Erol Sahin

Evolving Aggregation Behaviors in a Swarm of Robots

In this paper, we study aggregation in a swarm of simple robots, called s-bots, having the capability to self-organize and self- assemble to form a robotic system, called a swarm-bot. The aggregation process, observed in many biological systems, is of fundamental impor- tance since it is the prerequisite for other forms of cooperation that in- volve self-organization and self-assembling. We consider the problem of defining the control system for the swarm-bot using artificial evolution. The results obtained in a simulated 3D environment are presented and analyzed. They show that artificial evolution, exploiting the complex in- teractions among s-bots and between s-bots and the environment, is able to produce simple but general solutions to the aggregation problem.

Probabilistic aggregation strategies in swarm robotic systems

In this study, a systematic analysis of probabilistic aggregation strategies in swarm robotic systems is presented. A generic aggregation behavior is proposed as a combination of four basic behaviors: obstacle avoidance, approach, repel, and wait. The latter three basic behaviors are combined using a three-state finite state machine with two probabilistic transitions among them. Two different metrics were used to compare performance of strategies. Through systematic experiments, how the aggregation performance, as measured by these two metrics, change 1) with transition probabilities, 2) with number of simulation steps, and 3) with arena size, is studied.

Goal emulation and planning in perceptual space using learned affordances

In this paper, we show that through self-interaction and self-observation, an anthropomorphic robot equipped with a range camera can learn object affordances and use this knowledge for planning. In the first step of learning, the robot discovers commonalities in its action-effect experiences by discovering effect categories. Once the effect categories are discovered, in the second step, affordance predictors for each behavior are obtained by learning the mapping from the object features to the effect categories. After learning, the robot can make plans to achieve desired goals, emulate end states of demonstrated actions, monitor the plan execution and take corrective actions using the perceptual structures employed or discovered during learning. We argue that the learning system proposed shares crucial elements with the development of infants of 7-10 months age, who explore the environment and learn the dynamics of the objects through goal-free exploration. In addition, we discuss goal emulation and planning in relation to older infants with no symbolic inference capability and non-linguistic animals which utilize object affordances to make action plans.

SWARM-BOT: pattern formation in a swarm of self-assembling mobile robots

We introduce a new robotic system, called swarm-bot. The system consists of a swarm of mobile robots with the ability to connect to/disconnect from each other to self-assemble into different kinds of structures. First, we describe our vision and the goals of the project. Then we present preliminary results on the formation of patterns obtained from a grid-world simulation of the system.

The learning and use of traversability affordance using range images on a mobile robot

We are interested in how the concept of affordances can affect our view to autonomous robot control, and how the results obtained from autonomous robotics can be reflected back upon the discussion and studies on the concept of affordances. In this paper, we studied how a mobile robot, equipped with a 3D laser scanner, can learn to perceive the traversability affordance and use it to wander in a room tilled with spheres, cylinders and boxes. The results showed that after learning, the robot can wander around avoiding contact with non-traversable objects (i.e. boxes, upright cylinders, or lying cylinders in certain orientation), but moving over traversable objects (such as spheres, and lying cylinders in a rollable orientation with respect to the robot) rolling them out of its way. We have shown that for each action approximately 1% of the perceptual features were relevant to determine whether it is afforded or not and that these relevant features are positioned in certain regions of the range image. The experiments are conducted both using a physics-based simulator and on a real robot.

Evolving aggregation behaviors for swarm robotic systems: a systematic case study

When one attempts to use artificial evolution to develop behaviors for a swarm robotic system, he is faced with decisions to be made regarding the parameters of the evolution. In this paper, aggregation behavior is chosen as a case, where performance and scalability of aggregation behaviors of perceptron controllers that are evolved for a simulated swarm robotic system are systematically studied with different parameter settings. Four experiments are conducted varying some of the parameters, and rules of thumb are derived, which can be of guidance to the use of evolutionary methods to generate other swarm robotic behaviors.

