An Architecture for Real-Time Control in Multi-robot Systems

Althoff, Daniel; Kourakos, Omiros; Lawitzky, Martin; Mörtl, Alexander; Rambow, Matthias; Rohrmüller, Florian; Brščić, Dražen; Wollherr, Dirk; Hirche, Sandra; Buss, Martin

doi:10.1007/978-3-642-10403-9_5

Cited by 18 publications

(14 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Subjects 1-3 were standing on target position 1, subjects 4-6 on target 2 and the remaining two on target 3. The mobile robot [15] was built within the CoTeSys cluster at the Technische Universität München, Germany. The trajectories performed by the robot were based on previously measured trajectories of the human-human experiments but adapted to the larger dimension of the robot.…”

Section: Human-robot Scenariomentioning

confidence: 99%

Inferring the goal of an approaching agent: A human-robot study

Basili

Huber

Kourakos

et al. 2012

2012 IEEE RO-MAN: The 21st IEEE International Symposium on Robot and Human Interactive Communication

Self Cite

View full text Add to dashboard Cite

Abstract-The ability to infer intentions and predict actions enables coordinating of one's own actions with those of another human and allows smooth and intuitive interaction. The aim to achieve equally effective human-robot interactions is a crucial aspect of current robotic studies. Thus, we assume that studying human-human interaction provides valuable insights allowing to implement mutual intention recognition and action prediction in robotic systems. A common scenario of interaction, be it in everyday life or in an industrial setting, is that two or more agents share the same workspace and perform tasks without interference. If humans are involved, the robots should act sufficiently predictable to enable the human to attribute goals and predict motion trajectories. In the present work, we first analyzed how well a human recognizes the goal of another person entering the room, and whether this ability is deteriorated by concealing gaze direction of the other person. In a second setup, the same experiment was repeated by replacing the approaching person with a wheeled robot. On average, the distance at which subjects predicted the goal of the approaching agent was approx. 4 m and depended on subject and goal position, but not on the type of agent. However, goal attribution showed a considerable proportion of errors for the robot (19%), much less for a human with hidden gaze direction (6%), and almost none for a human with visible gaze (1%). Thus, our subjects apparently decided on the goal of the approaching agent without taking into account the reliability of directional cues, thus resulting in more errors. In a human-robot setting, such wrong predictions about robotic behavior may easily lead to dangerous situations. For smooth and safe interaction, it is therefore important to ameliorate the predictability of robotic actions.

show abstract

Section: Human-robot Scenariomentioning

confidence: 99%

Inferring the goal of an approaching agent: A human-robot study

Basili

Huber

Kourakos

et al. 2012

2012 IEEE RO-MAN: The 21st IEEE International Symposium on Robot and Human Interactive Communication

Self Cite

View full text Add to dashboard Cite

show abstract

“…The aim is therefore to define and to implement mathematical models derived from human-human experiments in autonomous robots. Here we aim to quantitatively describe one aspect of human interaction with the goal to implement the results in the robotic system presented in [2] (see figure 1). Until now, several studies were done on human-robot interaction [1], [3], [4], [9]- [15] but only few of them [3], [9], [10], [12] were based on the analysis of humanhuman experiments.…”

Section: Introductionmentioning

confidence: 99%

Investigating Human-Human Approach and Hand-Over

Basili

Huber

Brandt

et al. 2009

Cognitive Systems Monographs

Self Cite

View full text Add to dashboard Cite

Humans interact safely, effortlessly, and intuitively with each other. An efficient robot assistant should thus be able to interact in the same way. This requires not only that the robot can react appropriately to human behaviour, but also that robotic behaviour can be understood intuitively by the human partners. The latter can be achieved by the robot mimicking certain aspects of human behaviour so that the human partner can more easily infer the intentions of the robot. Here we investigate a simple interaction scenario, approach and hand-over, to gain better understanding of the behavioural patterns in human-human interactions. In our experiment, one human subject, holding an object, approached another subject with the goal to hand over the object. Head and object positions were measured with a motion tracking device to analyse the behaviour of the approaching human. Interaction indicated by lifting the object in order to prepare for hand-over started approximately 1.2 s before the actual hand-over. Interpersonal distance varied considerably between subjects with an average of 1.16 m. To test whether the behavioural patterns observed depended on two humans being present, we replaced in a second experiment the receiving subject with a table. We found that the behaviour of the transferring subject was very similar in both scenarios. Thus, the presence of the receiving subject plays a minor role in determining parameters such as start of interaction or interaction distance. We aim to implement and test the parameters derived experimentally in a robotic assistant to improve and facilitate human-robot interaction.

show abstract

“…3) Software Architecture: Our real-time control framework [10][11], which is based on the KogmoRTDB real-time database [12] is used during demonstration and autonomous task execution. In addition to synchronized data management it allows to record and replay data streams.…”

Section: ) Teleoperator and Autonomous Robotmentioning

confidence: 99%

Autonomous manipulation of deformable objects based on teleoperated demonstrations

Rambow

Schauss

Buss

et al. 2012

2012 IEEE/RSJ International Conference on Intelligent Robots and Systems

Self Cite

View full text Add to dashboard Cite

Abstract-While humans can manipulate deformable objects smoothly and naturally, this is still a challenge for autonomous robots due to the complex object dynamics. The presence of rigid environment constraints and altering contact phases between the deformable object, the manipulator, and the environment makes this problem even more challenging. This paper presents a framework for deformable object manipulation that makes use of a single human demonstration of the task. The recorded trajectories are automatically segmented into a sequence of haptic control primitives involving contact with the rigid environment and vision-guided grasp primitives. The recorded motion/force trajectories serve as reference for a compliant control scheme in contact situations. In order to cope with positioning uncertainties a variable admittance control is proposed. The proposed approach is validated in an experimental mounting task for a deformable linear object with multiple re-grasping. The task is demonstrated with a multimodal teleoperation system and transfered to a robotic platform with a pair of seven degrees of freedom manipulators.

show abstract

An Architecture for Real-Time Control in Multi-robot Systems

Cited by 18 publications

References 6 publications

Inferring the goal of an approaching agent: A human-robot study

Inferring the goal of an approaching agent: A human-robot study

Investigating Human-Human Approach and Hand-Over

Autonomous manipulation of deformable objects based on teleoperated demonstrations

Contact Info

Product

Resources

About