Narrow Results

This paper proposes a learning method for detecting object affordances through haptic exploration by a multi-fingered robot hand. Learning how to remove a screw cap from a bottle is the present target task. Assuming that coarse manipulation strategy is given by other methods, such as visual observation of a model task, the system applies coarse grabbing actions to the target object. In response to the exploratory actions, the object moves (rotates, in this case) along the physical constraint (screw). The robot detects the resulting motion through proprioception of the compliant fingers. A non-supervised statistical learning method is applied to categorize the resulting motion. The method is a combination of high-order local autocorrelation (HLAC), principal components analysis (PCA), and mean-shift clustering. Experiments with a real multi-fingered robot hand and bottle caps of different diameters confirm that the proposed method can detect and categorize rotational constraints.

A distinct property of robot vision systems is that they are embodied. Visual information is extracted for the purpose of moving in and interacting with the environment. Thus, different types of perception-action cycles need to be implemented and evaluated.

In this paper, we study the problem of designing a vision system for the purpose of object grasping in everyday environments. This vision system is firstly targeted at the interaction with the world through recognition and grasping of objects and secondly at being an interface for the reasoning and planning module to the real world. The latter provides the vision system with a certain task that drives it and defines a specific context, i.e. search for or identify a certain object and analyze it for potential later manipulation. We deal with cases of: (i) known objects, (ii) objects similar to already known objects, and (iii) unknown objects. The perception-action cycle is connected to the reasoning system based on the idea of affordances. All three cases are also related to the state of the art and the terminology in the neuroscientific area.

Humanoid robots that have to operate in cluttered and unstructured environments, such as man-made and natural disaster scenarios, require sophisticated sensorimotor capabilities. A crucial prerequisite for the successful execution of whole-body locomotion and manipulation tasks in such environments is the perception of the environment and the extraction of associated environmental affordances, i.e., the action possibilities of the robot in the environment. We believe that such a coupling between perception and action could be a key to substantially increase the flexibility of humanoid robots.

In this paper, we approach the affordance-based generation of whole-body actions for stable locomotion and manipulation. We incorporate a rule-based system to assign affordance hypotheses to visually perceived environmental primitives in the scene. These hypotheses are then filtered using extended reachability maps that carry stability information, for identifying reachable affordance hypotheses. We then formulate the hypotheses in terms of a constrained inverse kinematics problem in order to find whole-body configurations that utilize a chosen set of hypotheses.

The proposed methods are implemented and tested in simulated environments based on RGB-D scans as well as on a real robotic platform.

The external triggers cause transitions; to stay competitive, organizations create, respond to change, and shape the environment they interact with. The interactions manifest their traits as characteristics. Like biological species, organizations possess memes (or genotypes), memes mature as ideas or innovations, their interactions with the environment manifest as characteristics (phenotypes). IT organizations experience fast changes, for better response to change adopted agile software development (ASD). When phenotypes involve the development of affordances and display plasticity (agility), apart from cost-benefit criteria, it contributes to co-evolution among organizations and the environment. To examine the phenomena of co-evolution with diverse analytic and heuristic views, the author used multiple ASD case-studies from IT product$/$services organizations. The author noted that organizations increase the height of their fitness landscape, i.e., competitive advantage, by either developing and$/$or acquiring phenotypes. Acquisition meets cost-benefit criteria, but does not assist in sustaining the height, co-evolution, and$/$or cumulate as stable designs, thereby, there are inappropriate responses to external triggers.

This paper reports on a theory-based empirical investigation of cultural considerations in the appropriation of affordances and on the development of technological intersubjectivity in a computer supported collaborative learning environment. Socio-technical affordances are "action-taking possibilities" and "meaning-making opportunities" in a socio-technical system relative to the capabilities of an actor. Technological intersubjectivity is a technology-mediated interactional social relationship between two or more participants. The basic premise of this research project is that social affordances of technologies vary along cultural dimensions. To empirically evaluate this premise, an experimental study was conducted. The experimental study design consisted of three independent groups of dyads from similar or different cultures (American-American, American-Chinese, and Chinese-Chinese) doing collaborative problem-solving in a knowledge-mapping learning environment. Participants interacted through an asynchronous computer interface providing multiple tools for interaction (diagrammatic workspace, embedded notes, threaded discussion). Based on theories of culture and empirical findings in cultural psychology documenting cross-cultural variations in behavior, communication and cognition, several research hypotheses were advanced. Statistical results show that members of different cultures appropriated the resources of the interface differently in their interaction, and formed differential relations with and impressions of each other. However, analysis of the individually written essays show no statistically significant differences in learning outcomes. Implications for technology enhanced learning are discussed.

