Towards a Cognitive System that Can Recognize Spatial Regions Based on Context

We present in this paper, a qualitative spatial relationships representation scheme called IO&T which combines fuzzy Intrinsic Orientation and Topological spatial relationships, and a similarity measure based on this representation. This scheme is invariant under translation and rotation. In addition, the proposed picture similarity retrieval approach, which is based on dominant objects, is especially useful for similarity retrieval involving a small number of dominant objects.KeywordsSpatial RelationshipOrientation RelationshipSpatial RelationMaximal CliqueTopological RelationshipThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

This article responds to the widespread and oft-noted challenges digital humanists face in working with data that is uncertain and characterised by complex narratives. Using an example drawn from the vast archives of post-war interviews with Holocaust survivors, it draws on approaches developed in Qualitative Spatial Representation (QSR) to explore how two key spatial aspects of survivor's narratives – their uncertain wartime trajectories and the slippage in scales as these are retold – can be represented. Spatial information in narratives tends to not provide the exact coordinates necessary to store the information in geospatial databases. Instead, narratives rely much more on often less precise qualitative spatial relations such as ‘near’, ‘next to’, ‘at the corner of’ without precise geometric interpretations. Given that relational databases are ill-equipped to store this kind of relational spatial knowledge from natural language sources, the article argues for a need for digital humanists to return to first principles and reconsider database design. Descriptive triple-based graph representations, which have been devised to accommodate this kind of highly irregular, semi-structured relational knowledge, have the potential to work with, rather than against, the grain of the narrative sources that underlie the work of much of the digital humanities.

The paper is a overview of the major qualitative spatial representation and reasoning techniques. We survey the main aspects of the representation of qualitative knowledge including ontological aspects, topology, distance, orientation and shape. We also consider qualitative spatial reasoning including reasoning about spatial change. Finally there is a discussion of theoretical results and a glimpse of future work. The paper is a revised and condensed version of [33,34].

Chapter 13 Qualitative Spatial Representation and Reasoning

This paper presents an automated system for generating a semantic map of inventory in a retail environment. Developing this map involves assigning a department label to each discrete section of shelving. We use a priori information to boost data from laser and camera sensors for object recognition and semantic labeling. We introduce a soft object map and a dynamic programming algorithm for point cloud segmentation. The primary contribution of this work is the integration of multiple systems including an automated path planning and navigation subsystem and a semantic mapping object recognition system. This work also represents an important contribution to robots working reliably in human environments. To our knowledge this is the first actual implementation of a fully automated robot inventory labeling system for a retail environment. The framework presented in this paper is easily scalable to other retail environments and is also relevant in any indoor environment with organized shelves, such as business storage facilities and hospital pharmacies.

Autonomous robots are unsuccessful at operating in complex, unconstrained environments. They lack the ability to learn about the physical behavior of different objects through the use of vision. We combine Bayesian networks and qualitative spatial representation to learn general physical behavior by visual observation. We input training scenarios that allow the system to observe and learn normal physical behavior. The position and velocity of the visible objects are represented as qualitative states. Transitions between these states over time are entered as evidence into a Bayesian network. The network provides probabilities of future transitions to produce predictions of future physical behavior. We use test scenarios to determine how well the approach discriminates between normal and abnormal physical behavior and actively predicts future behavior. We examine the ability of the system to learn three naive physical concepts, "no action at a distance", "solidity" and "movement on continuous paths". We conclude that the combination of qualitative spatial representations and Bayesian network techniques is capable of learning these three rules of naive physics.

We develop a formal, symbolic representation of right-of-way-rules for sea navigation based on a qualitative spatial representation. Navigation rules specified qualitatively allow an autonomous agent consistently to combine all rules applicable in a context. The focus of this paper is to show how the abstract rule specification can be used during path-planning. We propose a randomized-qualitative approach to navigation, integrating the symbolic level with a probabilistic roadmap planner. The resulting navigation system maneuvers under the side constraint of rule compliancy. Evaluating our approach with case studies we demonstrate that qualitative navigation rules contributes to autonomous sailing.

