Simultaneous Past and Current Social Interaction-aware Trajectory Prediction for Multiple Intelligent Agents in Dynamic Scenes

Trajectory prediction of multiple agents in a crowded scene is an essential component in many applications, including intelligent monitoring, autonomous robotics, and self-driving cars. Accurate agent trajectory prediction remains a significant challenge because of the complex dynamic interactions among the agents and between them and the surrounding scene. To address the challenge, we propose a decoupled attention-based spatial-temporal modeling strategy in the proposed trajectory prediction method. The past and current interactions among agents are dynamically and adaptively summarized by two separate attention-based networks and have proven powerful in improving the prediction accuracy. Moreover, it is optional in the proposed method to make use of the road map and the plan of the ego-agent for scene-compliant and accurate predictions. The road map feature is efficiently extracted by a convolutional neural network, and the features of the ego-agent’s plan is extracted by a gated recurrent network with an attention module based on the temporal characteristic. Experiments on benchmark trajectory prediction datasets demonstrate that the proposed method is effective when the ego-agent plan and the the surrounding scene information are provided and achieves state-of-the-art performance with only the observed trajectories.

Modelling Consensus Emergence With Nonlinear Dynamics

The study of emergent, bottom-up, processes has long been of interest within organizational and group research. Emergent processes refer to how dynamic interactions among lower-level units (e.g. individuals) over time form a new, shared, construct or phenomena at a higher level (e.g. work group). To properly study emergence of shared constructs one needs models, and data, that both take into account variability across individuals and groups (multilevel), and variability over time (longitudinal). This article makes three contribution to the modelling and theory of of consensus emergence. First, we formulate two separate patterns of consensus emergence; homogeneous and heterogeneous. Homogeneous consensus emergence is characterized by gradual and almost deterministic adjustments of the individual trajectories, whereas heterogeneous consensus emergence show more randomly oscillating trajectories towards consensus. Second, we introduce a model-invariant statistic that measures the strength of the consensus; and allows for comparisons between different models and patterns of consensus emergence. Third, we show how Gaussian Processes can be used to further extend the consensus emergence models, allowing them to capture nonlinear dynamics, on both individual and group level, in emergent processes. Using an established data set, we show that conclusions on the pattern of consensus emergence can change depending on whether the nonlinear group mean change over time is adequately modelled or not. Thus it is crucial to correctly capture the group dynamics to properly understand the consensus emergence.

Dance wherever you are: the evolution of multi-modal delivery for social inclusion of rural older adults

Background and Objectives Older adult social inclusion involves meaningful participation that is increasingly mediated by information communication technology (ICT) and in rural areas requires understanding of older adults’ experiences in the context of the digital divide. This paper examines how the multi-modal streaming (live, pre-recorded, blended in-person) of the Sharing Dance Older Adults program developed by Canada's National Ballet School (NBS) and Baycrest, influenced social inclusion processes and outcomes in rural settings. Research Design and Methods Data were collected from on-site observations of dance sessions, research team reflections, focus groups and interviews with older adult participants and their carers in pilot studies in the Peterborough Region of Ontario, and the Westman Region of Manitoba, Canada (2017-2019). There were 289 participants including older adults, people living with dementia, family carers, long-term-care staff, community facilitators, and volunteers. Analytic themes were framed in the context of rural older adult social exclusion. Results Remote delivery addressed barriers of physical distance by providing access to the arts-based program and enhancing opportunities for participation. Constraints were introduced by the use of technology in rural areas and mitigated by in-person facilitators and different streaming options. Meaningful engagement in dynamic interactions in the dance was achieved by involving local staff and volunteers in facilitation of and feedback on the program and its delivery. Different streaming technologies influenced social inclusion in different ways: live-stream enhanced connectedness, but constrained technical challenges; pre-recorded was reliable, but less social; blended delivery provided options, but personalization was unsustainable. Discussion and Implications Understanding different participants’ experiences of different technologies will contribute to more effective remote delivery of arts-based programs with options to use technology in various contexts depending on individual and organizational capacities.

A Logic for Monitoring Dynamic Networks of Spatially-distributed Cyber-Physical Systems

Cyber-Physical Systems (CPS) consist of inter-wined computational (cyber) and physical components interacting through sensors and/or actuators. Computational elements are networked at every scale and can communicate with each other and with humans. Nodes can join and leave the network at any time or they can move to different spatial locations. In this scenario, monitoring spatial and temporal properties plays a key role in the understanding of how complex behaviors can emerge from local and dynamic interactions. We revisit here the Spatio-Temporal Reach and Escape Logic (STREL), a logic-based formal language designed to express and monitor spatio-temporal requirements over the execution of mobile and spatially distributed CPS. STREL considers the physical space in which CPS entities (nodes of the graph) are arranged as a weighted graph representing their dynamic topological configuration. Both nodes and edges include attributes modeling physical and logical quantities that can evolve over time. STREL combines the Signal Temporal Logic with two spatial modalities reach and escape that operate over the weighted graph. From these basic operators, we can derive other important spatial modalities such as everywhere, somewhere and surround. We propose both qualitative and quantitative semantics based on constraint semiring algebraic structure. We provide an offline monitoring algorithm for STREL and we show the feasibility of our approach with the application to two case studies: monitoring spatio-temporal requirements over a simulated mobile ad-hoc sensor network and a simulated epidemic spreading model for COVID19.

Evidence-based practice and management-by-knowledge of disability care: rigid constraint or fluid support?

