Natural language instructions are often underspecified and imprecise which makes them hard to understand for an artificial agent. In this article we present a system of connected knowledge representations that is used to control a robot through instructions. As actions are a key component of instructions and the robot's behavior the representation of action is central in our approach. First, the system consists of a conceptual schema representation which provides a parameter interface for action. Second, we present an intermediate representation of the temporal structure of action and show how this generic action structure can be mapped to detailed action controllers as well as language.

Facing the fourth industrial revolution, autonomous mobile robots are expected to play an important role in the production processes of the future. The new Logistics League Sponsored by Festo (LLSF) under the RoboCup umbrella focuses on this aspect of robotics to provide a benchmark testbed on a common robot platform. We describe certain aspects of the integrated robot system of our Carologistics RoboCup team, in particular our reasoning system for the supply chain problem of the LLSF. We approach the problem by deploying the CLIPS rules engine for product planning and dealing with the incomplete knowledge that exists in the domain and show that it is suitable for computationally limited platforms.

In this paper, we present an algorithm that integrates computer vision with machine learning to enable a humanoid robot to accurately fire at objects classified as targets. The robot needs to be calibrated to hold the gun and instructed how to pull the trigger. Two algorithms are proposed and are executed depending on the dynamics of the target. If the target is stationery, a least mean square (LMS) approach is used to compute the error and adjust the gun muzzle accordingly. If the target is found to be dynamic, a modified Q-learning is used to best predict the object position and velocity and to adjust relevant parameters, as necessary. The image processing utilizes the OpenCV library to detect the target and point of impact of the bullets. The approach is evaluated on a 53-DOF humanoid robot iCub. This work is an example of fine motor control which is the basis for much of natural language processing by spatial reasoning. It is one aspect of a long term research effort on automatic language acquisition.

The dynamical and uncertain environments of domestic service robots, which include humans, require rethinking of the benchmarking principles for testing these robots. In RoboCup@Home, statistical procedures are used to track and steer the progress of domestic service robots since 2006. This paper explains the procedures and shows outcomes of these international benchmarking efforts. Although aspects such as shopping in a supermarket receive a fair amount of attention in the robotics community, the authors think that a recently started test is the most important outcome of RoboCup@Home, namely the benchmarking of robot cognition.

We present a high-level overview of our research efforts to build an intelligent robot capable of addressing real-world problems. The UJI Humanoid Robot Torso integrates research accomplishments under the common framework of multimodal active perception and exploration for physical interaction and manipulation. Its main components are three subsystems for visuomotor learning, object grasping and sensor integration for physical interaction. We present the integrated architecture and a summary of employed techniques and results. Our contribution to the integrated design of an intelligent robot is in this combination of different sensing, planning and motor systems in a novel framework.

We present the integration of our symbolic planner as the high-level executive in the Tidyup-Robot project. Tidyup-Robot deals with mobile manipulation scenarios in a household setting. We introduce our system architecture and report on issues and advantages observed during development and deployment.

We propose an approach to configuration planning for robotic systems in which plans are represented as constraint networks and planning is defined as search in the space of such networks. The approach supports reasoning about time, resources, and information dependencies between actions. In addition, the system can leverage the flexibility of such networks at execution time to support dynamic goal posting and re-planning.

Recently, various commercial telepresence robots have become available to the broader public. Here, we present the telepresence domain as a research platform for (re-)integrating AI. With MITRO: Maastricht Intelligent Telepresence RObot, we built a low-cost working prototype of a robot system specifically designed for augmented and autonomous telepresence. Telepresence robots can be deployed in a wide range of application domains, and augmented presence with assisted control can greatly improve the experience for the user. The research domains that we are focusing on are human robot interaction, navigation and perception.

To provide insight into patient-level disease dynamics from data collected at irregular time intervals, this work extends applications of semi-parametric clustering for temporal mining. In the semi-parametric clustering framework, Markovian models provide useful parametric assumptions for modeling temporal dynamics, and a non-parametric method isused to cluster the temporal abstractions instead operating on the original data. Our contribution extends abstraction to continuous-time Markov models and the clustering componentto the non-parametric Bayesian setting, which does not require the number of clusters to be indicated a priori.

We propose a novel method of self-tracking cognitive and neuroanatomical data for monitoring and manipu- lating brain structure. Neuroprofiling, a web service for personalized brain data visualization, is a platform for collecting, analyzing and displaying neuroimaging and cognitive data in a meaningful, simple and individualized way. Users’ T1-weighted, volumetric magnetic resonance imaging (MRI) scans of their brain can be uploaded onto a website, which automatically segments, preprocesses and analyses the image using voxel-based morphometry (VBM) to produce a z-score statistical map of the brain. This reveals, for each subject, the cortical density of different brain regions relative to the mean densities of the population sample. Through a 3D interactive brain-model interface, users can review their unique neuroanatomical profile. By completing behavioral cognitive testing, they can assess different strengths and weaknesses in cognitive abilities that relate to their brain physiology. They can also compare brains with all other users as a group, as well as with experts across different skill domains.