Simultaneous Localization and Mapping (SLAM) for an autonomous cleaning robot

Simultaneous Localization and Mapping (SLAM) for an autonomous cleaning robot

SLAM: Simultaneous localization and mapping (SLAM) is a method used for autonomous vehicles that lets you build a map and localize your vehicle in that map at the same time1. SLAM algorithms allow the vehicle to map out unknown environments. Engineers use the map information to carry out tasks such as path planning and obstacle avoidance1. SLAM is a challenging problem in robotics that requires an agent to build a map of an unknown environment and locate itself within it.

MAPPING: With the rise in autonomous robots, it has become crucial for a simple and effective mapping system. Depending on the requirements, there are different ways of mapping a room, using different techniques and sensors. Mapping is a discipline related to computer vision and cartography that involves creating a representation of the environment that a robot can use for navigation and decision making. It is also a part of the SLAM (Simultaneous Localization and Mapping) process, which combines the localization of a robot and the mapping of the environment simultaneously. There are three main types of maps: sensorial, topological, and geometric. Sensorial maps are based on the direct perception of the environment by the robot’s sensors. Topological maps are graph-based representations of the places and paths in the environment. Geometric maps are coordinate based representations of the objects and distances in the environment. 

LOCALISATION: Localization is the process of determining the robot’s pose (position and orientation) relative to a given map of the environment. It is an essential task for robot navigation, as it allows the robot to plan its path and avoid obstacles. Our project aims to build an Arduino based robot which can use two ultrasonic sensors to read distance data from the environment and make the map. The sensors would relay the distance infront and to the left of the robot , which would then be used by the Arduino to relay the next move of the robot to the motor driver. And this will occur till the robot completes the map of the room.

Working:-

The robot uses the ultrasonic sensors to measure the distance to the nearest obstacles and the motor driver to control the wheels of the robot. The robot first moves around the perimeter of the room and records the distance measurements. Then it updates the map of the room. After completing the perimeter scan, the robot roams around in the inside of the room and repeats the same process of measuring, estimating and updating. The final output of the project is a 2D map of the room that shows the location of the robot and the obstacles. The project was tested and evaluated by comparing the generated map with the actual layout of the room.

In our approach, we propose the utilization of microcontrollers and ultrasonic distance sensors as the core components of the mapping system. Microcontrollers are small, cost-effective computing devices that can be programmed to handle specific tasks efficiently. They serve as the brain of the mapping system, processing sensor data and making decisions based on the collected information.

Ultrasonic distance sensors, on the other hand, are affordable and widely available sensors that measure distance by emitting ultrasonic waves and calculating the time taken for the waves to bounce back after hitting objects in the environment. These sensors provide distance measurements to objects in the vicinity of the robot, enabling the construction of a basic map.

 

Circuit Diagram:-

Hardware Required:-

1. Arduino UNO
2. HC-SR04 (Ultrasonic Sensor)
3. L298 Motor Driver
4. HC-05 Bluetooth Module
5. DC Gear Motors
6. 12v Li-ion Battery
7. 7805 Voltage Regulator with heat sink