To improve robustness in object recognition, many artificial visual systems imitate the way in wh... more To improve robustness in object recognition, many artificial visual systems imitate the way in which the human visual cortex encodes object information as a hierarchical set of features. These systems are usually evaluated in terms of their ability to accurately categorize well-defined, unambiguous objects and scenes. In the real world, however, not all objects and scenes are presented clearly, with well-defined labels and interpretations. Visual illusions demonstrate a disparity between perception and objective reality, allowing psychophysicists to methodically manipulate stimuli and study our interpretation of the environment. One prominent effect, the Müller-Lyer illusion, is demonstrated when the perceived length of a line is contracted (or expanded) by the addition of arrowheads (or arrow-tails) to its ends. HMAX, a benchmark object recognition system, consistently produces a bias when classifying Müller-Lyer images. HMAX is a hierarchical, artificial neural network that imitates the "simple" and "complex" cell layers found in the visual ventral stream. In this study, we perform two experiments to explore the Müller-Lyer illusion in HMAX, asking: (1) How do simple vs. complex cell operations within HMAX affect illusory bias and precision? (2) How does varying the position of the figures in the input image affect classification using HMAX? In our first experiment, we assessed classification after traversing each layer of HMAX and found that in general, kernel operations performed by simple cells increase bias and uncertainty while max-pooling operations executed by complex cells decrease bias and uncertainty. In our second experiment, we increased variation in the positions of figures in the input images that reduced bias and uncertainty in HMAX. Our findings suggest that the Müller-Lyer illusion is exacerbated by the vulnerability of simple cell operations to positional fluctuations, but ameliorated by the robustness of complex cell responses to such variance. Citation: Zeman A, Obst O and Brooks KR (2014) Complex cells decrease errors for the Müller-Lyer illusion in a model of the visual ventral stream. Front. Comput. Neurosci. 8:112.
To aid the development of the robotic soccer simulation league teamRoboLog-2000, a method for the... more To aid the development of the robotic soccer simulation league teamRoboLog-2000, a method for the specification of multi-agent teams by statechartshas been introduced. The results in the last years competitions showedthat though the team was competitive, it did not behave adaptive in unknownsituations. The design of adaptive agents with this method is possible, butnot in a straightforward manner. The purpose of this paper is to extend theapproach by a more adaptive action selection mechanism and to facilitate amore ...
ABSTRACT Steering behaviors are a set of reactive algorithms used for navigating autonomous agent... more ABSTRACT Steering behaviors are a set of reactive algorithms used for navigating autonomous agents in their environment. Combinations of steering behaviors can be used to create complex, interesting and lifelike movement. However, special care has to be given to their arbitration. If done the wrong way, the arbitration can lead to suboptimal, undesired, or even catastrophic results in certain situations. This article presents a solution to these problems by introducing inverse steering behaviors (ISBs) for controlling physical agents. Inverse steering behaviors change the original concept of steering behaviors and facilitate improved arbitration between different options by using cost based heuristics. The approach is demonstrated on a soccer playing agent.
The selection of an appropriate competition structure is critical for both the success and credib... more The selection of an appropriate competition structure is critical for both the success and credibility of any competition, both real and simulated. In this paper, the automated parallelism offered by the RoboCup 2D simulation league is leveraged to conduct a 28,000 game round-robin between the top 8 teams from RoboCup 2012 and 2013. A proposed new competition structure is found to reduce variation from the resultant statistically significant team performance rankings by 75% and 67%, when compared to the actual competition results from RoboCup 2012 and 2013 respectively.
RoboLog Koblenz is participating in the 2D Simulated Soccer com-petition for the 6th time. In thi... more RoboLog Koblenz is participating in the 2D Simulated Soccer com-petition for the 6th time. In this paper we focus on two of the features we im-proved from last year to this year. To improve the goal shot behavior of the RoboLog agents we included a scoring policy learned from observing games from RoboCup03 and the SSIL. In addition a smart dribbling algorithm based on In-verse Steering Behaviors–an extension to steering behaviors–has been added to the agents.
