Self Autonomous Robot using ROS

In this project we are using ROS (Robot Operating System) for simulation The Robot Operating System (ROS) is a flexible framework for writing robot software. It is a collection of tools, libraries, and conventions that aim to simplify the task of creating complex and robust robot behavior across a w

Project Title

Self Autonomous Robot using ROS

Project Area of Specialization

Robotics

Project Summary

In this project we are using ROS (Robot Operating System) for simulation The Robot Operating System (ROS) is a flexible framework for writing robot software. It is a collection of tools, libraries, and conventions that aim to simplify the task of creating complex and robust robot behavior across a wide variety of robotic platforms.

We decided to have TurtleBot perform the critical task navigating in the physical word.

TurtleBot is a mobile base that can autonomously move around an environment.

Project Objectives

• Localization and Navigation.

• Object detection and Collusion avoidance.

• Camera calibration.

• Lane detection.

• Traffic light and traffic signs detection.

• Parking

Project Implementation Method

• Localization and Navigation.

An autonomous car cannot navigate through an unknown environment without sensors and an on-board computer which would make use of acquired sensor's data to understand the environment. Different kinds of sensors (such as sonars, odometers, LIDAR, IMU, GPS and cameras) are used to make an autonomous car capable of sensing a wide range of environments

A map of the environment is a basic need of an autonomous car to perform services like moving from point A to point B

While it is moving through an environment, the car should also be aware of its own location in that environment, and its own dimensions, to be able to solve navigation and route planning issues successfully

• Mapping of the environment.

Environment mapping is done by creating the 2D model of the environment surrounding a car using its sensors and mapping algorithms. The created map is then used for car's localization, navigation, and route planning.

• Localization.

Car localization tells the car where it is in relation to its environment. Localization uses odometry, laser data and a map . The localization algorithms play a crucial role in the positioning. As input, localization algorithm requires a global map with occupied cells, a LIDAR, RADAR, or ultrasound.

The ROS platform could greatly shorten the robot development cycle, and simultaneous localization and mapping (SLAM) could easily be realized using ROS ,This is possible because ROS already has ready packages for this purpose called gapping. By using this package, ROS-based self-driving car could simply map the environment by using LIDAR sensor (Kinect).

• Traffic light and traffic signs detection.

In this we use SIFT algorithm SIFT stands for Scale-Invariant Feature Transform

SIFT is quite an involved algorithm. There are mainly four steps involved in the SIFT algorithm.

1. Scale-space peak selection: Potential location for finding features.

2. Key point Localization: Accurately locating the feature key points.

3. Orientation Assignment: Assigning orientation to key points.

4. Key point descriptor: Describing the key points as a high dimensional vector.

5. Key point Matching

• Parking

TurtleBot detects the parking sign, and park itself at a parking lot in the gazebo simulation environment,

Benefits of the Project

The Benefit of the project is to collect requirements, assemble mechanical and electronic parts, connect sensors and interface them to the ROS, implement motor and servo control and set up obstacle detection algorithms, environment mapping, localization, and route planning. ROS-based autonomous bot is both a feasible and a working project.

As such, the problems, solutions, benefits, and challenges discussed in this ROS-based autonomous bot project can be implemented on any size and environments of any type, it can benefit the autonomous driving community, both academically and commercially.

Technical Details of Final Deliverable

The SLAM (Simultaneous Localization and Mapping) is a technique to draw a map by estimating current location in an arbitrary space. The SLAM is a well-known feature of TurtleBot from its predecessors.

• Run SLAM Node

• Run Teleoperation Node

• Tuning Guide

• Mapping (This map will used for the Navigation).

Navigation is to move the robot from one location to the specified destination in each environment. For this purpose, a map that contains geometry information of furniture, objects, and walls of the given environment is required.

In SLAM the map was created with the distance information obtained by the sensor and the pose information of the robot itself. The Navigation enables a robot to move from the current pose to the designated goal pose on the map by using the map, robot’s encoder, IMU sensor, and distance sensor.

• Run Navigation Nodes

• Estimate Initial Pose

• Set Navigation Goal

Using Gazebo environment for the simulation

• Install Simulation Package

• Launch Simulation World

• Operate TurtleBot3

• SLAM Simulation

  • Launch Simulation World

  • Run SLAM Node

  • Run Teleoperation Node

  • Save Map

• Navigation Simulation

  • Launch Simulation World

  • Run Navigation Node

  • Estimate Initial Pose

  • Set Navigation Goal

• Camera Calibration

  • Camera Imaging Calibration

  • Intrinsic Camera Calibration

  • Extrinsic Camera Calibration

  • Check Calibration Result

• Lane Detection

• Traffic Sign Detection

Final Deliverable of the Project

HW/SW integrated system

Core Industry

Transportation

Other Industries

Medical , Manufacturing

Core Technology

Robotics

Other Technologies

Artificial Intelligence(AI)

Sustainable Development Goals

Industry, Innovation and Infrastructure, Sustainable Cities and Communities

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com