dc.description.abstract | This thesis aims to improve the guiding robot and develop a wearable device for helping visually impaired people to walk outdoor safely. The guiding robot has three improvements. First, this research uses much more training data and another semantic segmentation neural network to raise the accuracy of recognizing road, people, and cars. Second, the robot is added one more function that it will rotate to find another way if its walkable area is not enough to go through. Third, while the destination is a store, the robot will lead the blind closer to the store due to the direction information between the robot and the store signboard provided from other research team.
Next, the guiding robot will be changed to a wearable device. The wearable device has not only the same functions as the robot, but also the new algorithm which can detect the position of the crosswalks so the blind can cross the road by following the crosswalk.
The information including the guiding commands which used to guide the blind and the distances and types of obstacles in front of him/her will be broadcasted by a smartphone. To avoid interference between broadcasted messages, this research defines the priority of each message. The messages with higher priority can interrupt the broadcasting one to ensure the important information will not be missed.
In conclusion, the thesis improves the accuracy of environment recognition, has the abilities of route finding and can take the blind to the store. The wearable device has the same functions as the robot and can detect crosswalks in order to lead the visually impaired people pass the intersection safely. | en_US |