SSIR 2012 Abstracts


Full Papers
Paper Nr: 3
Title:

DISTRIBUTED TEAM FORMATION FOR HUMANOID ROBOT SOCCER

Authors:

Onuralp Ulusoy and Sanem Sariel-Talay

Abstract: In this paper, we propose an adaptive team formation strategy for humanoid robot soccer. The proposed strategy involves distributed cooperative decisions through both communication and observations. Two agent groups, namely defenders and attackers, are formed by a case-based group formation method. Attackers are formed for constructing an attacking formation around the ball and scoring a goal whenever possible while defenders are for blocking and constructing a defensive obstacle against the opponent team. Cooperative decisions are made using communication among team members. Distribution of agents on the field is ensured by Voronoi cell construction of each agent through observations in a distributed manner. Experiments are set in the RoboCup 3D Soccer Simulation League environment where our method is compared to earlier team formation methods. The results illustrate that a distributed Voronoi cell construction method combined with a case-based grouping algorithm outperforms the others. Furthermore, it has been shown that our method is also robust to communication failures.

Paper Nr: 4
Title:

MINIMALISTIC VISION-BASED COGNITIVE SLAM

Authors:

Mário Saleiro, J. M. F. Rodrigues and J. M. H. du Buf

Abstract: The interest in cognitive robotics is still increasing, a major goal being to create a system which can adapt to dynamic environments and which can learn from its own experiences. We present a new cognitive SLAM architecture, but one which is minimalistic in terms of sensors and memory. It employs only one camera with pan and tilt control and three memories, without additional sensors nor any odometry. Short-term memory is an egocentric map which holds information at close range at the actual robot position. Long-term memory is used for mapping the environment and registration of encountered objects. Object memory holds features of learned objects which are used as navigation landmarks and task targets. Saliency maps are used to sequentially focus important areas for object and obstacle detection, but also for selecting directions of movements. Reinforcement learning is used to consolidate or enfeeble environmental information in long-term memory. The system is able to achieve complex tasks by executing sequences of visuomotor actions, decisions being taken by goal-detection and goal-completion tasks. Experimental results show that the system is capable of executing tasks like localizing specific objects while building a map, after which it manages to return to the start position even when new obstacles have appeared.

Paper Nr: 8
Title:

LEARNING PEG-IN-HOLE ACTIONS WITH FLEXIBLE OBJECTS

Authors:

Leon Bodenhagen, Andreas R. Fugl, Morten Willatzen, Henrik G. Petersen and Norbert Krüger

Abstract: This paper presents a method for learning Peg-In-Hole actions with flexible objects. To learn the actions we parametrize the entire trajectory by a single point and use Kernel Density Estimation to reflect the different variations of the action and the object characteristics. The object is characterized by its elastic behaviour rather than geometric properties. Thereby an action learned for one object can be transferred to a new object that behaves similarly although it might have different elastic properties, dimensions and geometries. To bootstrap the learning mechanism, the system performs simulated actions and utilizes the detailed information obtained from the simulation environment. Subsequently Peg-In-Hole actions are tested successfully on the real life setup.

Paper Nr: 9
Title:

POSSESSED ROBOT: HOW TO FIND ORIGINAL NONVERBAL COMMUNICATION STYLE IN HUMAN-ROBOT INTERACTION

Authors:

Hirotaka Osawa and Michita Imai

Abstract: We propose an alternative approach called the Possessed Robot method to find each robot's unique communication strategies. In this approach, the human manipulator behaves as if she/he possesses the robot and finds the optimal communication strategies based on each robot's shape and modalities. We implement the Possessed Robot system (PoRoS) including a reconfigurable body robot, an easier manipulation system, and a recording system to evaluate the validity of our method. We evaluate a block-assembling task by PoRoS by turning on and off the modality of the robot's head. Subsequently, the robot's motion during player's motion significantly increases whereas the ratio of confirmatory behaviour significantly decreases in the head-fixed design. Based on the results, we find an example case for the optimal communication strategy in the head-fixed design. In this case, the robot leads the users and the user follows the robot as in the turn-taking communication style of the humanlike condition. This result shows the feasibility of the Possessed Robot method to make appropriate strategy adjustments based on the robot design.

