AnbuKumar-maker/MultiSensor-Distance-Detection-in-ROS-Serial

Stars
2
Language
C++
Created almost 4 years ago
Updated almost 4 years ago

AnbuKumar-maker/MultiSensor-Distance-Detection-in-ROS-Serial

AnbuKumar-maker

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

In this repository I will document step by step how to setup multiple UltraSonic sensor to integrate with ROS Serial and detect the range using Jetson Nano and ROS for Autonomous Robots

AI-on-Jetson-Nano

I have created a series of programs using NVIDIA Jetson Nano, Pi Camera and Logitech Web Camera. I installed OpenCV version 4 along with Python 3 to create these sample programs

Machine-Learning-on-Arduino-33-BLE-Sense

In this repository I will maintain all the build related to Machine Learning excercise on Arduino 33 BLE Sense

Jupyter Notebook

AI-in-Xavier-NX

In this new repository, I will be tracking all the AI programs I will be building and deploying on Xavier NX with 2 cameras

Hexapod-Robot-With-AI-Capabilities

In this project I am building a 6 legged, 18 DOF Hexapod Robot and AI Capabilities using NVIDIA Jetson Nano and Intel RealSense T265. Below are details of the componens I have used and the codes for Arduino to drive the digital motors.tandard DYNAMIXEL AX-12A or Ultra Fast DYNAMIXEL AX-18A Series Robot Servos • 3 Degree-Of-Freedom Legs • Arduino-Compatible ArbotiX Robocontroller • Open Source Software • Advanced Inverse Kinematics Driven Gait Engine • 6 Different Walking Gaits Available • Extended Run Time with High Quality 4500mAh LiPo Battery • Included Top Deck makes it easy to add Arms, Grippers, Cameras, Pan/Tilts, even Computers! • Rugged Full Metal Frame Construction • Wireless Xbee Control via PC or Handheld USB Xbee Interface • USB A to Mini-B Cable

DeepLearning-in-ESP32

Object detection and identification is one of the most important and challenging branches of computer vision, which has been widely applied in peoples’ life, such as monitoring security, autonomous driving, and so on, with the purpose of locating instances of semantic objects of a certain class. With the rapid development of deep learning networks for detection tasks, the performance of object detectors has been greatly improved. By using Machine Learning and ResNet, we can easily identify the names of the objects which we needed. For this, firstly the training data is fed to the machine and labeled it correctly based on the nomenclature. By using the Camera Module, the test data is detected and verified with the train data using the ResNet algorithm. By repeated testing of the objects, the data set is updated or deleted based on the errors made by the machine in identification. On the repeated iteration of identifying the objects correctly ie., Accuracy reaching ≥ 95%, the dataset, and the application is used in Real World for automation. For this, I use Keras, an open-source neural-network library written in Python and by using the IoT module, the identified data is transferred to the Display device wirelessly. In Real-Time, this project is used for the identification of objects with more than 95% accuracy and transmit the data from anywhere and anytime using the cloud, and completely automate the process and reduces the manpower. ESP32 : Engineered for mobile devices, wearable electronics and IoT applications, ESP32 achieves ultra-low power consumption with a combination of several types of proprietary software. ESP32 also includes state-of-the-art features, such as fine-grained clock gating, various power modes and dynamic power scaling.

ChatGPT-Machine-Learning-Prompts

ESP32-ESP32CAM

Learn To Build Artificial Intelligence, Robotics and IoT Projects on ESP32, ESP32CAM Development Modules using C++ and MicroPython Coding. https://youtu.be/qP9wJLoscvk

Raspberry-Pi-4-Projects

In this repo, I will maintain all the codes of various types of projects I will be building using Raspberry Pi 4

Jetson-Xavier-NX---GSTREAMER

Documentation to follow the steps for various Gstreamer settings to improve, modify video quality capture from Xavier NX for Robotics and AI applications

