Path planning for blind people using ultrasonic

Path planning for blind people using ultrasonic
Abstract:
An apparatus and method for aiding a visually impaired or blind person to detect, identify and avoid objects in the field of vision of the surroundings. The apparatus includes ultrasonic sensors devices to detect and identify objects, a control unit, which receives and processes information from the devices and a audio representation unit to receive instructions from the control unit for purpose of audibly describing the objects to the person in the field of vision, thereby enabling the person to cope and proceed safely in the surroundings. The method for aiding a visually impaired person to detect, identify and objects in the field of vision surroundings includes the steps of receiving visual images of the objects, receiving range information concerning the objects, processing the image information, and audibly describing to the person the objects in the field of vision, thereby enabling the person to cope with, and proceed in his surroundings.
Electronic and computerized systems for helping visually impaired and blind people are well known in the art. This project describes an ultrasound based system which gives a proximity warning and is embodied in a cane. The cane is equipped with sensors to calculate the distance to nearby obstacles and guide the user away from potential collisions. The cane is pushed by the user ahead of him and it maneuvers itself around obstacles by means of two steerable wheels.
However, when the user approaches an object, like a closed door through which he wishes to pass, the cane tends to guide the user away from the door. The robotic cane's guidance can be overridden or modified via a controller incorporated into the handle. Where there is direct conflict between the commands of the computer and the human such as walking up to a door the cane is set to respond to the human's commands. In situations that are less clear, the computer's and human's commands are combined. For example, where a person directs the cane to turn right but the cane senses an object in the way, the cane would turn slightly to the right, accommodating both the user and sensor inputs. A task which appears beyond the capabilities of the disclosed cane is that it cannot prevent a user from stepping off a curb into traffic.

Introduction:
These objects, and others not specified hereinabove, are achieved by an exemplary embodiment of the present invention, wherein the system of the present invention is designed to aid visually impaired or blind people to detect, identify and avoid obstacles on their way and assist in finding their way to a specific target. The integration of ultrasonic sensors with microcontroller and. The system of the present invention is compact and light weight, and can be mounted on head of the blind person.
The system of the present invention provides detection and identification of fixed or moving obstacles, and can provide estimates of the relative range, speed and bearings of several simultaneous obstacles and objects. The system of the present invention alerts the blind person of immediate danger and provides the needed information by synthesized audio.
The system of the present invention has small physical dimensions, allowing the user free movement. Object identification and description is provided for a range up to 20 meters, as well as alerts for potential close range obstacles between one and two meters away, including stationary and moving objects, and changes in ground level, for example, steps or a ramp. The system gives estimates of the relative speed of objects, such as “moving fast towards you,” or “moving away”, etc.
A continuous audio description is provided according to the relevance and level of threat. The system of the present invention has the ability to “concentrate” on a specific object in order to achieve a higher level of details, and has the ability to read signs. A capability to “learn” is built in, thereby continually adding to the stored environment model with new objects, relevant details and description methods.

Working Principle:
The input unit comprises two ultrasonic sensors and an optional third sensor in order to compute the distance to the point on the surface of any object in the field of vision. In the optional arrangement, sensor is used in order to project a structured wave grid on the objects in the field of vision, while both sensors are used to compute the distance to the object's points in addition to their roles..
The sensors processor and control unit performs the necessary integration between the sensed data streams from the sensors, and the computation needed in order to relate distance to each grid point in the field of vision. Control unit also functions to adapt the sensors to any required depth of the field of vision. The input unit is wired or wirelessly linked via port to the controller unit. This link enables bi-directional flow of information.
In addition, the system includes the grouping of known objects into classes, the common properties of classes, and the common relations between classes of objects. For example, a specific chair will be described as composed of four column shaped components (legs), arranged as a rectangle with a flat horizontal board on top (seat). It belongs to a class of objects named Chair. This class has common physical dimensions, typical ranges of height width and typical behavior in time—it is stationary.
The recognition process makes use of all available information that can be extracted from the sensed data. Internal structure or shape is the way the object is composed of lower level (fewer complexes) components, e.g. the way a bench is composed of the legs seat and backrest, and the relations among them. The object's measurable properties are its physical dimensions. For example, the typical size of a bench is 1 meter wide and 130-150 cm high. The object's typical relations with other object classes in the surrounding neighborhood include physical relations like beside, on top, above etc. The recognition process follows the principle that recognition is achieved if the information available is enough to define it as belonging to a unique object class.

COMPONENTS USED:
 Microcontroller
 Ultrasonic Sensors
 Mini-speaker
 Power supply etc,
SOFTWARE USED:
 Keil C Compiler
 Embedded C

Advantages:
The system of the present invention has small physical dimensions, allowing the user free movement. Object identification and description is provided for a range up to 20 meters, as well as alerts for potential close range obstacles between one and two meters away, including stationary and moving objects, and changes in ground level, for example, steps or a ramp.
Disadvantages:
 If sensors fail, total system won’t work.
Applications:
 Useful for Blind Persons