Steering the conversation: A linguistic exploration of natural language interactions with a digital assistant during simulated driving

Abstract

Given the proliferation of 'intelligent' and 'socially-aware' digital assistants embodying everyday mobile technology - and the undeniable logic that utilising voice-activated controls and interfaces in cars reduces the visual and manual distraction of interacting with in-vehicle devices - it appears inevitable that next generation vehicles will be embodied by digital assistants and utilise spoken language as a method of interaction. From a design perspective, defining the language and interaction style that a digital driving assistant should adopt is contingent on the role that they play within the social fabric and context in which they are situated. We therefore conducted a qualitative, Wizard-of-Oz study to explore how drivers might interact linguistically with a natural language digital driving assistant. Twenty-five participants drove for 10 min in a medium-fidelity driving simulator while interacting with a state-of-the-art, high-functioning, conversational digital driving assistant. All exchanges were transcribed and analysed using recognised linguistic techniques, such as discourse and conversation analysis, normally reserved for interpersonal investigation. Language usage patterns demonstrate that interactions with the digital assistant were fundamentally social in nature, with participants affording the assistant equal social status and high-level cognitive processing capability. For example, participants were polite, actively controlled turn-taking during the conversation, and used back-channelling, fillers and hesitation, as they might in human communication. Furthermore, participants expected the digital assistant to understand and process complex requests mitigated with hedging words and expressions, and peppered with vague language and deictic references requiring shared contextual information and mutual understanding. Findings are presented in six themes which emerged during the analysis - formulating responses; turn-taking; back-channelling, fillers and hesitation; vague language; mitigating requests and politeness and praise. The results can be used to inform the design of future in-vehicle natural language systems, in particular to help manage the tension between designing for an engaging dialogue (important for technology acceptance) and designing for an effective dialogue (important to minimise distraction in a driving context).

Driven to discussion: engaging drivers in conversation with a digital assistant as a countermeasure to passive task‐related fatigue

“…Consequently, common linguistic techniques, such as back-channelling, fillers, vague language, hedged requests etc. [34] could be utilised and understood (by both parties). While the responses and capability of Vid may therefore not be truly representative of future talking technology, or indeed, designers' aspirations for such, it was a necessary approach to create a 'plausible' digital assistant.…”

“…Vid introduced itself to participants before they began driving, and initiated conversation using the same opening gambits for each participant (see examples in Table 1). These were selected to represent likely interactions with a digital driving assistant, based on discussions with industry experts, and have been used in several other similar studies (see: [33,34]). All interjections were designed to invite a response from participants, but did not necessarily demand a detailed reply.…”

A Survey of Autonomous Driving: Common Practices and Emerging Technologies

“…However, in vehicle domain there are additional challenges; low performance caused by uncontrollable cabin conditions such as wind and road noise [268]. Beyond simple voice commands, conversational natural language interaction with an ADS is still an unrealized concept with many unsolved challenges [269].…”

Speech Interfaces and Pilot Performance: A Meta-Analysis

“…The system anthropomorphization did not stop at perceptions of the system; in automation studies with speech input, users altered the way they interacted with the system to include emotion and social niceties. One study of such a system in a driving simulator saw operators employ politeness in response to the system requesting input, and praising and thanking it in response to confirmation of simple tasks such as setting the radio (Large, Clark, Quandt, Burnett, & Skrypchuk, 2017). One can assume it is a comparably rare occasion in which an airline pilot says "thank you" to the traditional knob-and-indicator autopilot for reaching an assigned altitude.…”