Scribd
Upload
8 views23 pages

SLAM Algorithm for Omni-Directional Robots

SLAM Algorithm for Omni-Directional Robots

Uploaded by

saifsaqqa26
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
8 views23 pages

SLAM Algorithm for Omni-Directional Robots

SLAM Algorithm for Omni-Directional Robots

Uploaded by

saifsaqqa26
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 23

SLAM Algorithm for Omni-Directional

Robots based on ANN and EKF


PROF. TAREK A. TUTUNJI
AL HUSSEIN TECHNICAL UNIVERSITY
JEEIT 2023
AMMAN, JORDAN 22.05.2023
OUTLINE
-- Overview
-- Mobile Robotics
-- SLAM
-- Kalman Filters
-- Artificial Neural Networks (ANN)
-- Implemented Algorithm
-- Robotino Platform
-- Results
Overview
A three-stage SLAM algorithm was developed and applied to an omni-directional robot
1. Artificial Neural Networks (ANN) are used to analyze the sensors and camera image data to search for
possible paths.
2. The camera image edges are detected using speeded up robust features (SURF) to find alternate paths.
3. The paths from the previous two stages are compared and the best match path is found while Extended
Kalman Filters (EKF) are used to estimate the robot position and orientation.

The proposed algorithm is programmed using MATLAB software, interfaced with an


omnidirectional robot by means of wireless communication, and validated experimentally
using Robotino platform.
Autonomous Cars
Three main questions:
◦ Where am I?
◦ Where am I going
◦ How do I get there?

Then, we need to
◦ Model the environment
◦ Perceive and analyze the environment
◦ Find its position
◦ Plan and execute the movement
Mobile Robot: See-Think-Act
Perception: Sensing & Information Extraction
Localization: Map Building
Cognition: Path Planning
Motion Control
Motion Control: Omni-Directional
SLAM
Simultaneous localization and mapping (SLAM) is an
autonomous localization and map building method that uses
information from the robot scans to construct a map of the
environment and update it while simultaneously tracking
the robot’s location as it moves.

This is a difficult problem because the robot’s location and


pose estimate can be based on inaccurate sensor readings.

SLAM with Extended Kalman Filter - YouTube


SLAM
Probabilistic Map-based Localization
Kalman Filter

https://www.kalmanfilter.net/kalman1d.html
Implemented Algorithm
The camera image was processed via Artificial Neural Networks (ANN) and used to locate markers and
build a map array of the environment while the nine built-in IR sensors were used to check for obstacles.
Motor encoder information was processed via EKF algorithm to estimate the robot states
FESTO Robotino
Robotino Sensors
Robotino has a total of nine
infrared sensors arranged at an
angle of 40 ° to each other
around the base. Each distance
sensor supplies a voltage value in
volts whose magnitude depends
on the distance to a reflecting
object.
Experimental setup
System input output
Experimental Results
Experimental Results
Conclusion
-- A modified SLAM technique composed of three-stages was programmed and
implemented using omni-directional robot.
-- Information from camera images, infrared sensors, and wheel encoders were
used in a SLAM-based algorithm to move the robot in a lab environment in order
to record the map.
-- The proposed method was simulated in Matlab and implemented in a Robotino
platform using wireless communication.
-- Experimental results show that the proposed method provided appropriate paths
with high-level of accuracy.
Challenges and Future Work

You might also like