Pia is a conversational assistant for the Pittsburgh international airport providing a connected, single-stop solution for all travel queries. As a data-rich assistant, she connects the different pain points and facilitates a seamless experience for both the airport and its passengers. Commercial air travel can present a number of difficulties for everyday people, from figuring out the best way to get to the airport to tracking down staff and wrangling long lines once they're there. Pia's intelligent interfaces assist with air travelers' complex and time-sensitive needs, while giving airports the data they need to best deliver their services to those passengers. Pia's AI-driven mobile assistance connects travelers on the move, but in activating underused check-in kiosks in airports, she can also help travelers that have never been in that airport, don't have the app installed, or don't know the local language.

Overview

Flying commercially can sometimes be described as nothing more than a series of inconvenient events. From late or canceled flights, long lines, crowded terminals, appalling food, and a series of long procedures and steps right from leaving our homes to the point of boarding our flight, the current traveler experience can be complicated and disconnected. During our research, we considered pain points across experiences before the airport, at the airport, as well as post-travel engagement. Our design involved the development of form, motion, and style of a digital ecosystem for a conversational assistant.

Accessible on the Pittsburgh Airport's mobile app and kiosks, Pia's capabilities in and out of the airport include:

Intelligent transit suggestions

Transit options that are customized to match flight time and available real-time transit data.

Parking and payment assistance

Parking options with visibility on available spots and walking time to reach the gate. Voice secured access to saved payment options.

Proactive prompts

From carrying essentials, saving your parking information to helping you leave on time.

Location-based service discovery

Explore dining, shopping, and other service experiences near your departure gate or specified location.

Multilingual support

Recognize languages based on the starting prompt and assist.

Staff assistance

Reach out to the airport staff from any kiosk at the airport for easy assistance.

Assistance while leaving the airport

Find the quickest way to leave the airport.

Our Point of View

Our goal for this project was to identify unique contexts in which voice assistants could be leveraged to provide information across pain points in a fraction of a second. Additionally, we put a great amount of thought into designing user-centered conversations. We researched existing conversational and AI design guidelines to help inform our design and found ways to push these conventions forward, reapplying them to the new context of traveling.

Our Process

In developing Pia, we followed an end-to-end design process that involved cycles of research, ideation, prototyping, and reflection. Our process can be divided into 3 parts:

1. Identifying use cases and experiences across the travel journey

2. Building a personality and an identity for supporting the experience

3. Designing a digital ecosystem considering patterns across VUI interaction,

Research:

? Field study - Situating ourselves in the day-to-day working of the airport to observe and understand key tasks, stakeholder relations, and available digital interfaces.

? Artifact Review - Studying existing solutions in mobile apps and kiosks to identify design opportunities

? User Interviews - Identifying unaddressed and repetitive frustrations and pain points

Synthesis:

We began by mapping pain points across the travel journey and identifying intervention opportunities right from pre-airport, procedural and post-flight experiences. In particular, we identified that airport services are often opaque to travelers and everyone creates their own methods with getting to and around airports in order to avoid as much pain as possible. Many people dread spending extra time there and see little into what they can do there beyond their gate. Further, airports are often understaffed, which is especially difficult considering people might land in the middle of the night or not know the local language.

We then mapped out customer journeys where we identified features where PIA could help, or hand off to other systems in the air travel ecosystem, alongside the modalities through which users would interact with PIA to use the features (e.g., touch, voice).

Ideation:

With a clearer understanding of the problems we wanted to solve, we built storyboards and personas covering use cases for both seasoned Pittsburgh travelers as well as international passengers who were interacting with the airport for the first time. We detailed several scenarios to cover opportunities identified in traveler experiences, such as flight delays, missed connections, getting to and from the airport, asking for help, and figuring out how to spend your time there. We ultimately focused on two stories to communicate Pia's features, featuring a local frequent-flier who's light on planning and cuts it close on timing, and an international student who lands in the middle of the night and needs to get into town without the mobile app.

