kara-branding-1.jpg

KARA: A Conversational User Interface for Ambulances Research and Design Case Study

Emergency medical technicians have clear protocols for managing emergency situations and stabilizing patients, but stress happens during transport. Whether it is the actions of others outside the ambulance, not knowing about road closures, or unforeseen conditions at the scene, medics deal with a lot of unknown variables. 

KARA is a conversational agent that augments the foresight capacity of emergency transport personnel in these moments of uncertainty, through shared logic, memory, and responsibility with the medics to safely transport patients.

 

Team: Catherine Shen, Kate McLean, Shruti Aditya Chowdhury
Contributions: Designing research workshops, concept generation, prototyping, UX design and demo, branding and visual design
Advisors: Peter Scupelli, Bruce Hanington


Proposed Solution


Process

Background—Human-Computer Symbiosis
Conversational user interfaces (CUIs) are positioned to change the way we interact with technology on a day-to-day basis. As part of the Microsoft Design Expo, our project brief was design a future solution that demonstrates the value of CUIs in building a symbiotic relationship between humans and machines, keeping in mind J.C.R. Licklider’s definition of human-computer symbiosis.


Exploratory Research

Territory exploration
We started by identifying an opportunity and territory for further investigation. With the advances in technology for driverless vehicles, we saw an opportunity to design conversational user interfaces that could make people feel more comfortable in these environments. We began scoping the design challenge by choosing a user group to focus on.

01-13 — Intro.jpeg

Identifying an opportunity space
After speaking with various stakeholders, we brainstormed multiple scenarios with different user groups and decided that emergency medical transport was a rich design opportunity for conversational user interface, human computer symbiosis, and autonomous driving technology.

How might CUIs play a role in the future of emergency transport?

 

Getting to know our users We spoke with a diverse range of emergency responders, from experienced EMTs to volunteer medics. Through over a dozen interviews, we sought to learn more about what the user journey and scenario look like.

Initial Insights
Emergency medical technicals (medics) are underresourced
Medics working in emergency transport are under a lot of stress
Medics working in emergency transport rely on systems, people, and themselves to navigate stressful, emergency situations.

In particular, we found that while being a medic is a high-stress job, medics often rely of protocols they've been trained to follow while actually dealing with patients. However, through our interviews, it surfaced that the most high-stress points of a dispatch call occur when the ambulance is in transit. There is a large number of unknown variables in these situations, and it is this uncertainty that requires foresight and quick decision-making.  


Generative Research

Ambulance Tour 
A touchstone tour of the inside of an ambulance to understand current interface and interaction challenges. We learned that even incremental multimodal interaction designs could seriously alleviate much of the issues associated with the current outdated and clunky systems. 

 

Workshops
We worked with multiple sets of participants doing the following activities

Ideal teammate collage 
To help us define the nature of the human-computer symbiosis. We learned that EMT teams function "more like a jazz band than an orchestra", and rely on each others problem-solving skills.

Journey mapping 
To understand stress points in a typical transport journey. We learned that moments of stress are associate with the uncertainties and unanticipated event that occur while in transit.

Role-play and Body Storming 
Participants show us what features and components they might like to see.

Debriefing
An informal conversation with the participants to gather reflections and brainstorm ideas.


Synthesis and Concept Generation

Having gathered a lot of information from this round of workshops, we had a team brainstorm session to identify themes and directions for a design concept. 


Ridealongs
We spent 16 hours doing ridealongs with EMTs which gave us a more empathetic view of their routines, challenges, coping mechanisms, and stresses. With these observations, combined with the resulting themes and directions, we brainstormed 100 CUI concepts, and then narrowed them down to 12 concepts which we storyboard.

Speed-datings using storyboards
We then took these storyboards back to our participants through a second workshop using speed dating to elicit feedback and card sorting to understand priorities.

Through this activity, we discovered that our users weren't looking for direct stress relief so we realized that our design would have to incorporate this indirectly.


Prototyping and Evaluation

We developed a Wizard of Oz style of prototyping 3 different scenarios with 15 touchpoints across the user journey to test the relevance and authenticity of the concepts, the forms of multi-modal feedback and how they would use a system like this individually, in pairs and across the larger organization of the EMS. 

We focused our designs to three main scenarios supported by design principles and various heuristics. Kara embodies a symbiotic relationship through co-action. Through shared logic, memory, and responsibility within an ambulance, Kara helps EMS personnel complete their missions, managing unknown risks and stresses along the way.


Interface

Kara is a unique solution for a symbiotic relationship with ambulance drivers, using conversation as a means to augment foresight and help drivers accomplish their transport tasks with the least stress possible.

Kara’s unique capability of sharing logic, memory, and responsibility with EMS personnel alleviates unnecessary stresses and prevents worst case outcomes. Through a multi-modal, primarily conversational interface, Kara contributes to emergency transportation task-based problem-solving with real-time contextually relevant information provided through hands-free, eyes-free means.