Multi-agent path finding has been proven to be a PSPACE-hard problem. Generating such a centralised multi-agent plan can be avoided, by allowing agents to plan their paths separately. However, this results in an increased number of collisions and agents must re- plan frequently. In this paper we present a framework for multi-agent path planning, which allows agents to plan independently and solve conflicts locally when they occur. The framework is a generalisation of the CQ-learning algorithm which learns sparse interactions between agents in a multi-agent reinforcement learning setting

With the increasing popularity of smartphones, the wide availability of mobile Internet and the higher computational power of mobile devices, new types of applications are now possible. It is important to provide a smooth user experience by facilitating the interaction with the device. To do so, the goal of the work is support proactive recommendations on the mobile device. In order to determine the best point in time for a recommendation, various context information needs to be taken into account. One interesting aspect is determining the current user activity, e.g. whether the user is walking or not. In this paper, we present an algorithm that runs online on a smartphone and analyzes the user activity based on GPS data.

Rapid development in the area of ambient intelligence introduced numerous applications. One of the fundamental underpinnings in such applications is an effective and reliable context-aware system able to recognize and understand activities performed by a human, and context in which it happened. However, there are two pending issues: (i) transferability, i.e., a specific implementation is tightly interrelated with a selected algorithm, available sensors, and a scenario/environment where they are employed; and (ii) comparability, i.e., there is no established benchmark problem that would enable a direct comparison of the developed context-aware systems. This paper first reviews some recent initiatives that address the abovementioned problems and then proposes a centralized collection of resources related to design and evaluation of context-aware systems. The main idea is to establish an online repository of datasets accompanied with the task, result and applied approach. Ideally, the contributors will provide the dataset with short description of the data, task and results, relevant paper, and link to resources such as implementation of the approach, preprocessing tools, and filtering. This would allow the community to quickly start building upon the latest state-of-the-art approaches, to benchmark newly developed techniques, and ultimately, to advance the frontiers in ambient intelligence.

We discuss preliminary work focusing on the problem of combining social interaction with task-based action in a dynamic, multiagent bartending domain, using an embodied robot. We show how the users' spoken input is interpreted, discuss how social states are inferred from the parsed speech together with low-level information from the vision system, and present a planning approach that models task, dialogue, and social actions in a simple bartending scenario. This approach allows us to build interesting plans, which have been evaluated in a real-world study, using a general purpose, off-the-shelf planner, as an alternative to more mainstream methods of interaction management.

A general consensus on representation of emotions and feelings in cognitive architectures is currently missing; yet artificial emotional intelligence is vital for the integration of future robots into the human society. This work introduces one possible approach to representation and processing of emotional mental states and attitudes, that allows for implementation of control of agent behavior by emotions as well as for recognition of emotional motivations in another agent's behavior. One particular advantage of this approach is that it allows for representation and processing of complex/social emotional attitudes, like shame, jealousy, resentment, or humor. The proposed validation of the approach is based on simulation of the emergence of emotional relationships in a small group of agents in a virtual environment.

Reading groups domain is a new domain for group recommenders. In this paper we propose a web based group recommender system which is called BoRGo: Book Recommender for Reading Groups, for reading groups domain. BoRGo uses a new information filtering technique which uses the difference between positive and negative feedbacks about a feature of a user profile and also presents an interface for after recommendation processes like achieving a consensus on the reading list.

Design tasks are notoriously difficult, because success is defined by the perception of the target audience, whose feedback is usually not available during design stages. Commonly, design is performed by professionals who have specific domain knowledge (i.e., an intuitive understanding of the implicit requirements of the task) and do not need the feedback of the perception of the viewers during the process. In this paper, we present a novel design methodology for creating minimal sketches of objects that uses an iterative optimization scheme. We define minimality for a sketch via the minimal number of straight line segments required for correct recognition by 75% of naiive viewers. Crowd-sourcing techniques allow us to directly include the perception of the audience in the design process. By joining designers and crowds, we are able to create a human computation system that can efficiently optimize sketches without requiring high levels of domain knowledge (i.e., design skills) from any worker.

Efforts by the pervasive, context-aware system development community have over the years produced a wide variety of context-aware techniques and frameworks. However, a bulk of this technology tends to be strictly tied to a native system, thus largely limiting its external adoption. In addressing this limitation, we introduce an interoperable context representation format, in the form of an ontology, which models core context-aware concepts for re-use within pervasive computing environments. The DCON Context Ontology is proposed as a novel vocabulary for the representation of activity context as experienced by a user, and sensed through one or more of their devices. We demonstrate how, combined with other domain ontologies, DCON provides for richer representations of multi-level context interpretations that are integrated with other known background information about a user.

The ESP Game tends to generate "low effort" or "surface semantics" tags. This paper presents two variations of the ESP Games called "squaring" and "scripting" that trim the ESP Game to collect "deep semantics" tags. The approaches do not require players to get used to, and for the GWAP operators to deploy, new games. First experiments point to the efficiency of squaring and scripting the ESP Game at collecting "deep semantic" tags.

The DARPA Mind’s Eye program seeks to develop in machines a capability that currently exists only in animals: visual intelligence. This paper describes a Neural-Symbolic Cognitive Agent that integrates neural learning, symbolic knowledge representation and temporal reasoning in a visual intelligent system that can reason about actions of entities observed in video. Results have shown that the system is able to learn and represent the underlying semantics of the actions from observation and use this for several visual intelligent tasks, like recognition, description, anomaly detection and gap-filling.