Prototyping:

During our prototyping phase, we ideated across both mobile and kiosk touchpoints making considerations across modes of interaction, and conversation history keeping in mind both software and hardware affordances provided by each.

Identity Design:

We were confident that a connected, smart assistant could help quickly collapse complex requests in these types of scenarios. And the experience research we did really drove how we thought about the personality, look, and feel of that assistant, which we wanted to communicate as decisive, responsive, and connected (rather than just friendly, whimsical, or human).

We also explored Pia's visual form by tapping into the existing visual affordances of mobility and intelligence to design how Pia looks, sounds and moves. Considering the symbol represented not just a static logo but an on-screen intelligence that communicates through its shape and sound, it was important to consider how each of our forms moved. Our final visual identity was chosen for invoking qualities of navigation and movement while providing versatile transformations. Our team also designed voice and conversation around task-oriented questions, prompted responses, and concise sentence structures to create a user-centered, AI-guided travel experience.

Graphic and Voice Interface Design:

We carefully considered how to balance touch modalities and voice interaction on Pia's interfaces. Through our research, we recognized that voice assistance could be an enormous benefit to travelers who are short on time and have their hands full. Pia's intelligence could collapse complex requests through speech and immediately connect to the relevant airport resources or information. However, while we developed interfaces that afforded instant connection to voice-led interfaces, we also created interfaces that could accommodate needs best served by touch navigation (e.g., for those in public spaces, dealing with personal information).

We studied interactions for other intelligent assistants (including Siri, Alexa, and others) to identify the patterns and interactions that would best suit our concept. We developed these into concept prototypes on both mobile and kiosk platforms, with an eye to the different needs of each. For example, kiosk users may be less familiar with the airport and its amenities, the local language, or even voice interface technology in general.

Stakeholders

For every passenger pain point, there is also an underlying airport pain point. Pia was therefore designed as an intelligent interface that optimizes passenger experiences across airports while also supporting operational staff. For example, as passengers may struggle with wayfinding, airports may have to spend more money to reevaluate their signage, include more languages, and get more staff to help direct lost travelers.

Direct stakeholders:

Direct stakeholders are passengers that engage directly with Pia either from their personal devices or on public airport kiosks. Anyone who has flown commercially can identify with a number of struggles in which they couldn't identify any resources to help. Living both on mobile and in kiosks, Pia is positioned to connect these passengers to what they need for a comprehensive and inclusive set of experiences.

Indirect stakeholders:

Beyond passengers, the efficacy of airport service impacts a number of indirect stakeholders as well. This may include partners, children, family, or friends who do not directly interact with Pia, but travel to and from the airport to pick up their loved ones. Internal teams working at the airport spend time and resources to improve their services, but may struggle to figure out how best to do that in such a unique environment. Those working at restaurant chains, service operators, and flight counters (whether in the airport or in other offices) are impacted on a daily basis by airports' abilities to organize and deliver services to the travelers who become their customers.

Impact and Importance

Most are more familiar with airlines than airports. They know everyday procedures for air travel, but seldom interact with service in the airport, and often don't get as much out of those experiences as they could. Typically, passengers see airlines as the face of air travel, even though they only cover a few touch-points such as booking, check-in, and boarding. Airports are connected to a greater share of the travel experience for which airlines don't have a presence, such as securing parking during your trip, finding dining or shopping before boarding, or finding a way into town after landing in a new city. Pia's connected assistance can fill in those gaps in travelers' experiences and help them more cohesively enjoy and benefit from the ecosystem around them, while hitting the marks in their travel itinerary.

These passenger experiences are always connected to staff & airport experiences, and Pia works to address them both head-on. Pia can give proactive suggestions to passengers, understand their needs, and route airport resources more intelligently to meet them. Predictive AI and shared data are essential for complicated systems such as those in airports to stay up-to-date with customer needs and keep their services visible and relevant. As airports strive to grow, get smarter, and work more sustainably, Pia can lift all of their services into a new tier of usability and efficacy, while enhancing engagement and connecting with the infrastructure around them.