"Qualitative Spatial Representation: A Special Section." International Journal of Humanities and Arts Computing, 13(1-2), p. 1

Qualitative Spatial Representations

An increasing number of computationally enhanced objects is distributed around us in physical space, which are equipped - or at least can be provided -- with sensors for measuring spatial contexts like position, direction and acceleration. We consider spatial relationships between them, which can basically be acquired by a pairwise comparison of their spatial contexts, as crucial information for a variety of applications. If such objects do have wireless communication capabilities, they will be able to build up an ad-hoc network and exchange their spatial contexts among each other. However, processing detailed sensor information and routing it through the network lowers their battery lifetime or even may exceed the capabilities of embedded systems with limited resources. Thus, we present a novel and efficient approach for inferring and distributing spatial contexts in multi-hop networks, which builds upon qualitative spatial representation and reasoning techniques. Simulation results show its behavior with respect to common network topologies.

A method of spatial reasoning based on qualitative trigonometry

Qualitative spatial conceptualizations provide a relational abstraction and interface to the metrical realities of the physical world. Humans, robots, and systems that act and interact, are embedded in space. The space itself undergoes change all the time, typically as a result of volitional actions performed by an agent, and events, both deterministic and otherwise, which occur in the environment. Both categories of occurrences are a critical link to the external world, in a predictive as well as an explanatory sense: anticipations of spatial reality conform to commonsense knowledge of the effects of actions and events on material entities. Similarly, explanations of the perceived reality too are established on the basis of such apriori established commonsense notions. The author reasons about space, actions, and change in an integrated manner, either without being able to clearly demarcate the boundaries of each type of reasoning, or because such boundaries do not exist per se. This chapter is an attempt to position such integrated reasoning as a useful paradigm for the utilization of qualitative spatial representation and reasoning techniques in relevant application domains. From a logical perspective, the author notes that formalisms already exist and that effort need only be directed at specific integration tasks at a commonsense conceptual, formal representational, and computational level.

Intelligent and efficient information retrieval becomes increasingly important. Analogous to thesauri in the realm of spatial concepts, gazetteers offer a controlled vocabulary that can be used for spatial queries. Gazetteers use geographic footprints to link place names to geographic locations. Which geographic footprint representation is chosen has a strong impact on the quality of spatial queries. However, the footprint representations currently used in standard gazetteers such as points, lines, grid cell representations, and bounding boxes do not offer enough topological information to support refined spatial queries. We propose a new type of spatial footprint that can be described as a qualitative representation of the spatial decomposition of geographic entities. It holds enough topological and ordinal information enable refined spatial queries without being subject to the constraints of exact polygon representations. The proposed spatial representation was developed to be combined with terminological reasoning techniques used in systems for intelligent information integration.

Prescribing tasks, which involve pharmacological knowledge, clinical decision-making and practical skill, take place within unpredictable social environments and involve interactions within and between endlessly changing health care teams. Despite this, curriculum designers commonly assume them to be simple to learn and perform. This research used mixed methods to explore how undergraduate medical students learn to prescribe in the ‘real world’. It was informed by cognitive psychology, sociocultural theory, and systems thinking. We found that learning to prescribe occurs as a dynamic series of socially negotiated interactions within and between individuals, communities and environments. As well as a thematic analysis, we developed a framework of three conceptual spaces in which learning opportunities for prescribing occur. This illustrates a complex systems view of prescribing education and defines three major system components: the “social space”, where the environmental conditions influence or bring about a learning experience; the “process space”, describing what happens during the learning experience; and the intra-personal “cognitive space”, where the learner may develop aspects of prescribing expertise. This conceptualisation broadens the scope of inquiry of prescribing education research by highlighting the complex interplay between individual and social dimensions of learning. This perspective is also likely to be relevant to students’ learning of other clinical competencies.

The existence of emotion and cognition as two interacting systems, both with important roles in decision-making, has been recently advocated by neurophysiological research (LeDoux, 1998, Damasio, 1994. Following that idea, this paper presents the ALEC agent architecture which has both emotive and cognitive learning, as well as emotive and cognitive decision-making capabilities to adapt to real-world environments. These two learning mechanisms embody very different properties which can be related to those of natural emotion and cognition systems. The reported experiments test ALEC within a simulated autonomous robot which learns to perform a multi-goal and multi-step survival task when faced with real world conditions, namely continuous time and space, noisy sensors and unreliable actuators. Experimental results show that both systems contribute positively to the learning performance of the agent.