Supporting Complex Tasks Using Multiple Devices

Intelligent digital assistants help people perform simple tasks such as question answering, event scheduling, etc. Complex task assistance requires monitoring goals, intentions, and task state. Additionally, complex tasks may exceed the capabilities of one single device or application, giving rise to the need to support people as they engage with two or more devices (e.g., smartphones, smart wearable devices, tablets, and desktop or laptop computers) simultaneously. Using multiple connected devices to support tasks has now become a viable design option for digital assistance since many users already own multiple devices. In this paper, we introduce a framework for developing multiple device experiences (MDX), then demonstrate some of the early capabilities of the framework by means of the AskChef cooking assistant. AskChef allows people to use their existing mobile devices (e.g., tablets), together with existing headless smart speakers (e.g., the Amazon Echo) for rich step-by-step guidance and contextual question answering over the culinary recipe loaded in their mobile device’s web browser. We conducted a pilot study in which people engaged in cooking recipes with the AskChef MDX system. All participants reported finding the support to be helpful, and indicated a willingness to use the system in the future. Nevertheless, AskChef erred on occasion, affording an opportunity to study how people respond to errors in multi-device scenarios. We examine participants’ perceptions and actions, and outline some directions for future research.

[1]  Alex X. Liu,et al.  The Insecurity of Home Digital Voice Assistants - Amazon Alexa as a Case Study , 2017, ArXiv.

[2]  Bernt Schiele,et al.  A database for fine grained activity detection of cooking activities , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Katarina Segerståhl,et al.  Crossmedia Systems Constructed around Human Activities: A Field Study and Implications for Design , 2009, INTERACT.

[4]  Abigail Sellen,et al.  "Like Having a Really Bad PA": The Gulf between User Expectation and Experience of Conversational Agents , 2016, CHI.

[5]  Richard A. Bolt,et al.  “Put-that-there”: Voice and gesture at the graphics interface , 1980, SIGGRAPH '80.

[6]  Timothy Brittain-Catlin Put it there , 2013 .

[7]  Dan Brickley,et al.  Schema.org: Evolution of Structured Data on the Web , 2015, ACM Queue.

[8]  Y. Wilks Is a Companion a Distinctive Kind of Relationship with a Machine? , 2010 .

[9]  Jeffrey Nichols,et al.  Understanding the Challenges of Designing and Developing Multi-Device Experiences , 2016, Conference on Designing Interactive Systems.

[10]  Simon Ostermann,et al.  Ingredients and Recipe for a Robust Mobile Speech-Enabled Cooking Assistant for German , 2013, KI.

[11]  Stefan Kopp,et al.  A Conversational Agent as Museum Guide - Design and Evaluation of a Real-World Application , 2005, IVA.

[12]  Ryen W. White Skill discovery in virtual assistants , 2018, Commun. ACM.

[13]  Jichen Zhu,et al.  Patterns for How Users Overcome Obstacles in Voice User Interfaces , 2018, CHI.

[14]  Sarah Sharples,et al.  Voice Interfaces in Everyday Life , 2018, CHI.

[15]  J. C. R. Licklider,et al.  Man-Computer Symbiosis , 1960 .

[16]  Adam Fourney,et al.  Exploring the Role of Conversational Cues in Guided Task Support with Virtual Assistants , 2018, CHI.