Once it is determined that the robot is in a collision course with an obstacle detected, the distance to that obstacle from the robot is estimated continuously.
The robot itself can navigate obstacles, detect lines and report back by using infrared, grey scale, and sound speakers.
This ability is useful, for example, for quickly determining location, navigating around obstacles, detecting threats, and guiding eye movements to gather more information.
Once the obstacle detected is avoided, the steering agent informs the obstacle detection agent that the obstacle is avoided and the navigation agent directs the steering agent to continue to follow a straight path.
Section "Obstacle avoidance" elaborates on the obstacle avoidance algorithm and the methods to estimate distance to the obstacle detected.
Once the distance to the obstacle detected is less than the critical distance, the robots perform a turning manoeuvre to avoid the obstacle.
But AR Drone and Turtlebot travel in different directions while avoiding the first obstacle, as the location of the obstacle detected is different.
The robots move forward in a straight line path if there is no obstacle detected or if the distance to the obstacle is greater than the critical distance or if the obstacle avoidance process is completed.
If the robot has moved 0.8 m from the point where a turning manoeuvre is initiated and if there is no obstacle detected, the robot stops the turning manoeuvre and moves forward in the same direction.
If any obstacle is detected, a feedback module then generates warnings and directions to avoid the obstacle(s) which are conveyed to the user via audio and vibrotactile feedback.
The device navigates garden obstacles by either the boundary wire (around a flower bed for example) or through a traction sensor device which makes it automatically back away from any obstacle it detects (a tree for example).
