Julia Peltason

The curious robot - Structuring interactive robot learning

If robots are to succeed in novel tasks, they must be able to learn from humans. To improve such human-robot interaction, a system is presented that provides dialog structure and engages the human in an exploratory teaching scenario. Thereby, we specifically target untrained users, who are supported by mixed-initiative interaction using verbal and non-verbal modalities. We present the principles of dialog structuring based on an object learning and manipulation scenario. System development is following an interactive evaluation approach and we will present both an extensible, event-based interaction architecture to realize mixed-initiative and evaluation results based on a video-study of the system. We show that users benefit from the provided dialog structure to result in predictable and successful human-robot interaction.

Mixed-initiative in human augmented mapping

In scenarios that require a close collaboration and knowledge transfer between inexperienced users and robots, the “learning by interacting” paradigm goes hand in hand with appropriate representations and learning methods. In this paper we discuss a mixed initiative strategy for robotic learning by interacting with a user in a joint map acquisition process. We propose the integration of an environment representation approach into our interactive learning framework. The environment representation and mapping system supports both user driven and data driven strategies for the acquisition of spatial information, so that a mixed initiative strategy for the learning process is realised. We evaluate our system with test runs according to the scenario of a guided tour, extending the area of operation from structured laboratory environment to less predictable domestic settings.

The Curious Robot as a Case-Study for Comparing Dialog Systems

Modeling interaction with robots raises new and different challenges for dialog modeling than traditional dialog modeling with less embodied machines. We present four case studies of implementing a typical human-robot interaction scenario with different state-of-the-art dialog frameworks in order to identify challenges and pitfalls specific to HRI and potential solutions. The results are discussed with a special focus on the interplay between dialog and task modeling on robots.

Where is this? - gesture based multimodal interaction with an anthropomorphic robot

Traditional visitor guidance often suffers from the representational gap between 2D map representations and the real-world. Therefore, we propose a robotic information system that exploits its physical embodiment to present a readily interpretable interface for visitor guidance. Similar to human receptionists, it offers a familiar point of reference that can be approached by visitors and supports intuitive interaction through both speech and gesture. We focus on employing an anthropomorphic body to improve guidance functionality and interpretability of the interaction. The map, which contains knowledge about the environment, is used by robot and visitor simultaneously, with the robot translating its content into gestures. This setting affords disambiguation of information requests and thus improves robustness. It has been tested both in a laboratory demonstration setting and in our university hall, where people asked for information and thereby used the system in a natural way.

Talking with robots about objects: a system-level evaluation in HRI

We present the design process, realization and evaluation of a robot system for interactive object learning. The system-oriented evaluation, in particular, addresses an open problem for the evaluation of systems, where overall user satisfaction depends not only on the performance of the parts, but also on their combination, and on user behavior. Based on the PARADISE method known from spoken dialog systems, we have defined and applied internal and external metrics for fine-grained and largely automatable identification of such relationships. Through evaluation with n=28 subjects, indicator functions explaining up to 55% of variation in several satisfaction metrics were found. Furthermore, we demonstrate that the systems interaction style reduces the need for instruction and successfully recovers partial failures.

A Mixed-Initiative Approach to Interactive Robot Tutoring

Integrating the components described in the previous articles of this chapter, we introduce the Bielefeld “Curious Robot”, which is able to acquire new knowledge and skills in direct human-robot interaction. This paper focuses on the cognitive architecture of the overall system. We propose to combine (i) a communication layer based on a generic, human-accessible XML data format, (ii) multiple low-level sensor and control processes publishing their sensor information into the system and receiving commands or parameterizations from higher-level deliberative processes, and (iii) high-level coordination processes based on hierarchical state machines. The efficiency of the proposed approach is shown in an interactive tutoring scenario, where the Bielefeld “Curious Robot”, a bimanual robot system, should learn to identify, grasp, and clean various everyday objects from a table. The capability of the system to interact with lay persons is proven in a user study.

On Grounding Natural Kind Terms in Human-Robot Communication

Our contribution situates Human-Robot Communication, especially the grounding of Natural Kind Terms, in the interface of Artificial Intelligence, Cognitive Psychology, Philosophy, Robotics and Semantics. We investigate whether a robot can be grounded in the sense favoured in Artificial Intelligence and Philosophy.We thus extend the notion of grounding to social symbol grounding using an interactive perspective addressing the question how grounding can be achieved in detail in interaction. For the acquisition of Natural Kind Terms we establish the notions of foundational common ground and foundational grounding in contrast to the established common ground and grounding. We introduce the robot setting used and provide a deep evaluation of a tutorial dialogue between a user and the robot. We investigate these Human-Robot Communication data from an ethno-methodological and an “omniscient” perspective (the latter amounting to consideration of automatic speech recognition results) and test whether these perspectives matter for analysing grounding. We show that the robot has acquired a partial concept of a Natural Kind Term—represented by statistics over visual object features—and that this is shared knowledge, hence the first step of a grounding sequence. Finally, we argue that grounding of robots can be achieved and extended to situated structures of considerable complexity.

Structuring Human-Robot-Interaction in Tutoring Scenarios

Contrary to the assumptions underlying many current robot systems, teaching is an interactive process where the tutor needs to be continuously informed about the learner’s internal states of understanding and perception. In an open ended learning situation this interaction can not be pre-modelled as the aspects that need clarification can not be foreseen. However, standard approaches do exactly this: they pre-define interactions by coupling system states with dialog acts. In our approach we target at losening this coupling between system and dialog states by providing general task and interaction patterns and means to relate them to each other.