FollowTracker Computer Vision Project

Daves Armoury

Updated 2 years ago

178

views

1

download
Classes (1)
tracker
Description

Having multiple robots work together is expanding as their abilities improve, but adding compute and sensor hardware to each one is expensive. Having one smart robot do all the advanced autonomy while others blindly follow it around is called “platooning” and can be a reasonable solution to this problem. Using this, we drive 2 comfy robots together with a single controller.

A YoloV5 network is trained to locate a tracker on another robot. Using a stereo camera, depth to that tracker is calculated and basic autonomy maintains a constant following distance. There are definitely better ways to do the following, but this way is simple to understand and a good starting project for anyone looking to get into AI or autonomous robotics!

https://www.youtube.com/watch?v=YfQvBd4r_QU https://github.com/davesarmoury/FollowMiniMe

Supervision

Build Computer Vision Applications Faster with Supervision

Visualize and process your model results with our reusable computer vision tools.

Cite This Project

LICENSE
CC BY 4.0

If you use this dataset in a research paper, please cite it using the following BibTeX:

                        @misc{
                            followtracker_dataset,
                            title = { FollowTracker Dataset },
                            type = { Open Source Dataset },
                            author = { Daves Armoury },
                            howpublished = { \url{ https://universe.roboflow.com/daves-armoury/followtracker } },
                            url = { https://universe.roboflow.com/daves-armoury/followtracker },
                            journal = { Roboflow Universe },
                            publisher = { Roboflow },
                            year = { 2023 },
                            month = { jan },
                            note = { visited on 2024-11-24 },
                            }