Team reactions to voiced agent instructions in a pervasive game

Moran, Stuart; Pantidi, Nadia; Bachour, Khaled; Fischer, Joel E.; Flintham, Martin; Rodden, Tom; Evans, Simon; Johnson, Simon

doi:10.1145/2449396.2449445

Cited by 17 publications

(17 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research around these experiences often reports on issues relevant to the CSCW community, such as 'live' orchestration from a control room [13], collaboration between people on the ground and online [18], and giving and following instructions in teams [50,44]. Some of these experiences may also have an educational character [51], or they may be classified as a 'serious' game, for example to study team coordination in a disaster response scenario [17].…”

Section: Mobile Collocated Experiencesmentioning

confidence: 99%

Designing Mobile Experiences for Collocated Interaction

Lundgren

Fischer

Reeves

et al. 2015

Proceedings of the 18th ACM Conference on Computer Supported Cooperative Work &Amp; Social Computing

Self Cite

View full text Add to dashboard Cite

Many of our everyday social interactions involve mobile devices. Yet, these tend to only provide good support for distributed social interactions. Although much HCI and CSCW research has explored how we might support collocated, face-to-face situations using mobile devices, much of this work exists as isolated exemplars of technical systems or interaction designs. This paper draws on a range of such exemplars to develop a practical design framework intended for guiding the design of new mobile experiences for collocated interaction as well as analysing existing ones. Our framework provides four relational perspectives for designing the complex interplay between: the social situation in which it takes place; the technology used and the mechanics inscribed; the physical environment; and the temporal elements of design. Moreover, each perspective features some core properties, which are highly relevant when designing these systems. As part of presenting the framework we also explain the process of its construction along with practical advice on how to read and apply it.

show abstract

Section: Mobile Collocated Experiencesmentioning

confidence: 99%

Designing Mobile Experiences for Collocated Interaction

Lundgren

Fischer

Reeves

et al. 2015

Proceedings of the 18th ACM Conference on Computer Supported Cooperative Work &Amp; Social Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Controlled experiments designed by the Human Factors community have sought to identify key aspects of human-agent collaboration [10,15,57,60], propose transfer-of-control policies to shift control between humans and agents [52], and evaluate strategies of agent support for teams [33]. In particular, prior research has recognised that interaction design is vital for the performance of socio-technical human-agent systems [38], particularly where an agent directly instructs humans [37]. In particular, the latter argue that, with inappropriate interaction design, agent-based planning support may function inefficiently, or at worst, hinder the performance of human teams.…”

Section: Challenges For Human-agent Collaborationmentioning

confidence: 99%

“…Crucially, to date, while all of these algorithms have been shown to perform well in simulations, none of them have been exercised to guide real human responders in real-time rescue missions. In turn, studies on the deployment of such intelligent technologies in the real-world reveal that they typically impose a cognitive burden on the first responders [37,38] and disrupt task performance. Hence, it is important to develop real-world simulations of disaster response where such technologies can be trialled so that the interactional issues between humans and agents may be explored.…”

Section: Introductionmentioning

confidence: 99%

Human–agent collaboration for disaster response

Ramchurn

Jiang

et al. 2015

Auton Agent Multi-Agent Syst

Self Cite

View full text Add to dashboard Cite

In the aftermath of major disasters, first responders are typically overwhelmed with large numbers of, spatially distributed, search and rescue tasks, each with their own requirements. Moreover, responders have to operate in highly uncertain and dynamic environments where new tasks may appear and hazards may be spreading across the disaster space. Hence, rescue missions may need to be re-planned as new information comes in, tasks are completed, or new hazards are discovered. Finding an optimal allocation of resources to complete all the tasks is a major computational challenge. In this paper, we use decision theoretic techniques to solve the task allocation problem posed by emergency response planning and then deploy our solution as part of an agent-based planning tool in real-world field trials. By so doing, we are able to study the interactional issues that arise when humans are guided by an agent. Specifically, we develop an algorithm, based on a multi-agent Markov decision process representation of the task allocation problem and show that it outperforms standard baseline solutions. We then integrate the algorithm into a planning agent that responds to requests for tasks from participants in a mixed-reality location-based game, called AtomicOrchid, that simulates disaster response settings in the real-world. We then run a number of trials of our planning agent and compare it against a purely human driven system. Our analysis of these trials show that human commanders adapt to the planning agent by taking on a more supervisory role and that, by providing humans with the flexibility of requesting plans from the agent, allows them to perform more tasks more efficiently than using purely human interactions to allocate tasks. We also discuss how such flexibility could lead to poor performance if left unchecked.

show abstract

“…Prior work in pervasive and urban games has explored elements of collocated interaction such as ''live'' orchestration from a control room through digital communication [12,30], collaboration between people on the ground and online [4], giving and following instructions in teams [37], and successfully merging physical and virtual play [4,11,46]. Can You See Me Now?…”

Section: Related Workmentioning

confidence: 99%

Expanding social mobile games beyond the device screen

Sra

Schmandt

2015

Pers Ubiquit Comput

View full text Add to dashboard Cite

Emerging pervasive games use sensors, graphics and networking technologies to provide immersive game experiences integrated with the real world. Existing pervasive games commonly rely on a device screen for providing game-related information, while overlooking opportunities to include new types of contextual interactions like jumping, a punching gesture, or even voice to be used as game inputs. We present the design of Spellbound, a physical mobile team-based game, to help contribute to our understanding of how we can design pervasive games that aim to nurture a spirit of togetherness. We also briefly touch upon how togetherness and playfulness can transform physical movement into a desirable activity in the user evaluation section. Spellbound is an outdoor pervasive team-based physical game. It takes advantage of the abovementioned opportunities and integrates real-world actions like jumping and spinning with a virtual world. It also replaces touch-based input with voice interaction and provides glanceable and haptic feedback using custom hardware in the true spirit of social play characteristic of traditional children's games. We believe Spellbound is a form of digital outdoor gaming that anchors enjoyment on physical action, social interaction, and tangible feedback. Spellbound was well received in user evaluation playtests which confirmed that the main design objective of enhancing a sense of togetherness was largely met.

show abstract

Team reactions to voiced agent instructions in a pervasive game

Cited by 17 publications

References 14 publications

Designing Mobile Experiences for Collocated Interaction

Designing Mobile Experiences for Collocated Interaction

Human–agent collaboration for disaster response

Expanding social mobile games beyond the device screen

Contact Info

Product

Resources

About