Close
0%
0%

Hackaday Prize Entry: AVATIFY

Desktop Buddy 4 Time Management AI (Web App) to get out of your Procrastination-Trap

Similar projects worth following
Most People Neglect Planning, because they think it is more effort to plan and do instead of just do. But it often reveals as a trap: You procrastinate or you waste time waiting or forget about them.

To solve this problem, I want something which does not interfere by other functionalities like a smartphone, but a device solely focusing on to tell you "what to do next" and "keep track" of it and ultimately help you manage your life.

There are figures, which shows people pay more attention to robots, or better: Personified Things. So i personified a "pocket watch" to an avatar, from which derives the word "Avatify".

Now with the new version (7th version) I am ready (=motivated) to do the web app stuff.
Feel free to join the project, I will appreciate any help.

This is exactly what Avatify does:

"What we need at most is a person, who forces us to do what we can do" (Ralph Waldo Emerson)

And thus my motto:

There's no style, wasting time.
There's no style, neglecting one's health.
Style is stop wasting with Avatify.

Planning is a complex task, thus often neglected.

It is "complex", because it requires focus, which means it is a task done by the neo-cortex.

The tasks done by neo-cortex is logic but slow and power-consuming.

Furthermore most of the planning process consists of rescheduling periodically repeated tasks.

Therefore I wrote a program that calculates automatically the complex frequencies in which tasks are repeatedly done.

Repetition of Action is called habit. And everyone knows that forming a good habit is very difficult. This is for one, you cannot "track" it, so you have a overview of your actions. Secondly, long-termed actions need to be integrated in daily plans, which the cubic robot „reminds to the opportunity“ to execute your resired habits. According to reinforcement learning, emotional feedback is valued most (social support), therefore the smiling face.

In near future I am planning to create an entire web-app, iOS-app and Wearable.


In the near future, to be more invasive into the daily life, to stick to the plan: It will have a 128x64 OLED display, HM-10 BLE module , heart-beat sensor, MPU6050, and a vibration motor.

First UART-Tests with the BLE-Module was successful, now I am trying to use the AT-Commands to configure it as TYPE3-Connection, which is the "Pairing" mode.

For the enclosure I choosed a TPE Flexible Filarment from SainSmart, tried it out with a cheap 3D Printing pen, but it didn’t go well, so I’ll buy one for myself.

There is also an update regarding the software. Now I have a very clear vision, what this machine should do:

If you consider my project is being called Avatify, consisting of the words „avatar“ and „…fy“, which means to convert sth. to an avatar.

WHAT do we convert to an avatar? Your Goal-Management. You need to break your goal down into smaller pieces.

These „smaller goals“ need to be also broken down, until a list of Todos remains.

This Todo-list will be scheduled into a monthly, weekly, daily plan.

The planning process contains more than the word „breaking down“ to explain.

Firstly the program supports you find your goal by stating it clearly. Then you will be asked to classify a importance to it, which could be machine guided.

Secondly, all the data of the former step from all the users will be used anonymously as a crowd sourcing mechanism, to suggest in which smaller parts your goal could be broken down.

Thirdly, due to the crowd sourced data, which represents „experience“ , the cost for each goal and step can be estimated more precisely.

At last, the system communicates with you to find out how frequent you want to do such a task. This information is passed to a scheduler.

This scheduler works feedback-based, which is the crucial part of Avatify.

Providing a Planning Software is not enough to ensure to accomplish one’s goal, because every plan requires adjustments.

These parts can be done by a computer easily, because it is a „logical“ task. But a real feedback of the plan is not just „done“ or „not done“. A better feedback would be you are happy or not.

Therefore your personal avatar will be happy to see you succeeding. This is the basic principle, and the system will be able to evolve more complex emotions in order to keep your brain and heart connected.

Due to the feedback mechanism, you aren’t just motivated, but your plans are kept realistic.