I2C-Motor-in-Jetson-Nano

In this repository I have documented the circuit diagram to connect PCA9685 to Jetson Nano followed by steps to install library and python code to run the servo motors

ROS-for-Layman

Here I have documented basic steps to install and configure ROS on Jetson Nano for any one to every to understand

Arduino-Sensor-Projects

In this repository I will maintain all the codes for different types of sensors to be connected to Arduino and read the sensor inputs

ESP32-SmartWatch

All the codes, documentation, bom list, gerber files, libraries extracted from Instructables

Raspberry-Pi-IoT-Projects

In this repository I will maintain all the codes related to Raspi IoT projects. I also have the Raspbean Stretch OS image which is bit older version but this is what is needed to work on these IoT projects

GStreamer-For-Jetson-Xavier-and-Nano

Understanding GStreamers are super critical to capture accurate image pixels to execute Artificial Intelligence capabilities in Computer Vision, below are the list of GStreamer parameters which can be tweaked to capture the required data from image / videos

Mecanum-Robot-For-Personal-Assistance

In this repository I will be documenting each steps to build a 4 wheel Mecanum Robot to assist you at home with ML algorithms, few sensors, motors and MCU

AnbuKumar-maker

Config files for my GitHub profile.

ESP32-AI-IoT-Robotics

In this section I will maintain all the source codes for the projects using ESP32Cam module, mainly AI, IoT and Robotics

Funny-Python-Projects

This is a introduction lesson about Funny Python series. This series is for those who have some basic knowledge about Python or even for those who do not have any knowledge on Python. We will directly start building Python projects instead of going through loops, functions, lists, tuples etc etc. We will build several funny and useful Python applications on a real time, however in order to do that we need bunch of Python libraries to be installed.

MecaBot

I am building a Mecannum Robot which can move in multiple directions and autonomously navigate a defined path A to path B without using LIDAR or Depth Camera. By using simple US100 Ultrasonic sensor, adding an array of 4 x 4 US100 sensors in all 4 directions of the bot using Arduino can achieve pre-defined path planning. Still this project is under fine tuning and experimentation

DeepLearning-Music-Recognition-Project

This is a deep learning project concept. You’ll build a deep learning model that employs neural networks to automatically classify music genres. The model takes as an input the spectogram of music frames and analyzes the image using a Convolutional Neural Network (CNN) plus a Recurrent Neural Network (RNN). The system’s output is a vector of the song’s projected genres. The model has been refined with a tiny sample (30 songs per genre) before testing it on the GTZAN dataset, resulting in an accuracy of 80%.

Arduino-Sensor-Libraries

In this repository I will maintain all the sensor libraries

Coding-Neural-Network

Learn How To Code Your Own Artificial Neural Network with Backpropagation Using Python From Scratch By Applying Supervised Learning Method for Multilayer Feed-Forward Networks

Artificial-Neural-Network-using-Jetson-Nano

This ia a new project I intend to build a neural network with my own algorithms for object classification and detection

Zero-To-Hero-Python-Resources

MachineLearning-Packages-in-Jetson-Nano

Steps to install certain packages on Jetson Nano to perform Macine Learning applications

Nano-RP2040-Connect

In this repository I will maintain the source codes for the projects been built using Arduino Nano RP2040 Connect

SriKaalaDevi-ChatBot

Python ChatBot application to be integrated with any site builder by customizing the front end UI design

Pico-Robot

This repository has complete details to build a remote controller Robot using Pico, MicroPython and nRF Radio Module

PIR-Motion-Detection-in-NodeMCU

In this project we use ESP8266 in its NodeMCU form factor as a home security device which with the help of PIR sensor senses the movement of intruder and sends and email and mobile notification to the owner along with the time.