This chapter discusses a top-down approach to modelling soccer knowledge, as it can be found in s... more This chapter discusses a top-down approach to modelling soccer knowledge, as it can be found in soccer theory books. The goal is to model soccer strategies and tactics in a way that they are usable for multiple robotic soccer leagues in the RoboCup. We investigate if and how soccer theory can be formalised such that specification and execution is possible. The advantage is clear: theory abstracts from hardware and from specific situations in different leagues. We introduce basic primitives compliant with the terminology known in soccer theory, discuss an example on an abstract level and formalise it. The formalisation of soccer presented here is appealing. It goes beyond the behaviour specification of soccer playing robots. For sports science a unified formal soccer theory might help to better understand and to formulate basic concepts in soccer. The possibility of the formalisation to develop computer programs which allow to simulate and to reason about soccer moves might also take sports science a step further.
The selection of an appropriate competition structure is critical for both the success and credib... more The selection of an appropriate competition structure is critical for both the success and credibility of any competition, both real and simulated. In this paper, the automated parallelism offered by the RoboCup 2D simulation league is leveraged to conduct a 28,000 game round-robin between the top 8 teams from RoboCup 2012 and 2013. A proposed new competition structure is found to reduce variation from the resultant statistically significant team performance rankings by 75% and 67%, when compared to the actual competition results from RoboCup 2012 and 2013 respectively.
ABSTRACT Background / Purpose: The Müller-Lyer (ML) illusion is where perceived line length is de... more ABSTRACT Background / Purpose: The Müller-Lyer (ML) illusion is where perceived line length is decreased by inward arrowheads, but is increased by outward arrowheads. Many theories have been put forward to explain the ML illusion, such as filtering properties of signal processing in primary visual areas (Bulatov et al 1997). Artificial models of the ventral visual processing stream provide us with the potential to isolate and test how exposure to different image sets affects classification performance. Main conclusion: We trained a feed-forward hierarchical model (Mutch & Lowe, 2008) to perform a dual category line length judgment task (short versus long) with over 90% accuracy. We trained the model using a control set of images that would capture features present in illusion stimuli. We then tested the system in its ability to judge relative line lengths for images in a control set versus images that induce the ML illusion in humans. In this way, we were able to isolate and observe the effect of exposure to different stimuli on illusion judgment in a simple-complex feed-forward network.
" During the last years, Robotic Soccer has become one of the most challenging r... more " During the last years, Robotic Soccer has become one of the most challenging research fields for multiagent systems (MAS). In RoboCup soccer, teams of autonomous agents have to cooperatively solve the problem of winning against another team of agents. There are different leagues to address a wide area of research problems. However, many of the solutions to these are also league-dependent. This publication contributes tools and techniques to create physical MAS in domains where each agent has insufficient ...
Information theory and the framework of information dynamics have been used to provide tools to c... more Information theory and the framework of information dynamics have been used to provide tools to characterise complex systems. In particular, we are interested in quantifying information storage, information modification and information transfer as characteristic elements of computation. Although these quantities are defined for autonomous dynamical systems, information dynamics can also help to get a "wholistic" understanding of input-driven systems such as neural networks. In this case, we do not distinguish between the system itself, and the effects the input has to the system. This may be desired in some cases, but it will change the questions we are able to answer, and is consequently an important consideration, for example, for biological systems which perform non-trivial computations and also retain a short-term memory of past inputs.Many other real world systems like cortical networks are also heavily input-driven, and application of tools designed for autonomous dynamic systems may not necessarily lead to intuitively interpretable results.
Steering behaviors are a set of reactive algorithms used for navigating autonomous agents in thei... more Steering behaviors are a set of reactive algorithms used for navigating autonomous agents in their environment. Combinations of steering behaviors can be used to create complex, interesting and lifelike movement. However, special care has to be given to their arbitration. If done the wrong way, the arbitration can lead to suboptimal, undesired, or even catastrophic results in certain situations.
Physically-realistic simulated environments are powerful platforms for enabling measurable, repli... more Physically-realistic simulated environments are powerful platforms for enabling measurable, replicable and statistically-robust investigation of complex robotic systems. Such environments are epitomised by the RoboCup simulation leagues, which have been successfully utilised to conduct massivelyparallel experiments in topics including: optimisation of bipedal locomotion, self-localisation from noisy perception data and planning complex multi-agent strategies without direct agent-to-agent communication.
