Autonomous Slam Based Robotic Wheelchair for Immobilized People

We did an innovative project that is based on autonomous navigation system under neural as well as artificial intelligence, voice recognization, joystick control, mobile application,... wheelchair. To solve the problem of partial impairments by using a smart autonomous SLAM based wheelchair.

Project Title

Autonomous Slam Based Robotic Wheelchair for Immobilized People

Project Area of Specialization

Robotics

Project Summary

We did an innovative project that is based on autonomous navigation system under neural as well as artificial intelligence, voice recognization, joystick control, mobile application,... wheelchair.

To solve the problem of partial impairments by using a smart autonomous SLAM based wheelchair. There is a need for an autonomous platform that is capable of mapping and traversing an arbitrary indoor environment. However, due to inconsistent GPS signals found in indoor environments could lead to inaccurate position data. Therefore, the problem lies in accurately localizing the current position within a confined space. So to accommodate this GSM technique will be used where the signals will be used for the autonomous movement of the robot.

For instance, for severely disabled people, the most appropriate technique would be the smart one. However, this type of intelligent wheelchair presents various technical and psychological problems.

From a technical point of view, to design a fully reliable and robust automatic intelligent wheelchair, we must use sophisticated sensors to detect perfectly the environment and to implement a real-time effective algorithm providing suitable real and safe decision.

This project is also based on a voice recognition based intelligent wheelchair system for physically handicapped people who are unable to drive the wheelchair by hand is represented in this paper where the patient can operate the wheelchair using voice commands and the location of patient can be traced using GPS module in the wheelchair that tracks and sends the information to smartphone application (app). Voice module is used to record patient's voice and recognize that voice to follow the instructions of the patient. This system converts the voice commands to hexadecimal numbers and then the data is fed to the GSM/GPRS module to control the wheelchair. GSM/GPRS module directs the motor driver IC to move the wheels in desired direction. Motor speed can also be controlled in three stages-low, medium, high. This system also offers obstacle detection automatically using IR sensor and a smartphone app has been developed for the family members of patient to know about the location of the patient. Use of firebase makes the system fast and android app offers low cost and user friendly environment than the conventional GSM based navigation systems. As this system simultaneously offers voice operated wheelchair, motor speed control, obstacle detection and GPS tracking of patient using android app, hopefully it will be a fruitful system for the handicapped people worldwide.

Project Objectives

1) Robotic wheelchair combines with GPS/GSM localization to make it easier for people to manoeuvre it.

2) Develop an intelligent low cost autonomous wheelchair with basic movement via Bluetooth , voice and joystick.

3) Develop navigational system with distance measuring sensors that will be based on Obstacle avoidance for smooth navigation
4) User call the wheelchair to its position and then wheel chair self localize itself in the unknown environment and navigate to the user postion

Project Implementation Method

The methodology that will be used in our proposed work include five major steps which involves

1. Sensing
2. Detection
3. Perception
4. Decision
5. Driving

Sensing:

To sense the environment RP-Lidar will be used which rotates at 360 degree and takes the readings of the ground truth. RP Lidar is an ease laser rangefinder, 360 degree 2D laser scanner arrangement created by Robopeak. The sensor can perform 360 degree examine inside six meters run. It checks by applying 5.5Hz when testing 360 degrees each round. 

Detection:

After the Sensing is done by the RP-Lidar the detection is done by using the Kalman Filter. The Kalman Filter (KF) is a lot of numerical conditions that when working together execute an indicator corrector sort of estimator that is ideal as in it limits the evaluated blunder covariance when some assumed conditions are met.

The KF procedure has two stages, to be specific:

Prediction step:

 The subsequent stage condition of the framework is anticipated given the past estimations

Update step:

 The present condition of the framework is assessed given the estimation around then advance

Perception:

The term restriction can be characterized as a work to decide and look through a place of an article, individuals or a particular area. At that point, the portable robot limitation can be noted as a moving robot that needs to work to discover a place of a specific objective. As indicated by Thrun et al [4], the versatile robot limitation is a procedure of building up a correspondence between the guides facilitate framework and the robots nearby organize framework. Mapping can be depicted as a procedure to show condition dependent on the encompassing data which is spoken to in a graphical picture. The guide can be displayed as a metric' or topological'.

Mapping helps confinement by demonstrating the objective or item positions in which region the article is found. Likewise, it aides depicting the earth or floor plan. There are numerous ways to deal with do condition mapping, for example, inhabitance lattice map, topological guide, highlight, or milestone guide and output guide utilizing the crude information.

Decision:

Now after all the process has undergone and the map is generate now the robot will make the decision to either to move or not by detecting the obstacles placed in its way and after detecting obstacles the robot takes the shortest path to reach the final destination.

Obstacle detection and tracking is an important content of autonomous vehicle environment perception. And it is also an important basis for path planning and decision- making of autonomous vehicle.

Driving:

After all the conditions are met and the map is generated the robot will then start to move and will follow the shortest path and after avoiding the obstacles it will get towards the final points that will be provided to the robot by the GSM module

Benefits of the Project

This autonomous wheelchair is to assist disabled people in their mobility, by warning of obstacles in the way and by assisting in the navigation to return back home. Provides additional useful capabilities for the hospital environment.Few patients such as quadriplegic's and multiple sclerosis type cannot drive joystick so we added a voice recognition system that is used to detect and recognizes that patient's voice and its output is the result of wheelchair is simultaneous movement.User call the wheelchair to its position and then wheel chair self localize itself in the unknown environment and navigate to the user postion

Technical Details of Final Deliverable

1) Autonomous wheelchair based on Hector-Slam for map generation. 

2) GPS as well as bluetooth communication with the help of Rp-Lidar for navigation purpose.

3) Voice Recognization for wheelchair movement.

4) Joystick for wheelchair movement.

5) Android application for overall controlling for visualization and for the purpose to call the wheelchair towards the user.

Final Deliverable of the Project

HW/SW integrated system

Core Industry

Health

Other Industries

Core Technology

Robotics

Other Technologies

Sustainable Development Goals

Required Resources

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