Development of a visual object localization module for mobile robots

Reports preliminary results from the design and implementation of a visual object localization module for mobile robots. The module takes an object-based approach to visual processing and relies on a preprocessing step that segments objects from the image. By tracking the size and the eccentricity of the objects in the image while the robot is moving, the visual object localization module can determine the position of objects relative to the robot using the displacement obtained from its odometry. In localizing the objects, the module is designed to combine the results of two different techniques. The visual looming technique measures the distance to an object using the change in the size of the object on the image plane. This technique is to be complemented by a variant of the triangulation technique that can locate an object using the eccentricity of the object when viewed from two different points. The module-with the preprocessing algorithm-is being implemented to run in real-time on a mobile robot. Evaluation of the visual localization module is being done in an integrated system introduced in the article. The integrated system creates an environment for real-time evaluation of the module as well as other mapping and navigation algorithms for mobile robots.

Staged Development of Robot Skills: Behavior Formation, Affordance Learning and Imitation with Motionese

Inspired by infant development, we propose a three staged developmental framework for an anthropomorphic robot manipulator. In the first stage, the robot is initialized with a basic reach-and- enclose-on-contact movement capability, and discovers a set of behavior primitives by exploring its movement parameter space. In the next stage, the robot exercises the discovered behaviors on different objects, and learns the caused effects; effectively building a library of affordances and associated predictors. Finally, in the third stage, the learned structures and predictors are used to bootstrap complex imitation and action learning with the help of a cooperative tutor. The main contribution of this paper is the realization of an integrated developmental system where the structures emerging from the sensorimotor experience of an interacting real robot are used as the sole building blocks of the subsequent stages that generate increasingly more complex cognitive capabilities. The proposed framework includes a number of common features with infant sensorimotor development. Furthermore, the findings obtained from the self-exploration and motionese guided human-robot interaction experiments allow us to reason about the underlying mechanisms of simple-to-complex sensorimotor skill progression in human infants.

Curiosity-driven learning of traversability affordance on a mobile robot

The concept of affordances, as proposed by J.J. Gibson, refers to the relationship between the organism and its environment and has become popular in autonomous robot control. The learning of affordances in autonomous robots, however, typically requires a large set of training data obtained from the interactions of the robot with its environment. Therefore, the learning process is not only time-consuming, and costly but is also risky since some of the interactions may inflict damage on the robot. In this paper, we study the learning of traversability affordance on a mobile robot and investigate how the number of interactions required can be minimized with minimial degradation on the learning process. Specifically, we propose a two step learning process which consists of bootstrapping and curiosity-based learning phases. In the bootstrapping phase, a small set of initial interaction data are used to find the relevant perceptual features for the affordance, and a support vector machine (SVM) classifier is trained. In the curiosity-driven learning phase, a curiosity band around the decision hyperplane of the SVM is used to decide whether a given interaction opportunity is worth exploring or not. Specifically, if the output of the SVM for a given percept lies within curiosity band, indicating that the classifier is not so certain about the hypothesized effect of the interaction, the robot goes ahead with the interaction, and skips if not. Our studies within a physics-based robot simulator show that the robot can achieve better learning with the proposed curiosity-driven learning method for a fixed number of interactions. The results also show that, for optimum performance, there exists a minimum number of initial interactions to be used for bootstrapping. Finally, the trained classifier with the proposed learning method was also successfully tested on the real robot.

Modeling self-organized aggregation in swarm robotic systems

In this paper, we propose a model for the self-organized aggregation of a swarm of mobile robots. Specifically, we use a simple probabilistic finite state automata (PFSA) based aggregation behavior and analyze its performance using both a point-mass and a physics-based simulator and compare the results against the predictions of the model. The results show that the probabilistic model predictions match simulation results and PFSA-based aggregation behaviors with fixed probabilities are unable to generate scalable aggregations in low robot densities. Moreover, we show that the use of a leave probability that is inversely proportional to the square of the neighbor count (as an estimate of aggregate size) does not improve the scalability of the behavior.