Designing a UX experience for a system designed to manage fleets of autonomous vehicles


*This project is under NDA hence the complete project cannot be shared and certain images are blurred




Experience Brief:
SAM software partners in-vehicle artificial intelligence (AI) with remote human support to help driver less autonomous vehicles make decisions in unpredictable situations such as obstructions on the road. My role was to come up with new interface concepts to facilitate interactions between the user and the AI driven software.

Duration:

8 Months

Team: 


Laura Cesfasky: UX researcher                 Omar Benthar: AI researchers
Viju James: Developer                                  Sparsh Sharma: UI design intern

My Role:
In this project I worked on creating UX Information Architecture, UX for AI functions, Wireframing, Interaction model design, AI frameworks to prioritize information, basic prototyping and user testing




Final design impact





Improved the average time to solve roadside cases for autonomous vehicles from 45 seconds to 22.5 seconds


AI concepts explored

1. User X Data relationship

2. Human + AI teaming principles

3.  Explainable AI (X.AI) concpets

4. Information architecture





More about the software







"Seamless Autonomous Mobility (SAM)" system developed in collaboration with NASA to realize a fully autonomous mobility. It partners in-vehicle artificial intelligence (AI) with remote human support to help driver less autonomous vehicles make decisions in unpredictable situations such as obstructions on the road.





Construction of the software


The user interacts with both screens





Experience gap while using SAM software










Usecase to design for










Obstruction use case:


The AV stops behind an stopped obstruction and
calls the user to help it overtake the obstacle.








Goal of redesigning SAM




The goal of redesigning the SAM system was to answer: 

“ How to balance the human need for meaningful engagement with AI technology with the need to minimize labor cost by getting the user situationally aware efficiently and accurately?”







Process followed to redesign











User X Data relationship for Obstruction use case

Motivation of exploring this framework:
1. To define what kind of information is useful for the user to know.
2. Prioritizing the information based on the need of user, which can impact both accuracy and speed of solving the problem.









Wireframing


Showing the interaction of going thru an Obstruction usecase









Information Architecture


The flow of information for the user as they solve the Obstruction usecase




Impact of the redesign

Reduced the average time to solve the cases from 45 seconds to 22.5 seconds






This design is fully developed and is part of the S.A.M system