Mobile Robot

Assistive Autonomous Mobile Robot

    Introduction

Robotic technology can be used in several ways to assist people for doing many tasks. Although there’s no precise definition, but by general agreement a robot is a programmable machine that imitates the actions or appearance of an intelligent creature–usually a human. To qualify as a robot, a machine has to be able to do two things: 

  1) Get information from its surroundings.
 2) do something physically such as move or manipulate objects.
Mobile robots are as following:
- Any robot which possesses mobility with respect to a medium. With Intelligentsenses which can react to its environment.
 - Any system which is entire system moves in an environment. This mobile robot is autonomous limited human intervention because it can:
- Decides on its own what to do.
- Summarizes information for human consumption.

Mobile robots are the focus of a great deal of current research Mobile robots are also found in social places, industry, military and security environments. They also appear as consumer products, for entertainment or to perform certain tasks in human environments like vacuum cleaning, rescue and assisstant.
Assistive robot is one field of mobile robots that is growing but has not yet been properly defined and circumscribed. An adequate definition of an assistive robot is one that gives aid or support to human and another automated system.

2- Project Scope

  Research assistive robotics includes rehabilitation robots, Wheelchair robots and other mobility aides, companion robots, manipulator arms for the physically disabled and educational robots.  To increase the performance of this kind of mobile robot, we may propose the proper architecture for implementation of each part. In this architecture a general model of assistive autonomous mobile robot is defined to help human in social environments such as home, small office, school, hospital and so on.

3- Components
We summarized some components in the follow:

3-1) Self Localization and Map Generation
Robot self localization or positioning is a major concern in mobile robot navigation. This process is crucial to a assistive robot because most of robot operations are related to position. This position must be found easily and repeatedly. Robot positioning can be done in two basic methods: absolute and relative positioning, or a combination of both.

3-2) Object Categorization
Recognition of object is an important capability for autonomous robotic systems. In our research we use of object categorization method instead of object recognition. In object categorization we attempt to recognize the objects and classified them into a specific class, such as glass, book, chair,… but in object recognition we try to find a specific object in specific group of objects such as finding the specific car in set of car images. Recent results have established various categorization methods that are based on local salient structures in the images. Some of these methods use just a ‘bag of key points’ model. Others include a certain amount of geometric modeling of 2D spatial relations between parts, or ‘constellations’
of parts. In this research we propose a new real time image categorization for clutter environment. Also, these robots equipped with two camera, one top of robots and make panoramic image from omni directional mirror and second front camera. For distance measurement of object, we use of stereo vision with omni directional mirror image and image captured from front camera.

3-3) Navigation
The basic navigation problem can be defined as:
How does a robot go from A to B successfully? (Fig 1)
This involves:
1. Path Planning (local or global) - with either on-line or on the decision based planning and/or off-line planning.
2. Localization (Knowledge of Position or State) - this is essential for path planning.
3. Collision Avoidance

  

Fig 1: Three possible paths for a robot to go from A to B, with obstacles represented by circles.

 

4- Hardware Description
The assistive mobile robot platform will be built to explore the added value of an embodied companion in an intelligent robot. To increase the ability of movement mechanical system is proposed as shown in Fig 2.  Omni system can move to X, Y and rotation at the same time.
Three MAXON motors coupled with EPOS driver are locomotion of the robot. Each motor is in radius of curvature in the 120 degree that mounted on the omni wheels.

     Fig 2: Omni directional robot platform

The main objective of the assistive robot is to integrate intelligent components with high flexibility and reliability. Localization and tracking service is based on wire less sensor, laser finder and omni directional mirror. The vision sensor provides the omni directional view of the assisted person and any other objects in the environment. The CO2 and thermopile array detector are used to detect smoke and fire of environment.

 

5- Resource Opportunity
     

To perform of this project we need to following candidate with expertise:

    - Bachelor degree in computer, electronic and mechanical engineering,

     - PhD and Master degree or researcher in intelligent system and robotic,   control and mechanical engineering,

 

6- Objectives of the Research

-Build a real autonomous mobile robot to assist to people in indoor environment

-Developing the artificial intelligent methods in robotic systems

-Provide a professional research environment to publishing in the high impact factor journals