Prediction of intent in robotics and multi-agent systems

Moving beyond the stimulus contained in observable agent behaviour, i.e. understanding the underlying intent of the observed agent is of immense interest in a variety of domains that involve collaborative and competitive scenarios, for example assistive robotics, computer games, robot–human interaction, decision support and intelligent tutoring. This review paper examines approaches for performing action recognition and prediction of intent from a multi-disciplinary perspective, in both single robot and multi-agent scenarios, and analyses the underlying challenges, focusing mainly on generative approaches.     

Exogenous spatial precuing reliably modulates object processing but not object substitution masking

Object substitution masking (OSM) is used in behavioral and imaging studies to investigate processes associated with the formation of a conscious percept. Reportedly, OSM occurs only when visual attention is diffusely spread over a search display or focused away from the target location. Indeed, the presumed role of spatial attention is central to theoretical accounts of OSM and of visual processing more generally (Di Lollo, Enns, & Rensink, Journal of Experimental Psychology: General 129:481–507, 2000). We report a series of five experiments in which valid spatial precuing is shown to enhance the ability of participants to accurately report a target but, in most cases, without affecting OSM. In only one experiment (Experiment 5) was a significant effect of precuing observed on masking. This is in contrast to the reliable effect shown across all five experiments in which precuing improved overall performance. The results are convergent with recent findings from Argyropoulos, Gellatly, and Pilling (Journal of Experimental Psychology: Human Perception and Performance 39:646–661, 2013), which show that OSM is independent of the number of distractor items in a display. Our results demonstrate that OSM can operate independently of focal attention. Previous claims of the strong interrelationship between OSM and spatial attention are likely to have arisen from ceiling or floor artifacts that restricted measurable performance.     

Predicting students' intention to smoke by theory of planned behaviour variables and parental influences across school grade levels

Differences were examined in Theory of Planned Behaviour determinants of students' intention to smoke including parents' attitudes towards smoking and parents' current cigarette use among Greek students of different school grade levels. Students (N?=?763) aged 10-18 years reported their attitudes towards smoking, subjective norms, perceived behavioural control, self-identity and intention to smoke while their parents (N?=?525) reported their attitudes towards smoking and their current cigarette use. All the TPB variables increased from lower to higher school grade level. Multi-sample path analyses showed that parent's attitudes towards smoking positively predicted students' intention to smoke only for elementary school children. Parents' current cigarette use did not contribute significantly. Students' attitudes, perceived behavioural control and self-identity predicted systematically intention to smoke in contrast to the subjective norm that did not contribute at all. Perceived behavioural control contributed to a higher degree in intention to smoke for senior high school students compared to the junior high school and elementary students. Self-identity contributed to a higher degree in intention to smoke for elementary compared to the junior high school students. The results of this study suggests that the determinants of smoking vary between early and late adolescence.     

Predicting students’ intention to smoke by theory of planned behaviour variables and parental influences across school grade levels

Differences were examined in Theory of Planned Behaviour determinants of students’ intention to smoke including parents’ attitudes towards smoking and parents’ current cigarette use among Greek students of different school grade levels. Students (N?=?763) aged 10–18 years reported their attitudes towards smoking, subjective norms, perceived behavioural control, self-identity and intention to smoke while their parents (N?=?525) reported their attitudes towards smoking and their current cigarette use. All the TPB variables increased from lower to higher school grade level. Multi-sample path analyses showed that parent's attitudes towards smoking positively predicted students’ intention to smoke only for elementary school children. Parents’ current cigarette use did not contribute significantly. Students’ attitudes, perceived behavioural control and self-identity predicted systematically intention to smoke in contrast to the subjective norm that did not contribute at all. Perceived behavioural control contributed to a higher degree in intention to smoke for senior high school students compared to the junior high school and elementary students. Self-identity contributed to a higher degree in intention to smoke for elementary compared to the junior high school students. The results of this study suggests that the determinants of smoking vary between early and late adolescence.     

The Robot in the Crib: A Developmental Analysis of Imitation Skills in Infants and Robots

Interesting systems, whether biological or artificial, develop. Starting from some initial conditions, they respond to environmental changes, and continuously improve their capabilities. Developmental psychologists have dedicated significant effort to studying the developmental progression of infant imitation skills, because imitation underlies the infant's ability to understand and learn from his or her social environment. In a converging intellectual endeavour, roboticists have been equipping robots with the ability to observe and imitate human actions because such abilities can lead to rapid teaching of robots to perform tasks. We provide here a comparative analysis between studies of infants imitating and learning from human demonstrators, and computational experiments aimed at equipping a robot with such abilities. We will compare the research across the following two dimensions: (a) initial conditions-what is innate in infants, and what functionality is initially given to robots, and (b) developmental mechanisms-how does the performance of infants improve over time, and what mechanisms are given to robots to achieve equivalent behaviour. Both developmental science and robotics are critically concerned with: (a) how their systems can and do go 'beyond the stimulus' given during the demonstration, and (b) how the internal models used in this process are acquired during the lifetime of the system.     

异步异构分层并行演化算法及其在串并系统可靠性优化中的应用(英文)

本文提出了一种新的并行演化算法――异步异构分层并行演化算法(AHHPGA),用于求解串并系统可靠性分配的多目标优化问题(RAP)。AHHPGA采用分层结构,上层由粗粒度模型构成,下层由细粒度模型构成。在AHHPGA的每个子种群中,采用不同的全局/局部搜索度和拓扑结构,构成异构模型。AHHPGA的迁移方式包括异步接收和异步迁出。采用基于模型的复杂系统可靠性评价工具(HiP-HOPS),以克服可靠性框图方法(RBD)的缺点。仿真结果表明,基于异步异构分层并行演化算法和HiP-HOPS工具的串并系统可靠性分配的多目标优化方法,优于传统的基于遗传算法的优化方法。