evolvable Hardware, 2004. Proceedings
, 2004
"... Sensor evolution in nature aims at improving the ac-quisition of information from the environment and is in-timately related with selection pressure towards adaptiv-ity and robustness. Recent work in the area aims at study-ing the perception-action loop in a formalized information-theoretic manner. ..."
Abstract
-
Cited by 32 (18 self)
- Add to MetaCart
(Show Context)
Sensor evolution in nature aims at improving the ac-quisition of information from the environment and is in-timately related with selection pressure towards adaptiv-ity and robustness. Recent work in the area aims at study-ing the perception-action loop in a formalized information-theoretic manner. This paves the way towards a principled and general understanding of the mechanisms guiding the evolution of sensors in nature and provides insights into the design of mechanisms of artificial sensor evolution. In our paper we study the perception-action loop of agents. We evolve finite-state automata as agent controllers to solve an information acquisition task in a simple vir-tual world and study how the information flow is organized by evolution. Our analysis of the evolved automata and the information flow provides insight into how evolution orga-nizes sensoric information acquisition, memory, processing and action selection. In addition, the results are compared to ideal information extraction schemes following from the Information Bottleneck principle. 1.
Tracking Information Flow through the Environment: Simple Cases of Stigmergy
- Artificial Life IX: Proceedings of the Ninth International Conference on the Simulation and Synthesis of Living Systems
, 2004
"... Recent work in sensor evolution aims at studying the perception-action loop in a formalized information-theoretic manner. By treating sensors as extracting information and actuators as having the capability to “imprint ” information on the environment we can view agents as creating, maintaining and ..."
Abstract
-
Cited by 28 (6 self)
- Add to MetaCart
(Show Context)
Recent work in sensor evolution aims at studying the perception-action loop in a formalized information-theoretic manner. By treating sensors as extracting information and actuators as having the capability to “imprint ” information on the environment we can view agents as creating, maintaining and making use of various information flows. In our paper we study the perception-action loop of agents using Shannon information flows. We use information theory to track and reveal the important relationships between agents and their environment. For example, we provide an information-theoretic characterization of stigmergy and evolve finite-state automata as agent controllers to engage in stigmergic communication. Our analysis of the evolved automata and the information flow provides insight into how evolution organizes sensoric information acquisition, implicit internal and external memory, processing and action selection. 1
Relevant information in optimized persistence vs. progeny strategies
- Artificial Life X: Proceedings of The 10th International Conference on the Simulation and Synthesis of Living Systems, Bloomington IN
, 2006
"... Identifying and utilizing information is central to reproductive success. We study a scenario where a multicellular colony has to trade-off between utility of strategies for investment in persistence or progeny and the (Shannon-type) relevant information necessary to realize these strategies. We dev ..."
Abstract
-
Cited by 23 (14 self)
- Add to MetaCart
(Show Context)
Identifying and utilizing information is central to reproductive success. We study a scenario where a multicellular colony has to trade-off between utility of strategies for investment in persistence or progeny and the (Shannon-type) relevant information necessary to realize these strategies. We develop a general approach to treat such problems that involve iterated games where utility is determined by iterated play of a strategy and where, in turn, informational processing constraints limit the possible strategies.
Information theory of decisions and actions
, 2010
"... The perception-action cycle is often defined as “the circular flow of information between an organism and its environment in the course of a sensory guided sequence of actions towards a goal ” (Fuster 2001, 2006). The question we address in this paper is in what sense this “flow of information ” can ..."
Abstract
-
Cited by 20 (6 self)
- Add to MetaCart
(Show Context)
The perception-action cycle is often defined as “the circular flow of information between an organism and its environment in the course of a sensory guided sequence of actions towards a goal ” (Fuster 2001, 2006). The question we address in this paper is in what sense this “flow of information ” can be described by Shannon’s measures of information introduced in his mathematical theory of communication. We provide an affirmative answer to this question using an intriguing analogy between Shannon’s classical model of communication and the Perception-Action-Cycle. In particular, decision and action sequences turn out to be directly analogous to codes in communication, and their complexity — the minimal number of (binary) decisions required for reaching a goal — directly bounded by information measures, as in communication. This analogy allows us to extend the standard Reinforcement Learning framework. The latter considers the future expected reward in the course of a behaviour sequence towards a goal (value-to-go). Here, we additionally incorporate a measure of information associated with this sequence: the cumulated information processing cost or bandwidth required to specify the future decision and action sequence (information-to-go). Using a graphical model, we derive a recursive Bellman optimality equation for information measures, in analogy to Reinforcement Learning; from this, we obtain new algorithms for calculating the optimal trade-off between the value-to-go and the required information-to-go, unifying the ideas behind the Bellman and the Blahut-Arimoto iterations. This trade-off between value-to-go and information-togo provides a complete analogy with the compression-distortion trade-off in source coding. The present new formulation connects seemingly unrelated optimization problems. The algorithm is demonstrated on grid world examples.
