Vous êtes sur la page 1sur 5

Final Report

on
System Architecture of an AI
Robot
Prepared for

Created by
Yash Agarwal

INTRODUCTION

The term 'System Architecture' is a response to the conceptual


and practical difficulties of the description and the design of
complex systems. Now, a system is called a complex system
when they are designed by integrating many heterogenous
components, software and hardware.
What is meant by an Artificial Intelligent Robot, anyway?
A machine which can extract data and information from the
environement and can process this knowledge to move safely
in a meaningful and purposeful manner.
Recently vast amount of AI projects are being made in
domains like Games, Music, Knowledge and Reasoning to
name a few.

Sensors
1. Camera
2. LIDAR
3. GPS

4. IMU
5. Ultrasonic Sensors
6. Encoder
Definitions
Camera There are many types of camera to acquire environment
input images such as single camera, stereo cameras,
omnidirectional cameras.
Lidar LIDAR is an acronym for Light Detection and Ranging.
This sensor is used to measure distances to a targets by
illuminating the target using lasers.
GPS Global Positioning System which can be used to get
position and time in all weather conditions through satellite
communication.
IMU Inertial Measurement unit is electronic device that
measures and reports a body's specific force, angular rate, and
sometimes the magnetic field surrounding the body, using a
combination of accelerometers and gyroscopes.
Ultrasonic Sensors They generate high-frequency sound waves
and evaluate the echo which is received back by the sensor,
measuring the time interval between sending the signal and
receiving the echo to determine the distance to an object.
Encoder - Optical encoders enable an angular displacement to be
converted directly into a digital form. An optical encoder is an
angular position sensor : It has a shaft mechanically coupled to an
input driver which rotates a disc rigidly fixed to it.

Control Algorithms
Visual Odometry It is the process of determining the position
and orientation of a robot by analyzing the associated camera
images.
SLAM Acronym for Simultaneous localization and
mapping.SLAM is the computational problem of constructing or
updating a map of an unknown environment while simultaneously
keeping track of an agent's location within it.
Path Planning Breaking down the best motion path to the target
location simultaneously satisfying all the contraints set by the
user.

Cascade control and Findings


A primary or master controller generates a control effort that
serves as the setpoint for a secondary or slave controller. That
controller in turn uses the actuator to apply its control effort
directly to the secondary process. The secondary process then
generates a secondary process variable that serves as the control
effort for the primary process.
A master control can use more than one slave controls and also a
swarm or robots can be made with one as a master robot while
others as slave controls.
Various implementations of this concept can be seen in Robotic
arms, AI cars and robots, etc.

Various sensors(described above) when mounted on a chassis with


the aim of detecting obstructions and analysing paths without a
driver will be using various techniques such as Visual odometry,
path planning, pose estimation while environment will be
analaysed and updated using SLAM algorithms which are tailored
according to the requirements.
When a control or a task is dependent on more than one variables
Slave controls are used which work and move bots using actuators
satifying the set points provided by the Master control. Thus
making is possible for the Robot to move without human
assistance.

Vous aimerez peut-être aussi