This paper describes research work aimed at designing realistic reasoning techniques for humanoid robots provided with advanced skills. Robots operating in real-world environments are expected to exhibit very complex behaviors, such as manipulating everyday objects, moving in crowded environments or interacting with people, both socially and physically. Such — yet to be achieved — capabilities pose the problem of being able to reason upon hundreds or even thousands different objects, places and possible actions to carry out, each one relevant for achieving robot goals or motivations. This article proposes a functional representation of everyday objects, places and actions described in terms of such abstractions as affordances and capabilities. The main contribution is twofold: (i) affordances and capabilities are represented as neural maps grounded in proper metric spaces; (ii) the reasoning process is decomposed into two phases, namely problem awareness (which is the focus of this work) and action selection. Experiments in simulation show that large-scale reasoning problems can be easily managed in the proposed framework.

Challenging tasks are essential in developing and demonstrating mathematical understanding. They provide opportunities to learn and the motivation for student to engage with learning. This chapter highlights how the real-world and digital technologies provide many opportunities to design and implement challenging tasks for all learners. The affordances of technology-rich teaching and learning environments need more attention if teachers and their students are to be better enabled to maximise opportunities for learning mathematics. A range of tasks are presented and discussed. Planning by teachers for varied student responses is critical in enabling ‘as needed’ in-the-moment scaffolding to keep students engaged with mathematical thinking.

In this paper, I will focus on how teachers can use typical problems to develop both conceptual fluency as well as procedural skills. These typical problems will be considered as mathematical tasks that teachers can opt to select, reformulate or create new ones for use in class. Teachers may find it easier to make sense of the mathematics and pedagogical considerations in the implementation of these tasks, as they are readily available in textbooks and past examination papers as compared to rich tasks. I will demonstrate that typical problems do have affordances for developing conceptual fluency and in that sense are equally good, if not better, better than the so-called rich tasks. With limited time at their disposal, teachers have to be strategic in noticing the affordances of typical problems and in optimally using their available time for selecting and using relevant tasks for their lessons. As such, the gist of the paper, connecting to my previous work, will be on how teachers can use typical problems in their day-to-day practice to enhance the learning of their students, against a backdrop of teacher noticing.

Classically, visual attention is assumed to be influenced by visual properties of objects, e.g. as assessed in visual search tasks. However, recent experimental evidence suggests that visual attention is also guided by action-related properties of objects ("affordances"),^1,2 e.g. the handle of a cup affords grasping the cup; therefore attention is drawn towards the handle. In a first step towards modelling this interaction between attention and action, we implemented the Selective Attention for Action model (SAAM). The design of SAAM is based on the Selective Attention for Identification model (SAIM).³ For instance, we also followed a soft-constraint satisfaction approach in a connectionist framework. However, SAAM's selection process is guided by locations within objects suitable for grasping them whereas SAIM selects objects based on their visual properties. In order to implement SAAM's selection mechanism two sets of constraints were implemented. The first set of constraints took into account the anatomy of the hand, e.g. maximal possible distances between fingers. The second set of constraints (geometrical constraints) considered suitable contact points on objects by using simple edge detectors. We demonstrate here that SAAM can successfully mimic human behaviour by comparing simulated contact points with experimental data.

Open governmental data available via platforms like data.gov have earned a place in the innovation agenda of governments and local authorities alike. To successfully make use of these sources, governments around the world experiment with competitive virtual contests or challenges to ignite the creativity of developers and hackers and motivate them to turn this data into novel digital applications. However, such efforts don’t seem to be sustainable. Applications developed in such contests regularly fail to ignite the continuous use by the end users. We argue that governments need to adopt an ecosystem perspective facilitating cocreation within the diverse open data innovation ecosystems of developers, producers, and users in order to foster the generativity needed for continuous value creation. However, various tensions among actors appear along the way. Taking a paradoxical view towards ecosystem tensions, we propose a socio-technical infrastructure that supports ecosystem generativity by addressing latent tensions in the “breeding zone” of an open data innovation. The infrastructure supports generative responses to these tensions in three ways: creating virtual trading zones, supporting the duality of stable and dynamic roles, and providing technological affordances for fluidity. This framework could set the stage for future research, encouraging system designers and policymakers to foster cocreation in open data innovation ecosystems.