LiDAR-Configuration-in-ROS

I have documented steps to configure LiDAR with ROS on Jetson Nano. Follow these instructions step by step after installing ROS Jetson Nano JetPack 4.3

MPU6050-Servo-Control

In this project you can control a servo motor using MPU6050 IMU board and Arduino UNO or Nano. Circuit diagram and codes are included

Machine-Learning-Algorithms

In this repository I am maintaining the Python codes to execute different types of Machine Learning Algorithms

Face-Recognition-Using-Python-OpenCV-on-Jetson-Nano

In this project, I have used Jetson Nano, installed Python3, installed OpenCV4 and used PiCamera

ESP32-Camera-Survelliance-Robot

This is a low cost, simple and easy solution to navigate your home via internet to monitor using ESP32 Camera Surveillance Robot

Machine-Learning-in-Arduino

One of the exciting aspects of running machine learning models on embedded hardware is the ability to use low power devices with greater contextual awareness to trigger high energy devices only when it is valuable to do so.As a proof-of-concept, we want to use the low-power Arduino Nano 33 BLE Sense and an ArduCam Mini 2MP, along with the TensorFlow Lite library, to trigger a relay to turn on/off when a person is recognized.

Machine-Learning-in-Jetson-Nano

I will be building various ML techniq to train a model in Jetson Nano for Data Generation to be used in Object Detection

Dual-Servo-Camera-Control

Using this project code, you can control 2 Pan/Tilt mechanism (4 Servo Motors) with 2 cameras to detect various objects, human faces and execute various Artificial Intelligence applications using Deep Learning methods / Libraries

MicroPython-Sensor-Logger

A system for recording sensor values to a Google Sheet. Making use of HTTP requests to communicate between the micro-controller and the server, and utilising gspread to write data to online spreadsheet.

Huskylens-A.I-Machine-Vision-Sensor

In this repository I will be maintaining all the codes, drivers and libraries related to Huskeylens in order to build several AI projects and deploy on physical Robot

Magic-Wand-in-Jetson-Nano

The wands which are bought from the Wizarding World of Harry Potter in Universal Studios, have a retroreflective bead at their tip. Those retroreflective beads reflect a great amount of infrared light which is given out by the camera in the motion capture system. So, what we humans perceive as a not-so-distinctive tip of the wand moving in the air, the motion capture system perceives as a bright blob which can be easily isolated in the video stream and tracked to recognize the pattern drawn by the person and execute the required action. All this processing takes place in real time and makes use of computer vision and machine learning. A simple night vision camera can be used as our camera for motion capture as they also blast out infrared light which is not visible to humans but can be clearly seen with a camera that has no infrared filter. So, the video stream from the camera is fed into a Raspberry Pi which has a Python program running OpenCV which is used for detecting, isolating and tracking the wand tip. Then we use SVM (Simple Vector Machine) algorithm of machine learning to recognize the pattern drawn and accordingly control the GPIOs of the Jetson Nano to perform some activities. In this case, the GPIOs control a servo motor which opens or closes a harry potter themed box according to the letter drawn by the person with the wand.

Human-Detection-and-Tracking-in-Jetson-Nano

The project focuses on a real-time robust human detection and tracking system for video surveillance that can be used in varying situations. The system consist of two parts first human detection and secondly tracking. Early research is biased to human recognition rather than tracking. Monitoring the movements of human being raised the need for tracking. Monitoring movements are of high interest in determining the activities of a person and knowing the attention of person. This project focuses on Person Detection and tracking. The tracking algorithm used here is Kalman Filtering. The Kalman Filter has long been regarded as the optimal solution to many tracking and data prediction tasks. Its use in the analysis of visual motion. The purpose of Filtering is to extract the required information from a signal, ignoring everything else. In this project the Kalman Filter is fed with the velocity, position and direction of the person which helps it to predict the future location of the Person based on his previous data.

