Automating cleaning for Roomba users
Building an experience around cleanliness predictions unlocked the ability for Roombas to automatically decide which rooms needed to be cleaned and how best to clean them.
ROLE + TEAM
Principal Product Designer; Led UX on a team of product management, research and engineering leaders, as well as UI designers & a copywriter. Responsible for driving the UX discovery, rapid prototypes and testing to a production release.
TOOLS
Figma, FigJam, Miro, DScout, Usertesting.com
SKILLS
Storyboarding, User Interviews, Rapid Prototyping
DELIVERABLES
New feature, Dirt Detective, released in early 2024 with follow up improvements to be released in Q1 2025
CONTEXT
iRobot users purchase Roombas to take cleaning off their to-do list and simplify the path to a clean home.
We knew from prior research that people tend to think about where they want to clean before how or what tool they’ll use: "I need to clean the kitchen" versus "I’m going to run my Roomba today."
The original iRobot app started as a single page, centered around Roomba control.
​
While our products handle the physical act of cleaning, this model left the user to decide where, when, and how to clean manually.​
As more of our new products came equipped with mapping capabilities and intelligent features, we saw an opportunity to leverage that intelligence to automate cleaning decisions for our users.
KEY INSIGHTS
Early discovery work uncovered insights about how we can better meet user expectations.
01
Match Users' Approach to Cleaning
Align with how users think about cleaning: where first, how second.
02
Offload the Mental “To-do” List
Minimize to-do lists, don’t just replace household tasks with device management.
03
Create a Frictionless Experience
Alert users when actions are required, don’t require users to check in with the app.
04
Build a Partnership with Users
Collaborate with users to achieve cleaning goals.
We decided to create an intelligent system, centered around spaces in the home, automating where, when and how to clean.
I created storyboards to architect these ideas & tested them with users to see what concepts resonated most.
We walked through 6 storyboards in a series of user interviews. We asked users to rank the stories they found most advanced, most helpful and most exciting, and also asked them to share any thoughts, feelings and reactions to the stories.​
​
-
People were generally excited to see their robots working autonomously in the home, and were comfortable collaborating with them.
-
Despite a strong interest and trust in our intelligence, most users still wanted an option to override the robot when needed
-
Device integration was a nice to have, but did not spark as much excitement as we had guessed it might
With those ideas in mind, I created a series of loose wires to iterate on these broader concepts.
Wires quickly turned into hundreds of rapid low-fi prototypes focused on exploring different ways to present cleanliness insights in a useful way.
We tested each phase of these designs iteratively with users.
Here’s a progression of how the experience evolved over time.
We tested various heatmaps, color schemes, scoring systems - from granular numerical scores to emojis. We tested options that surfaced the why behind the prediction - our back end can identify a closed door, as well as obstacle types.
Our testing showed that the map visualization of cleanliness was intuitive for users to understand. While most users believed in our intelligence, most still wanted the ability to override our predictions and create their own routines, confirming the delicate balance between automation and control.
Ultimately we went with a simple, easy to scan visualization of dirtiness by room paired with the ability to clean them directly.
INTRODUCING: DIRT DETECTIVE​
​
Cleanliness predictions, powered by the Dirt Detective algorithm, introduced the ability for Roombas to automatically decide if rooms needed to be cleaned, and prioritize them based on cleanliness.
Cleanliness Predictions
The new My Home tab featured a real-time map of predicted home cleanliness, giving users a one button way to clean dirty rooms.
Home Settings
By asking users about secondary factors in their home we could train our intelligence to more accurately reflect ground truth.
This was an industry first, and a huge step towards a truly autonomous and goal driven robot, rather than an appliance that simply waits to be told what to do.
WHAT'S NEXT?
As we move into 2025 we will continue focusing our efforts on bringing users a space-centered, intelligent app purpose built to simplify their path to a clean home.
Smart Cleaning Settings
In Q1 2025, we will offer Smart Cleaning Settings to automatically choose options like vacuum suction level, mopping strength and number of passes based on predicted cleanliness of the space.
Smart Notifications
Situations come up where we need users’ help to ensure we can keep their homes clean.
We have designed a out-of-app notifications strategy to provide clear and actionable requests for assistance when needed, further building a partnership with our users.