Background: Although increasingly accepted in some corners of social work, critics have claimed that evidence-based practice (EBP) methodologies run contrary to local care practices and result in an EBP straitjacket and epistemic injustice. These are serious concerns, especially in relation to already marginalised clients.Aims and objectives: Against the backdrop of criticism against EBP, this study explores the ramifications of the Swedish state-governed knowledge infrastructure, ‘management-by-knowledge’, for social care practices at two care units for persons with intellectual disabilities.Methods: Data generated from ethnographic observations and interviews were analysed by applying a conceptual framework of epistemic injustice; also analysed were national, regional and local knowledge products within management-by-knowledge related to two daily activity (DA) units at a social care provider in Sweden.Findings: In this particular case of disability care, no obvious risks of epistemic injustice were discovered in key knowledge practices of management-by-knowledge. Central methodologies of national agencies did include perspectives from social workers and clients, as did regional infrastructures. Locally, there were structures in place that focused on creating a dynamic interplay between knowledge coming from various forms of evidence, including social workers’ and clients’ own knowledge and experience.Discussion and conclusions: Far from being a straitjacket, in the case studied management-by-knowledge may be understood as offering fluid support. Efforts which aim at improving care for people with disabilities might benefit from organisational support structures that enable dynamic interactions between external knowledge and local practices.<br />Key messages<br /><ul><li>Examining one case of disability care in Sweden, both social workers’ and clients’ experiences were included in EBP infrastructures.</li><br /><li>In this study, Swedish EBP infrastructures functioned more like fluid support than a straitjacket.</li><br /><li>Organisational structures that combine different knowledge sources at service providers can minimise the risk of epistemic injustice within social care.</li></ul>

Enacting Ought: Ethics, Anti-Racism, and Interactional Possibilities

Focusing on political and interpersonal conflict in the U.S., particularly racial conflict, but with an eye to similar conflicts throughout the world, we argue that the enactive approach to mind as life can be elaborated to provide an exigent framework for present social-political problems. An enactive approach fills problematic lacunae in the Western philosophical ethics project by offering radically refigured notions of responsibility and language. The dual enactive, participatory insight is that interactional responsibility is not singular and language is not an individual property or ability, something that someone simply and uniformly 'has' or 'controls'. These points have not been integrated into our self-understanding as moral actors, to everyone’s detriment. We first advocate for adequate appreciation of Colombetti and Torrance’s 2009 suggestion that participatory sense-making necessarily implies shared responsibility for interactional outcomes. We argue that the enactive approach presents open-ended cultivation of virtue as embodied, contextualized, and dynamic know-how and destabilizes an individualist metaphysics. Putting this framework to work, we turn to the interactional challenges of conversations that concern differences and that involve potentially oppositional parties, offering a reading of Claudia Rankine’s Just Us. Finally, we make explicit Rankine’s normative project of mindful navigation of multiple perspectives in an interaction. We abstract three interrelated spheres of participatory intervention: location, language, and labor. These also indicate routes for empirical investigation into complex perspective-taking in dynamic interactions.

The Capability Approach in Epidemiological Studies

Population epidemiology is the science that deals with disorders and certain conditions at the population level, i.e. at the macro-level. In contrast to experimental studies, the scientist in epidemiology cannot manipulate conditions to make studies of associations as pure as possible. The science of epidemiological studies examines the occurrence of diseases, risk and protective factors for diseases, and the prognosis of different disorders and conditions in different populations. The capability approach is an ideal framework for epidemiological studies because it captures the dynamic and multiple processes involved in these types of studies, in relation to both time and space, as well as socioeconomic, psychological and biological factors. Determinants for common disorders and conditions include complex interactions among a multitude of factors acting between and within macro-, meso- and micro-levels during the life-course of an individual. In this chapter, we will discuss how the capability approach can be used in epidemiology in general, and in old age in particular, giving examples from specific conditions, such as cognitive function and dementia, depression, multimorbidity and functional ability, and non-modifiable and modifiable risk factors, such as genetics and nutrition. We conclude that the capability approach is a valuable tool in epidemiological studies. In these types of studies, capability is the final outcome of the dynamic interactions between a multitude of factors at the micro-, meso- and macro-levels leading to disorders and other conditions, which leads to restrictions in the individual’s ability to perform actions in order to reach goals he or she has reason to value.

Foundations' Civic Engagement With Stakeholders

Nonprofit organizations often adopt social media such as Facebook to encourage stakeholders to engage in the organizational mission. Calls to action via social media tend to reach subscribers who “like” or follow the organization via one-way communication. Researching effective approaches to dialogic communication, which asks followers to engage rather than observe, the authors focus on relationship management theory (RMT). RMT stresses organizational-stakeholder dynamic interactions. Using a quantitative modeling approach, the authors examine Facebook posts made by three different types of foundations (community, corporate, and independent) to determine how foundations call for stakeholder engagement. To date, few studies focus directly on types of posts and the response, or lack of response, to organizational messages via social media. Civic engagement requires action on the part of the stakeholder to address social problems. Defining participation and engagement varies by field and types of interaction. This research contributes to literature examining the “digital citizen.”

Introduction

This chapter serves as an overview of the book and orients readers to subsequent chapters. It provides major contexts for networked collective actions and offers a quick look at the emergence of nontraditional intermediaries and their dynamic interactions with traditional intermediaries. Then the chapter introduces South Korean citizens’ candlelight vigils in 2016 and 2017 calling for the impeachment of President Park Geun-hye and discusses how the impeachment example is an instance of the complex changes being observed in collective actions facilitated by digital communication technologies. The chapter briefly explains theoretical and methodological approaches used in this book in analyzing the intricate relationships between various agents (e.g., individuals, institutions, bots/algorithms) and their interactions with relevant affordances during South Korean citizens’ candlelight vigils demanding Park’s impeachment. The chapter ends with a brief summary of the focus of subsequent chapters.