PID-Control-using-Arduino

The working principles of the PID controller The working principles of the PID controller are best understood by breaking it down and analyzing each element individually. Proportional gain—This gives an output that is proportional to current error (the difference between what you want and what you have). If, for example, a room’s temperature setpoint is 22°C, but the room is actually at 24°C (an error of 2°C) the controller applies a corrective action that is proportional to the error—in this scenario, it may turn the heat to a medium setting, whereas it would set it to a high setting if the room’s temperature was say 15°C. Integral gain—This is multiplied by the integral (or sum) of the error by looking at its history. Returning back to the temperature example, the system may detect that 10 minutes were spent at 24°C, 10 at 23°C, and 10 at 22°C as the room cools down. If a system is heading too slowly to a setpoint, the integral error begins to increase and makes the correction stronger, in this case, perhaps by turning the heater down to a lower level. Derivative—This is how fast the error is changing. With the temperature example, the room is cooled by 1°C every 10 minutes. This means that the error is shrinking by 1°C, even 10 minutes. By keeping track of this, overshoot—such as making the room too cold—can be avoided, improving system efficiency. Reasons to use PID In short, PID is used for more precise control of the variable that is subject to control. It can also respond quickly to changes, making systems more efficient.

GPTChatBot

In this repository, I have added a word doc with step by step instructions to build your own AI driven ChatBot using GPT API

Voice-Controlled-AI-Vision

This project will present the architectural design behind a voice controlled AI camera. The main idea is to control a camera by a voice interface to take a photo and have it send you an email with the photo description of what it observes. The project encompasses multiple components starting from hardware modules like Matrix Voice, Jetson Nano and RPIU2 to software frameworks like SNIPS AI and of course custom Python AI scripts that comprise the neural backend engine. So in a nutshell we will leverage the Snips AI platform and Matrix Voice for the voice interface and Keras/Tenorflow DNN running on a Jetson Nano SBC for the image inference AI. The demo code attached is setup so that if a person is detected an email is sent to the user with the annotated image from the AI engine. The class can be changed however.

Google-Assistant-Robot

This project is all about controlling a Robotic Car in a different way through the various devices, or by different means of controlling like voice command, mouse, keyboard, or mobile touch screen. Or by different platforms like a webpage, mobile app, and even though today's digital Assistant like 'Google Assistant'. When you say start robot it starts moving in a forwarding direction, when you say move left it starts moving in the left direction, When you say move Right it starts moving in the Right direction, When you say move backward it starts moving in a Backward direction, When you say stop it will be stoped. It is a simple example of the coming day of smart IoT, AI, and ML-enabled Vehicles. In these types of vehicles, there is no need for a driver to drive a car. These type of cars are self controllable with the help of new technology like 5G and IoT. These types of cars can make good use of Sensor data to detect Traffic other vehicles, Objects, Humans in their surroundings and is also capable of interact with other roadside vehicles to make a good decision for its preferred and the best route which are helpful in making driving hassle-free.

HumanDetection-AI-in-Arduino

One of the exciting aspects of running machine learning models on embedded hardware is the ability to use low power devices with greater contextual awareness to trigger high energy devices only when it is valuable to do so. As a proof-of-concept, we want to use the low-power Arduino Nano 33 BLE Sense and an ArduCam Mini 2MP, along with the TensorFlow Lite library, to trigger a relay to turn on/off when a person is recognized.

Machine-Learning---Sensor-Data-Analytics

Employing machine learning to the sensors and signal data is making the devices smarter than ever. Get started with ML and Azure. Over the past few years, Deep Neural Networks have provided us the best results on a variety of problems, such as pattern recognition, computer vision, and Speech recognition and image classification. Employing Machine Learning to the sensors and signal data is making the devices smarter than ever and is going to be a breakthrough in the field of IoT. Whether you are using sounds, vibrations, images, electrical signals or accelerometer or other kinds of sensor data, you can build richer analytics by teaching a machine to detect and classify events happening in real-time, at the edge, using an inexpensive micro controller for processing - even with noisy, high variation data.