Paper Nr: 11
Title:

REFLEXIVE COLLISION RESPONSE WITH VIRTUAL SKIN - Roadmap Planning Meets Reinforcement Learning

Authors:

Mikhail Frank, Alexander Förster and Jürgen Schmidhuber

Abstract: Prevalent approaches to motion synthesis for complex robots offer either the ability to build up knowledge of feasible actions through exploration, or the ability to react to a changing environment, but not both. This work proposes a simple integration of roadmap planning with reflexive collision response, which allows the roadmap representation to be transformed into a Markov Decision Process. Consequently, roadmap planning is extended to changing environments, and the adaptation of the map can be phrased as a reinforcement learning problem. An implementation of the reflexive collision response is provided, such that the reinforcement learning problem can be studied in an applied setting. The feasibility of the software is analyzed in terms of runtime performance, and its functionality is demonstrated on the iCub humanoid robot.

Paper Nr: 12
Title:

ADDRESSING THE LONG-TERM EVALUATION OF A TELEPRESENCE ROBOT FOR THE ELDERLY

Authors:

Amedeo Cesta, Gabriella Cortellessa, Andrea Orlandini and Lorenza Tiberio

Abstract: This paper presents aspects of an ongoing work for a long-term evaluation of a telepresence robot named GIRAFF, as a tool for facilitating interaction and support delivery to older people living at home. Most robotic systems are usually used for short periods of time and in laboratory settings, while this paper describes the challenges, both technological and related to the user evaluation that human-robot interaction should addressed in view of a real use of the technology for a long time span outside the laboratory. The work describes our experience in developing testing sites and in designing an evaluation plan to assess the potential of the GIRAFF platform for telepresence. We highlight open points related to the transition from a limited use in time (short term) to a significant period of time (long term). From a human-robot interaction perspective, we first introduce some results from the short term evaluation, obtained by interviewing 26 nurses as possible clients (people connecting to the robot) and 10 older adults as possible end users (people receiving visits through the robot). The paper describes then a complete evaluation plan designed for the long term assessment. From a technological point of view a set of mandatory “intelligent features” are taken into account that could enable a better real world deployment by inheriting capabilities form state-of-the-art autonomous intelligent robots.

Short Papers
Paper Nr: 5
Title:

EXPLORING INTERFACES IN A DISTRIBUTED COMPONENT-BASED PROGRAMMING FRAMEWORK FOR ROBOTICS

Authors:

A. C. Domínguez-Brito, F. J. Santana-Jorge, J. Cabrera-Gámez, J. D. Hernández-Sosa, J. Isern-González and E. Fernández-Perdomo

Abstract: CoolBOT is a C++ distributed component-based programming framework for robotics. A system can be seen as a distributed network of software components interconnected by port connections where system behavior emerges from the interaction and independent execution of the components integrating the system. Recently we have endowed CoolBOT with two new types of software components: views and probes. On one side, in order to separate and decouple robot control from graphical displays, we have introduced the concept of view as an integrable, composite and reusable graphical interface available for CoolBOT system integrators and developers. On the other side, probes have been devised as interfaces for interoperability with non CoolBOT software.

Paper Nr: 6
Title:

EFFICIENTLY FINDING (NEARLY) MINIMAL FST OF REPETITIVE UNSEGMENTED DEMONSTRATION DATA

Authors:

Frederick L. Crabbe

Abstract: This paper presents an algorithm that enables a robot to learn from demonstration by inferring a nearly minimal plan instead of the more common policy. The algorithm uses only the demon- strated actions to build the plan, without relying on observation of the world states during the demonstration. By making assumptions about the format of the data, it can generate this plan in O(n5).