sketch-city-street-cityscape-illustration-drawing-759233542.jpg
Picture20_edited.png

MiMi
 

Discover, Drive, Assist Learn,
replacing guiding dog


100% autonomous,
just like a self-driving car on sidewalks

guanxian.gif
83-835647_wave-black-and-white-computer-

Before

After

242e12c5180073807fc7ff2d5f244d1c.gif
map.PNG
images.png

Hey Jean!
Give me a moment, I will plan your trip!

" Hey MiMi, Take me to the nearest Starbucks "

Shortest route is 29 minutes away...
We will use metro
10 and metro 8.

" OK MiMi, Engage !"

Picture12_edited.png
blind-man.png
blind-man.png
guanxian.gif

Powered by AI

 

MiMi is an assistive technology that aims to bring back autonomy for VIs in their day to day mobility. It integrates several cutting-edge technologies such as robotics, deep learning and machine learning to solve four principal challenges:

 

  • Going to unknown places while having a sense of the surrounding environment

  • Detect and avoid obstacles

  • Detect and recognize guiding signs and

  • Move in full security and comfort.

 

 

feqtures_edited.jpg
CooperativeIcyCats-size_restricted.gif
1_WDh2Pua8RqxT-OIHmyoRHQ.gif

Learn
& Share

MiMi starts by learning about its users, their walking speed, habits and frequently visited places.
It also uses a combination of sensors and cameras to collect data points and generate 3D maps for the surrounding environment to enhance performance and reduce computational operations.

It memorizes routes, locations, building's entry doors, inside buildings and other objects of our daily life.


MiMi offers the possibility to share with the community 3D maps of places and defined routes. The user can also discover new places  and register POIs on the World Map and gain loyalty points. Maps could be sold on a marketplace.

1_NLnnf_M4Nlm4p1GAWrWUCQ.gif

Understand
& AutoDrive

MiMi recognizes obstacles (static or moving), avoid them and trace its trajectory in real-time. It drives the user from point A to point B in full autonomy, using embedded navigation systems.

 

Various classes of objects are detected and classified using Reconnaissance Algorithms such as vehicules, road and pedestrians signs, sidewalks, people, objects, animals, stairs, lifts, metro stations, bus stops and many more...

 

Intelligent assistance feature can also be triggered on demand to describe surrounding environment and allow users to navigate more safely and securely.

6e13104be2d4ace5be943d0cf26fa33a.gif

Interact
& Connect

Based on the trip plan and real-time situations, embedded navigation system traces or updates  best route as it integrates with smart city infrastructure through APIs. The user can know when a bus or a metro arrive, get live on=-trip information. Mimi exchanges information about traffic perturbations, public transport, bus stops, metro stations, taxi services etc. to keep the user informed of any changes. 

Users can also connect their canes together and have a walk, just like vehicles platooning. This feature enable blind people to enjoy a walk without having to worry about their security. They will have more time to talk with their friends or simply listening to a song.  

guanxian.gif

Navigation

MiMi is developed to assist a VI to go from point A (current location) to point B (final destination) with very little intervention.

 

MiMi uses maps services and integrates with smart city infrastructure through APIs to communicate and exchange information about traffic, public transport, bus stops, metro stations, taxi services etc.

guanxian.gif

 

Ideally, through a voice command, user will input the address where he/she wants to go; MiMi locates itself, plans the trip with best route possible. then engage after getting a confirmation.

 

During the trip, MiMi will find automatically its way to sidewalks or other pedestrians walking areas by tracing possible trajectories based on trained models and satellite images.

When encountering obstacles/dangers, MiMi will use its state-of-the-art stereo camera to measure distance to the objects (static/dynamic), provide shape, size and other relative information as input to calculate the maneuvering trajectory required to avoid the obstacle safely and fluidly.

 

In addition, it detects traffic signs and lights to facilitate and assist VIs in crossing intersections or finding stairs and elevators.

 

Simultaneously, MiMi predicts movement of dynamic objects such as cars, flow of people to increase users safety during navigation.

 

Gradient
logo-made-in-France.png

Designed to change your life
FOREVER

guanxian.gif

Modular & Convenient

Camera & laser sensors installed on the grip

makes MiMi multifunction

Screenshot 2021-12-02 164605.png
Foldqble.png

46 Rue de Meudon,

92100

Boulogne-Billancourt,

Paris,

France

© 2021 Association Vision Pour Tous, All rights reserved

Thanks for submitting!