**9. Conclusions**

*Geographic Information Systems in Geospatial Intelligence*

**8. Obstacle avoidance navigation systems**

context-aware. More examples can be found in [16].

**8.1 Image processing obstacle avoidance navigation**

A comprehensive automated navigation system must incorporate effective tools for detecting road obstacles and instantly propose the optimal alternate route bypassing the detected obstacle. It combines optimal route finding, real-time route inspection, and route adjustments to ensure safe navigation. The following are three examples utilizing advanced technologies such as computer vision, fuzzy logic, and

Unmanned aerial vehicles (UAVs) use vision as the principal [17] source of information through the monocular onboard camera. The system compares the obtained image to the obstacles to be avoided. Micro aerial vehicle (MAV), to detect and avoid obstacles in an unknown controlled environment. Only the feature points are compared with the same type of contrast, achieving a lower computational cost without reducing the descriptor performance. After detecting the obstacle, the vehicle should recover the path. The algorithm starts when the vehicle is closer to the obstacle than the distance allowed. The limit area value is experimentally obtained defining the dimensions of obstacles in pixels at a specific distance. The output of the control law moves the vehicle away from the center of the obstacle avoiding it. If the error is less than zero, the vehicle moves to the right side.

Detouring of permanent obstacles, a preliminary process is applied to scan the route and correct it such that the corrected route already considers all known obstacles

Mobile robots perform tasks such as rescue and patrolling. It can navigate intelligently by using sensor control techniques [18]. Several techniques have been applied for robot navigation and obstacle avoidance. Fuzzy logic technique is inspired by human perception-based reasoning. It has been applied to behavior-based robot navigation and obstacle avoidance in unknown environments. It trains the robot to navigate by receiving the obstacle distance from a group of sensors. A reinforcement learning method and a genetic algorithm optimize the fuzzy controller for improving its performance while the robot moves. Comparing the performance of different functions such as triangular, trapezoidal, and Gaussian for mobile robot navigation shows that the Gaussian membership function is more efficient for

**8.2 Fuzzy logic technique for mobile robot obstacle avoidance navigation**

A similar concept is using neural network learning method to construct a path planning and collision-free for robots. Real-time collision-free path planning is more difficult when the robot is moving in a dynamic and unstructured

The system is composed of three embedded components; a map manager, a motion tracker, and a hindrance dodging [19]. The map manager generates semantic maps from a given building model. The hindrance dodging detects visible objects lying on the road and suggests a safe bypass route to the target location. A developed prototype performed very well proving that this navigation system is effective

**8.3 Context-aware mobile wearable system with obstacle avoidance**

**24**

and skips them.

navigation.

environment.

and efficient.

This chapter introduces various complementing navigation concepts and implementations, integrating advanced technologies and improving and expanding existing traditional navigation solutions. The outcome is a wide variety of solutions for cases where standard navigation technologies such as GPS are less effective or not applicable. We presented several areas where various technologies have been tailored to specific problems. For each problem we described different cases with unique technologies and implementations.