To improve robustness in object recognition, many artificial visual systems imitate the way in wh... more To improve robustness in object recognition, many artificial visual systems imitate the way in which the human visual cortex encodes object information as a hierarchical set of features. These systems are usually evaluated in terms of their ability to accurately categorize well-defined, unambiguous objects and scenes. In the real world, however, not all objects and scenes are presented clearly, with well-defined labels and interpretations. Visual illusions demonstrate a disparity between perception and objective reality, allowing psychophysicists to methodically manipulate stimuli and study our interpretation of the environment. One prominent effect, the Müller-Lyer illusion, is demonstrated when the perceived length of a line is contracted (or expanded) by the addition of arrowheads (or arrow-tails) to its ends. HMAX, a benchmark object recognition system, consistently produces a bias when classifying Müller-Lyer images. HMAX is a hierarchical, artificial neural network that imitates the "simple" and "complex" cell layers found in the visual ventral stream. In this study, we perform two experiments to explore the Müller-Lyer illusion in HMAX, asking: (1) How do simple vs. complex cell operations within HMAX affect illusory bias and precision? (2) How does varying the position of the figures in the input image affect classification using HMAX? In our first experiment, we assessed classification after traversing each layer of HMAX and found that in general, kernel operations performed by simple cells increase bias and uncertainty while max-pooling operations executed by complex cells decrease bias and uncertainty. In our second experiment, we increased variation in the positions of figures in the input images that reduced bias and uncertainty in HMAX. Our findings suggest that the Müller-Lyer illusion is exacerbated by the vulnerability of simple cell operations to positional fluctuations, but ameliorated by the robustness of complex cell responses to such variance. Citation: Zeman A, Obst O and Brooks KR (2014) Complex cells decrease errors for the Müller-Lyer illusion in a model of the visual ventral stream. Front. Comput. Neurosci. 8:112.
To aid the development of the robotic soccer simulation league teamRoboLog-2000, a method for the... more To aid the development of the robotic soccer simulation league teamRoboLog-2000, a method for the specification of multi-agent teams by statechartshas been introduced. The results in the last years competitions showedthat though the team was competitive, it did not behave adaptive in unknownsituations. The design of adaptive agents with this method is possible, butnot in a straightforward manner. The purpose of this paper is to extend theapproach by a more adaptive action selection mechanism and to facilitate amore ...
ABSTRACT Steering behaviors are a set of reactive algorithms used for navigating autonomous agent... more ABSTRACT Steering behaviors are a set of reactive algorithms used for navigating autonomous agents in their environment. Combinations of steering behaviors can be used to create complex, interesting and lifelike movement. However, special care has to be given to their arbitration. If done the wrong way, the arbitration can lead to suboptimal, undesired, or even catastrophic results in certain situations. This article presents a solution to these problems by introducing inverse steering behaviors (ISBs) for controlling physical agents. Inverse steering behaviors change the original concept of steering behaviors and facilitate improved arbitration between different options by using cost based heuristics. The approach is demonstrated on a soccer playing agent.
The selection of an appropriate competition structure is critical for both the success and credib... more The selection of an appropriate competition structure is critical for both the success and credibility of any competition, both real and simulated. In this paper, the automated parallelism offered by the RoboCup 2D simulation league is leveraged to conduct a 28,000 game round-robin between the top 8 teams from RoboCup 2012 and 2013. A proposed new competition structure is found to reduce variation from the resultant statistically significant team performance rankings by 75% and 67%, when compared to the actual competition results from RoboCup 2012 and 2013 respectively.
RoboLog Koblenz is participating in the 2D Simulated Soccer com-petition for the 6th time. In thi... more RoboLog Koblenz is participating in the 2D Simulated Soccer com-petition for the 6th time. In this paper we focus on two of the features we im-proved from last year to this year. To improve the goal shot behavior of the RoboLog agents we included a scoring policy learned from observing games from RoboCup03 and the SSIL. In addition a smart dribbling algorithm based on In-verse Steering Behaviors–an extension to steering behaviors–has been added to the agents.
