Close
0%
0%

DIY e-kayak

The e-bike of kayaks. My AI powered kayak will detect if the user is turning left or right and automatically assist with the electric motor

bare-naked-embeddedBare Naked Embedded
Following
Liked Like project

Just one more thing

To make the experience fit your profile, pick a username and tell us what interests you.

Pick an awesome username
hackaday.io/
Your profile's URL: hackaday.io/username. Max 25 alphanumeric characters.
Pick a few interests
Projects that share your interests
People that share your interests

We found and based on your interests.

Choose more interests.

OK, I'm done! Skip
Public Chat
Similar projects worth following
497 views
0 comments
1 followers
View Gallery
Public Chat
I am setting out to build the e-bike of kayaks! The kayak will be able to determine when the user is paddling and automatically turn on the electric motor to assist. Further, I'll train an ML model to detect if the user is trying to turn left or right. The ML model will use IMU (Inertial Measurement Unit) data from the oar trained against GPS data on the kayak to determine this.

To date I have successfully shown I can build the e-kayak hardware for under $1,000. Reaching speeds nearing 5 mph with a range of about 16 miles, I'm super happy with the performance.

I have now created a controller which clamps to the paddle. This controller commands speed, shows battery indication and tracks the paddle position in space.

I am nearly ready to tackle the main goal of this project, machine learning on the edge!! Stay tuned.

This project is broken into four main parts:

Part 1:

Part one was the proof of concept phase. The goal of this phase was to prove I could build an electrified kayak for under $1,000 that was practical and functional to use. I created the first prototype for about $650. 

Part one is complete

Part 2:

Part two of the project was to clean up the part one prototype into a more usable form factor and pave the way for end goal features. These features include paddle assist machine learning, GPS way points and direction control. 

Part two is complete

Part 3:

Part three is wrapping up loose ends of part two. Part two created the final form factor hardware and firmware but it is largely untested in the field. Part three will involve hardening the design based on real life field testing. It will also include implementing any features that are dependent for paddle assist. This mainly includes the GPS module.

In Work

Part 4:

Implement full feature list including paddle and direction assist with machine learning on the edge.

In Work

For an overview of the project, check out my YouTube series!!


  • Phase Three Complete

    Bare Naked Embedded • 06/05/2024 at 14:05 • 0 comments

    Hi all! Phase three is now complete. I was able to take the breadboarded prototype hardware and create some custom PCBs that all my breakout boards mount to. I also created a custom breakout board for the on/off controller IC from part two. This IC allows me to use a single button as a power switch and input button for controlling speed. 

    With the help of Jordan Godoy, we were able to finish the 3D printed housing and I have to say, it looks pretty awesome! 

    Right now, I have IMU data streaming from the paddle controller to the host Raspberry Pi. The Pi then logs all this data and I can create paddle animations to show how paddle tracking works. Next, I need to get the Pi commanding my motor controller. Then I'll hit the water!!

    Huge thanks to PCBWay for sponsoring the prints and PCBs for this phase of the project! 

    Check out my YouTube series!

  • Phase Two Prototyped

    Bare Naked Embedded • 04/01/2024 at 15:35 • 0 comments

    Just finished my second video! Build out all the oar controller hardware and firmware on the breadboard. This video walks through all the technical details!

    Next I'll be creating some PCBs to fit everything into the oar controller 3D printed housing!

  • Phase One Complete

    Bare Naked Embedded • 12/25/2023 at 20:00 • 0 comments

    Read the full details on my personal blog!  https://barenakedembedded.com/diy-electric-kayak/ 

    Phase one of the project was the proof of concept. It showed I could build an e-kayak for under $1,000 that could travel at a walking pace with a range of at least 2 hours. 

    I ended up with a range of ~16 miles (4 hours) and a max speed of ~4.5 mph. I was super happy with the results and learned a lot through my first round of testing! Next step is to get my computer out of my lap and build up the oar hardware cluster!

View all 3 project logs

Enjoy this project?

Share

Discussions

Similar Projects
Project Owner Contributor

Urban VAWT

warren-janssensWarren Janssens

I have trained wild magpies in my Garden to trade litter for food! The whole project relies on mechanical design, electronics, software and
Project Owner Contributor

BirdBox

hfor62hfor62

Upgrades for my previous RC car project
Project Owner Contributor

YaRC Vehicle V4

welters-hackzWelters Hackz

Receiving 1.7GHz HRPT signals from NOAA satellites
Project Owner Contributor

Dish Rotator for NOAA images

johannesJohannes

Does this project spark your interest?

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

Going up?

About Us Contact Hackaday.io Give Feedback Terms of Use Privacy Policy Hackaday API

© 2024 Hackaday

Yes, delete it Cancel

Report project as inappropriate

You are about to report the project "DIY e-kayak", please tell us the reason.

Send message

Your application has been submitted.

Remove Member

Are you sure you want to remove yourself as a member for this project?

Project owner will be notified upon removal.