Open Source Tools I'm using under the following terms.
Arduino

WordNet

Node.js
Swift

NLTK

SCIKIT

PYTHON

avatify_v5.stl

unfinished

Standard Tesselated Geometry - 145.39 kB - 07/01/2016 at 15:51

Download

IMG_0453.MOV

Pitch

quicktime - 38.14 MB - 05/29/2016 at 14:54

Download

eliza.png

very conceptional design of the primary interaction system

Portable Network Graphics (PNG) - 191.59 kB - 05/29/2016 at 13:25

Preview
Download

softwareConcept.png

rought design and capture of the idea. Not ready to programme

Portable Network Graphics (PNG) - 450.95 kB - 05/29/2016 at 13:06

Preview
Download

Portable Network Graphics (PNG) - 583.46 kB - 04/23/2016 at 12:17

Preview
Download

View all 6 files

  • 1 × HM-10
  • 1 × Arduino Mini
  • 1 × 128x64 OLED display (I2C)
  • 1 × Silent Vibration Motor
  • 1 × MPU6050

View all 9 components

  • Goal Finder (interact, process, share)

    KennyAwesome05/29/2016 at 13:38 0 comments

    A fact: A person needs 3 things:

    1) Goal

    2) Plan

    3) Todo

    But it's rare to have them all, because these are logical and thus requiring focus and conscious thinking. This is for many people very difficult. Therefore, the avatify-programme does that for them.
    In this log, i will discuss the 1) Goal part.

    PART A (Eliza)


    To make this possible, we need interaction. This interaction will be based on Eliza-System by Weizbaum, but with different questions. The 4 core questions will be:
    - What do you want to achieve?
    - Why do you want to achieve it?
    - How important is it to you?

    - Does it have a deadline?

    The Following is less scientific, but I assume it will work that way, on which I will be working on the next few months.


    PART B (NeuronPool)

    All these input will be stored as a corpus and will be fed to the "NeuronTranslator".
    It connects the many artificial feature-neurons like Part-of-Speech-Neurons and ontology-knowledge-base-neurons and wordnet-neurons. According the connection and their strength of bond, the inputted information will be stored implicitly. This means, at the time, we connect the translated new neuron-chunk to the existing local neuron-knowledge-base, there will be a "spike-wave" through the local neuron-knowledge-base. At some point it will stop propagating. The "border" where it stops is the meaning/interpretation/semantics of the input.
    So if we pushed artificially the border +1, there will be a semantic prediction or suggestion. By doing this, the input to the system is kept at minimal and through suggesting, getting the significant idea will be easy as pie for the user.

    PART C (Crowd Sourcing)

    In part B I mentioned "local neuron-knowledge-base" meaning the user-specific storage of the information. By correlating the inputs and suggestions of other users (anonymously) there can be extracted many relations specific to the domain of planning. But this requires an already annotated corpus, which I do not possess. First experiment will be a new years resolution, but I assume that it will not be sufficient.

    Therefore I will introduce "help-points" into my system. Basically, there is a global "job-hunting" list, which will be ranked by individual skills of each user. If there is a task, most suitable and the helping user is willing to help, he can earn such a point. The one, whom is helped, pays one or more help-point.

    Such a task could be to do the "border + 1" of Part B, if the system fails to predict. This is at is essence very simple and clear, which is the obligational part of crowd sourcing or micro-tasking.

    In a sum, the extracted relations and the humans supporting the system to improve and to extend, a "GLOBAL neuron-knowledge-base" can be created, which is the main goal of this software-module.

  • Planning The Software

    KennyAwesome05/29/2016 at 13:09 0 comments

    After few meetings and recruiting some new Mitstreiter (german: co-fighter) I have finally crystallized my ideas.

    I have devided into 3 major parts:
    1) Finding Goals
    2) The actual Planning and Feedbacking thingy

    3) some extras to make the life as less annoying as possible.

    Further details will be discussed in the upcoming project logs.

  • SmartTracker_Version1.1

    KennyAwesome04/23/2016 at 12:20 0 comments

    I made It rounder, with the parts inside. they are not fixed, allowing me to retrieve the parts, if nessesary.

    The eyes represents the emotional feedback.

    It also has a heart beat sensor on the back. Inside an MPU-6050 and hm-10.

    I am about to program it.

  • New Hardware: Wearable

    KennyAwesome04/13/2016 at 09:39 0 comments

    First Shot of a wearable design.
    Size limitation to the width: Display (30mm), Length: battery (45mm), height: sum up all the thickness and add 50% (aether ;) )
    If the electronic parts are fitted in, the thing printed out on 3D printer, did some basic programming for demo, I will post a video

View all 4 project logs

Enjoy this project?

Share

Discussions

Similar Projects

Does this project spark your interest?

Become a member to follow this project and never miss any updates