This chapter discusses a top-down approach to modelling soccer knowledge, as it can be found in s... more This chapter discusses a top-down approach to modelling soccer knowledge, as it can be found in soccer theory books. The goal is to model soccer strategies and tactics in a way that they are usable for multiple robotic soccer leagues in the RoboCup. We investigate if and how soccer theory can be formalised such that specification and execution is possible. The advantage is clear: theory abstracts from hardware and from specific situations in different leagues. We introduce basic primitives compliant with the terminology known in soccer theory, discuss an example on an abstract level and formalise it. The formalisation of soccer presented here is appealing. It goes beyond the behaviour specification of soccer playing robots. For sports science a unified formal soccer theory might help to better understand and to formulate basic concepts in soccer. The possibility of the formalisation to develop computer programs which allow to simulate and to reason about soccer moves might also take sports science a step further.
The selection of an appropriate competition structure is critical for both the success and credib... more The selection of an appropriate competition structure is critical for both the success and credibility of any competition, both real and simulated. In this paper, the automated parallelism offered by the RoboCup 2D simulation league is leveraged to conduct a 28,000 game round-robin between the top 8 teams from RoboCup 2012 and 2013. A proposed new competition structure is found to reduce variation from the resultant statistically significant team performance rankings by 75% and 67%, when compared to the actual competition results from RoboCup 2012 and 2013 respectively.
ABSTRACT Background / Purpose: The Müller-Lyer (ML) illusion is where perceived line length is de... more ABSTRACT Background / Purpose: The Müller-Lyer (ML) illusion is where perceived line length is decreased by inward arrowheads, but is increased by outward arrowheads. Many theories have been put forward to explain the ML illusion, such as filtering properties of signal processing in primary visual areas (Bulatov et al 1997). Artificial models of the ventral visual processing stream provide us with the potential to isolate and test how exposure to different image sets affects classification performance. Main conclusion: We trained a feed-forward hierarchical model (Mutch & Lowe, 2008) to perform a dual category line length judgment task (short versus long) with over 90% accuracy. We trained the model using a control set of images that would capture features present in illusion stimuli. We then tested the system in its ability to judge relative line lengths for images in a control set versus images that induce the ML illusion in humans. In this way, we were able to isolate and observe the effect of exposure to different stimuli on illusion judgment in a simple-complex feed-forward network.
" During the last years, Robotic Soccer has become one of the most challenging r... more " During the last years, Robotic Soccer has become one of the most challenging research fields for multiagent systems (MAS). In RoboCup soccer, teams of autonomous agents have to cooperatively solve the problem of winning against another team of agents. There are different leagues to address a wide area of research problems. However, many of the solutions to these are also league-dependent. This publication contributes tools and techniques to create physical MAS in domains where each agent has insufficient ...
Information theory and the framework of information dynamics have been used to provide tools to c... more Information theory and the framework of information dynamics have been used to provide tools to characterise complex systems. In particular, we are interested in quantifying information storage, information modification and information transfer as characteristic elements of computation. Although these quantities are defined for autonomous dynamical systems, information dynamics can also help to get a "wholistic" understanding of input-driven systems such as neural networks. In this case, we do not distinguish between the system itself, and the effects the input has to the system. This may be desired in some cases, but it will change the questions we are able to answer, and is consequently an important consideration, for example, for biological systems which perform non-trivial computations and also retain a short-term memory of past inputs.Many other real world systems like cortical networks are also heavily input-driven, and application of tools designed for autonomous dynamic systems may not necessarily lead to intuitively interpretable results.
Steering behaviors are a set of reactive algorithms used for navigating autonomous agents in thei... more Steering behaviors are a set of reactive algorithms used for navigating autonomous agents in their environment. Combinations of steering behaviors can be used to create complex, interesting and lifelike movement. However, special care has to be given to their arbitration. If done the wrong way, the arbitration can lead to suboptimal, undesired, or even catastrophic results in certain situations.
Physically-realistic simulated environments are powerful platforms for enabling measurable, repli... more Physically-realistic simulated environments are powerful platforms for enabling measurable, replicable and statistically-robust investigation of complex robotic systems. Such environments are epitomised by the RoboCup simulation leagues, which have been successfully utilised to conduct massivelyparallel experiments in topics including: optimisation of bipedal locomotion, self-localisation from noisy perception data and planning complex multi-agent strategies without direct agent-to-agent communication.
Uploads
Papers by Oliver Obst