Meaningful Information, Sensor Evolution, and the Temporal Horizon of Embodied Organisms
- IN ARTIFICIAL LIFE VIII
, 2002
"... We survey and outline how an agent-centered, information-theoretic approach to meaningful information extending classical Shannon information theory by means of utility measures relevant for the goals of particular agents can be applied to sensor evolution for real and constructed organisms. F ..."
Abstract
-
Cited by 16 (10 self)
- Add to MetaCart
We survey and outline how an agent-centered, information-theoretic approach to meaningful information extending classical Shannon information theory by means of utility measures relevant for the goals of particular agents can be applied to sensor evolution for real and constructed organisms. Furthermore, we discuss the relationship of this approach to the programme of freeing artificial life and robotic systems from reactivity, by describing useful types of information with broader temporal horizon, for signaling, communication, affective grounding, two-process learning, individual learning, imitation and social learning, and episodic experiential information (memories, narrative, and culturally transmitted information).
Sensor adaptation and development in robots by entropy maximization of sensory data
- In Proceedings of the 6th IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA-2005
"... Abstract — A method is presented for adapting the sensors of a robot to the statistical structure of its current environment. This enables the robot to compress incoming sensory information and to find informational relationships between sensors. The method is applied to creating sensoritopic maps o ..."
Abstract
-
Cited by 14 (5 self)
- Add to MetaCart
(Show Context)
Abstract — A method is presented for adapting the sensors of a robot to the statistical structure of its current environment. This enables the robot to compress incoming sensory information and to find informational relationships between sensors. The method is applied to creating sensoritopic maps of the informational relationships of the sensors of a developing robot, where the informational distance between sensors is computed using information theory and adaptive binning. The adaptive binning method constantly estimates the probability distribution of the latest inputs to maximize the entropy in each individual sensor, while conserving the correlations between different sensors. Results from simulations and robotic experiments with visual sensors show how adaptive binning of the sensory data helps the system to discover structure not found by ordinary binning. This enables the developing perceptual system of the robot to be more adapted to the particular embodiment of the robot and the environment. Index Terms — Ontogenetic robotics, sensory systems, entropy maximization
Evaluating Team Performance at the Edge of Chaos
- RoboCup 2003: Robot Soccer World Cup VII, LNCS 3020, 89–101
, 2004
"... Abstract. We introduce a concise approach to teamwork evaluation on multiple levels — dealing with agent’s behaviour spread and multi-agent coordination potential, and abstracting away the team decision process. The presented quantitative information-theoretic methods measure behavioural and epistem ..."
Abstract
-
Cited by 13 (8 self)
- Add to MetaCart
(Show Context)
Abstract. We introduce a concise approach to teamwork evaluation on multiple levels — dealing with agent’s behaviour spread and multi-agent coordination potential, and abstracting away the team decision process. The presented quantitative information-theoretic methods measure behavioural and epistemic entropy, and detect phase transitions — the edge of chaos — in team performance. The techniques clearly identify under-performing states, where a change in tactics may be warranted. This approach is a step towards a unified quantitative framework on behavioural and belief dynamics in complex multi-agent systems. 1
Digested information as an information theoretic motivation for social interaction
- Journal of Artificial Societies and Social Simulation
, 2011
"... Within a universal agent-world interaction framework, based on Information Theory and Causal Bayesian Networks, we demonstrate how every agent that needs to acquire relevant information in regard to its strategy selection will automatically inject part of this information back into the environment. ..."
Abstract
-
Cited by 11 (10 self)
- Add to MetaCart
Within a universal agent-world interaction framework, based on Information Theory and Causal Bayesian Networks, we demonstrate how every agent that needs to acquire relevant information in regard to its strategy selection will automatically inject part of this information back into the environment. We introduce the concept of “Digested Information ” which both quantifies, and explains this phenomenon. Based on the properties of digested information, especially the high density of relevant information in other agents actions, we outline how this could motivate the development of low level social interaction mechanisms, such as the ability to detect other agents.
The effects on visual information in a robot in environments with oriented contours
- Lund University Cognitive Studies
, 2004
"... For several decades experiments have been performed where animals have been reared in environments with orientationally restricted contours. The aim has been to nd out what e ects the visual eld has on the development of the visual system in the brain. In this paper we describe similar experiments p ..."
Abstract
-
Cited by 8 (3 self)
- Add to MetaCart
(Show Context)
For several decades experiments have been performed where animals have been reared in environments with orientationally restricted contours. The aim has been to nd out what e ects the visual eld has on the development of the visual system in the brain. In this paper we describe similar experiments performed with a robot acting in an environment with only vertical contours and compare the results with the same robot in an ordinary ofce environment. Using metric projections of the informational distances between sensors it is shown that all visual sensors in the same vertical column are clustered together in the environment with only vertical contours. We also show how the informational structure of the sensors unfold when the robot moves from the environment with oriented contours to a normal environment. 1.
