http://dl.gi.de/handle/20.500.12116/11096 2026-07-22T22:10:51Z http://dl.gi.de/handle/20.500.12116/11353 From Object Recognition to Activity Interpretation and Back, Based on Point Cloud Data Albrecht, Sven; Wiemann, Thomas; Hertzberg, Joachim; Guesgen, Hans W.; Marsland, Stephen Semantic mapping of static environments has become a hot topic in robotics. The aim of the Mermaid project was to investigate the transfer of a sensor data interpretation approach for mapping to the problem of activity recognition in smart home applications such as elderly care. The basic structure of the semantic mapping approach, i.e., to assemble hypotheses of object aggregates in a closed-loop process of bottom-up raw data interpretation and top-down expectation generation from a domain ontology, can be extended to the temporal domain to include activity interpretation. This paper reports initial results, based on a study using point clouds from depth (RGB-D) sensor data. 2013-01-01T00:00:00Z http://dl.gi.de/handle/20.500.12116/11349 Human-Centered Robotics Visser, Ubbo 2013-01-01T00:00:00Z http://dl.gi.de/handle/20.500.12116/11346 Stream-Based Hierarchical Anchoring Heintz, Fredrik; Kvarnström, Jonas; Doherty, Patrick Autonomous systems situated in the real world often need to recognize, track, and reason about various types of physical objects. In order to allow reasoning at a symbolic level, one must create and continuously maintain a correlation between symbols denoting physical objects and sensor data being collected about them, a process called anchoring.In this paper we present a stream-based hierarchical anchoring framework. A classification hierarchy is associated with expressive conditions for hypothesizing the type and identity of an object given streams of temporally tagged sensor data. The anchoring process constructs and maintains a set of object linkage structures representing the best possible hypotheses at any time. Each hypothesis can be incrementally generalized or narrowed down as new sensor data arrives. Symbols can be associated with an object at any level of classification, permitting symbolic reasoning on different levels of abstraction. The approach is integrated in the DyKnow knowledge processing middleware and has been applied to an unmanned aerial vehicle traffic monitoring application. 2013-01-01T00:00:00Z http://dl.gi.de/handle/20.500.12116/11347 Co-constructing Grounded Symbols—Feedback and Incremental Adaptation in Human–Agent Dialogue Buschmeier, Hendrik; Kopp, Stefan Grounding in dialogue concerns the question of how the gap between the individual symbol systems of interlocutors can be bridged so that mutual understanding is possible. This problem is highly relevant to human–agent interaction where mis- or non-understanding is common. We argue that humans minimise this gap by collaboratively and iteratively creating a shared conceptualisation that serves as a basis for negotiating symbol meaning. We then present a computational model that enables an artificial conversational agent to estimate the user’s mental state (in terms of contact, perception, understanding, acceptance, agreement and based upon his or her feedback signals) and use this information to incrementally adapt its ongoing communicative actions to the user’s needs. These basic abilities are important to reduce friction in the iterative coordination process of co-constructing grounded symbols in dialogue. 2013-01-01T00:00:00Z