Collective exploration of swarm robots

Robots have some general intelligence, perhaps a singular intelligence determining tasks and each individual robot takes that tasks and use their own intelligence and talking with each other to perform it. Swarm robotics is the study of how to design groups of robots that operate withou

Project Title

Collective exploration of swarm robots

Project Area of Specialization

Robotics

Project Summary

Collective Exploration of Swarm Robots

Robots have some general intelligence, perhaps a singular intelligence determining tasks and each individual robot takes that tasks and use their own intelligence and talking with each other to perform it.

Swarm robotics is the study of how to design groups of robots that operate without relying on any external infrastructure or on any form of centralized control. In a swarm robotics, the collective behavior of robots results from local interactiion between the robots and the environment in which they act.

Our project is collective exploration of swarm robots in which we are designing and builting three robots using four wheeled chasis, Raspberry Pi, Raspberry Pi Camera 5MP, Ultrasonic sensor, DC motors, Servo Motors, Motor Module L298, Bluetooth module for communication.

Basically idea behind this project is to explore the object, encircle the object and target the object. We are using a tennis ball as our object or target, robots will search the object using Particle Swarm Optimization(PSO) technique and they will detect the object by Raspberry Pi camera using Computer Vision (OpenCV) if one of the robot found the object then it will track the object and will communicate with other robots and will share coordinates or predicted location to the other two robots and other robots will follow the coordinates given by the robot 1. When all the robots will detect the object then the robots will encircle the object using Grey Wolf Optimization(GWO) technique and then the robots will fire the object.Hence in this project our robots will first explore the object using (PSO) and OpenCV then they will communicate with each other using bluetooth module then after the communication they will track and encircle the object. and finally they will lock the target and fire the object.

Project Objectives

Objectives

• A single robot may not be able to work properly for military purpose. However a group of robots can solve that problem.
• The first Objective of this project is to implement the behavior of swarm robots in real life.
• We are implementing different behavior of swarm in real life in order to implement this idea for military purpose.
• The one of the Objective of this project is to save human from further injuries and use robots instead.

Project Implementation Method

Project Scope

Swarm robotics is a new approach to the coordination of multirobot systems which consist of large numbers of mostly simple physical robots. The desired collective behaviour emerges from the interactions between the robots and interactions of robots with the environment.

The project scope of collective exploration of swarm robots is very bright because we are using multiple behaviors of swarm in real life in order to use it for military purpose and save human lives. We are using hybrid algorithm Particle Swarm Optimization(PSO) and Grey Wolf Optimization(GWO).

Behaviors

Behaviors are given below:

Searching
Object detection
Tracking through shortest path
Approach and Encircle
Attack the  prey

Algorithm

• Particle swarm optimization (PSO) for searching
• Grey Wolf optimization(GWO) for encircle and attack
• Back propagation(BP) for selecting shortest path in tracking phase

Hardware and software

Ultrasonic Sensor

Ultrasonic sensors are very commonly used to measure distance because they are inexpensive and easy to handle.They are used to avoid obstacles, to navigate, and for map building.

Bluetooth Module

Bluetooth is a technology for wireless communication. We are using HC-05 for communication purpose. HC-05 Bluetooth module provides switching mode between master and slave mode which means it able to use neither receiving nor transmitting data.

Camera

We are using Raspberri Pi camera (5MP).The camera module provides vision based localization and obstacle avoidance in the swarm system. We use RPI Camera with servo Motor Board on our robot swarm. This camera can transmit the live feed to the host computer over wireless communication. In differentiating between the obstacle and goal objects, ultrasonic sensor have some limitations, which can be rectified by using the camera module.

Motors

We are using DC gear motors four on each robot, these motors are actuated and controlled using the motor controllers.

Motor Controller

We are using L298 motor module for controlling the motors.

Raspberry Pi(RPI)

We wre using micro computer RPI and we are using raspbean as an operating system for RPI. For OpenCv we are using Python language as it is easy to use for computer vision.

Robot Operating System(ROS)

For coding and simulation we are using robot operating system (ROS).

Power Supply

We are using Laptop cells as our power supply, we are using 3-cell for each robot. Each cell contains 3.7V

Experimental Results

We have designed and built 3 robots and experiments related to the computer vision and tracking also have done, all the work related to hardware and computer vision have been completed. Now we are working on the communication between the robots.

All the robots are detecting and tracking the object(Tennis ball) separately but to collaborate and interaction with each other we are working on communication, our 60-70% project have been completed.

Benefits of the Project

Benifits

• The swarm  robots can complete the tasks that a complex individual can do while having high robustness and flexibility and low cost.
• Wars are on ahead and every country is trying best to bring new nuclear weapons. How would be the scene if the soldiers would be robots. Surely the Army will no more be humans in coming centuries.
• Our robots are energy efficient. Since the individuals in the swarm are much smaller and simpler than a giant robot, the energy cost is far beyond the cost of a single robot compared with the battery size. This means that the life time of the swarm is enlarged. In an environment without fueling facilities or where wired electricity is forbidden, the swarm robotics can be much useful than traditional single robot.
• Our robots in the project will be autonomous as they will be capable of interacting and motioning in the environment.
• Our robots will show decentralization. With a good set of cooperative rules, the individuals can complete the task without centralized controls which promises the scalability and flexibility of the swarm. At the same time, the swarm can benefit more in the environments when communication is interrupted or lagged and improves the reaction speed and precision of the swarm.
• Robots in our project will be homogeneous, in a swarm robotics system, the robots should be divided into the roles as few as possible and the number of robots acting as each role should be as large as possible. So, in our case our task is same for all the robots to search the object, to encircle the object and finally target the object
• The interaction in the swarm is local, allowing the individuals to join or quit the task at any time without interrupting the whole swarm robots. This also indicates that the system is adaptable for different sizes of population without any modification of the software or hardware which is very useful for real-life application.

Technical Details of Final Deliverable

At the end of the project we will deliver three homogenous robots capable of searching, detecting , tracking , encircling and target the prey or object.

We will deliver a cardboard of almost 4*4 or 5*5 on which we will define a red zone area our robots will be present in this environment and the robots will be continuously searching for the object or prey around this red zone area.

Object which is a tennis ball is already defined for robots as a prey or object so when we keep or through the tennis ball in the red zone area then the robot will suddenly detect the object then say this robot as "Alpha" so Alpha will communicate with two other robots named as "Beta" and "Gamma" respectively.

Alpha will send the signal to beta and gamma , when beta and gamma will receive the signal then both these robots will rush to the object and then detec the object After the detection now all three robots will encircle the object using Grey Wolf bahavior and finally fire the object.

so our deliverable will be

Three robots , each robot containing:

• Raspberry Pi
• Raspberry Pi camera
• four wheeler chasis with DC motor on each tyre
•  Motor controller
•  Ultrasonic sensor
• servo motors 
• Power supply of 3-cell battery containing 11.1V
•  Buck Converter to convert 11.1 to 5V
• Bluetooth module 
• Tennis ball
• cardboard
• other things or etc.

Final Deliverable of the Project

HW/SW integrated system

Type of Industry

Others , Telecommunication

Technologies

Artificial Intelligence(AI), Robotics, Others

Sustainable Development Goals

Good Health and Well-Being for People, Affordable and Clean Energy, Decent Work and Economic Growth, Industry, Innovation and Infrastructure

Required Resources

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