Daejung Shin

Fuzzy neural networks for obstacle pattern recognition and collision avoidance of fish robots

The problems of detection and pattern recognition of obstacles are the most important concerns for fish robots’ path planning to make natural and smooth movements as well as to avoid collision. We can get better control results of fish robot trajectories if we obtain more information in detail about obstacle shapes. The method employing only simple distance measuring IR sensors without cameras and image processing is proposed. The capability of a fish robot to recognize the features of an obstacle to avoid collision is improved using neuro-fuzzy inferences. Approaching angles of the fish robot to an obstacle as well as the evident features such as obstacles’ sizes and shape angles are obtained through neural network training algorithms based on the scanned data. Experimental results show the successful path control of the fish robot without hitting on obstacles.

Fish Robots for Water Pollution Monitoring Using Ubiquitous Sensor Networks with Sonar Localization

A new method is proposed to build an autonomous water pollution monitoring map by fish robots using ubiquitous sensor networks with sonar localization. Autonomous fish robots are introduced instead of fixed data logging stations to track pollutant sources as well as monitoring. Autonomous tracking is one of important functions in mobile underwater vehicles which monitor water pollution indices. When fish robots find obstacles on its path, proper direction changes to avoid collision are necessary. Otherwise, they should follow the given tracks as close as possible to obtain a pollution map. For efficient tracking performance and procedures of surveying water areas, fish robots use GPS and a sonar system to find exact localization. Although GPS is a fundamental tool to obtain positional information for large areas, it is not the best choice in accurate applications due to intolerable errors. In this paper, we propose to employ USN motes with sonar system to transmit sonar signals to calculate precise positional information in a given area. Our experimental results in a lake show that fish robots obtain more detailed positional information and make better tracking performance in the real situation.

Collision recognition and direction changes using fuzzy logic for small scale fish robots by acceleration sensor data

For natural and smooth movement of small scale fish robots, collision detection and direction changes are important. Typical obstacles are walls, rocks, water plants and other nearby robots for a group of small scale fish robots and submersibles that have been constructed in our lab. Two of 2-axes acceleration sensors are employed to measure the three components of collision angles, collision magnitudes, and the angles of robot propulsion. These data are integrated using fuzzy logic to calculate the amount of propulsion direction changes. Because caudal fin provides the main propulsion for a fish robot, there is a periodic swinging noise at the head of a robot. This noise provides a random acceleration effect on the measured acceleration data at the collision instant. We propose an algorithm based on fuzzy logic which shows that the MEMS-type accelerometers are very effective to provide information for direction changes.

Sonar Localization Using Ubiquitous Sensor Network for Water Pollution Monitoring Fish Robots

We present a sonar localization method using ubiquitous sensor network for autonomous water pollution monitoring fish robots. Autonomous tracking is one of important functions in mobile underwater vehicles which monitor water pollution indices. When fish robots find obstacles on its path, proper direction changes to avoid collision are necessary. Otherwise, they should follow the given tracks as close as possible to obtain a pollution map. For efficient tracking performance and procedures of surveying water areas, fish robots use GPS and a sonar system to find exact localization. Although GPS is a fundamental tool to obtain positional information, it is not the best choice in our system due to large errors. Fish robots need to have more precise localization methods. In this paper, we propose to employ USN motes with sonar system to transmit ultrasonic sound to calculate precise positional information. Our experimental results show that fish robots obtain more detailed positional information and make better tracking performance in the real situation.

Obstacle Recognition and Collision Avoidance of a Fish Robot Based on Fuzzy Neural Networks

Detection and recognition of obstacles are the most important concerns for fish robots to avoid collision for path planning as well as natural and smooth movements. The more information about obstacle shapes we obtain, the better control of fish robots we can apply. The method employing only simple distance measuring sensors without cameras is proposed. We use three fixed IR sensors and one IR sensor, which is mounted on a motor shaft to scan a certain range of foreground from the head of a fish robot. The fish robot’s ability to recognize the features of an obstacle is improved to avoid collision based on the fuzzy neural networks. Evident features such as obstacles’ sizes and angles are obtained from the scanned data by a simple distance sensor through neural network training algorithms. Experimental results show the successful path control of the fish robot without hitting on obstacles.

Estimation of sound direction for improved interaction of entertainment dolphin robots

In this paper, in order to improve the entertainment dolphin robotpsilas ability to interact with people, a pair of microphones as the ears of a dolphin robot is used to estimate the peak sound directions from surrounding viewers. Dolphin robots should turn towards people who want to interact with them, while swimming autonomously. A pair of left and right microphones is located to form the binaural ears of a dolphin robot. Since the magnitudes of the measured microphone signals decrease as the difference between directions of the microphone and sounds increases, the magnitudes of the left and right signals of microphones are compared to find the sound direction relative to the robotpsilas body line. The same rule applies to the second pair of microphones to determine the sound direction relative to the front.

Fuzzy Distance Estimation for a Fish Robot

We designed and implemented fish robots for various purposes such as autonomous navigation, maneuverability control, posture balancing and improvement of quick turns in a tank of 120 × 120 × 180㎝ size. Typically, fish robots have 30-50 × 15-25 × 10-20㎝ dimensions; length, width and height, respectively. It is essential to have the ability of quick and smooth turning to avoid collision with obstacles or walls of the water pool at a close distance. Infrared distance sensors are used to detect obstacles, magneto-resistive sensors are used to read direction information, and a two-axis accelerometer is mounted to compensate output of direction sensors. Because of the swing action of its head due to the tail fin movement, the outputs of an infrared distance sensor contain a huge amount of noise around true distances. With the information from accelerometers and e-compass, much improved distance data can be obtained by fuzzy logic based estimation. Successful swimming and smooth turns without collision demonstrated the effectiveness of the distance estimation.

Development and Performance Analysis of Artificial Muscle for Fish Robots Using Water Pumps

A new method is proposed to build artificial muscle for fish robots using water pumps and bellows rubber pipes. Since bio-mimetic robots mimic the patterns of behaviours of real animals, it is natural for actuators of robots to adopt the actuating patterns of muscle fibres.The proposed actuator, called artificial muscle, has several advantages. The artificial muscle units have been applied in various types of fish robots which have been developed in our lab. The muscle units replace conventional motors for various kinds of movements. When direction changes are necessary for a fish robot, a muscle unit can change the directions of a tail fin or its lower body just like real muscle does. The experimental results in a pond show that fish robots swim smoothly using artificial muscle units.

Protection of orchard from wild animals and birds using USN facilities

Orchard fruits are vulnerable to wild birds and animals. One peck on fruit results in critical damage to the produce. Therefore, it is very important to monitor the nearby presence of birds and animals. Then the actuation of various devices should follow to repel the hazardous animals. Traditional methods have been widely applied depending on the kinds of produce and imperiling animals. In this paper, we propose a method to protect orchard produce from wild animals and birds via ubiquitous sensor network devices, which is applied to orchards along with traditional methods to improve the protection performance. Microphones and camera modules are added to the basic sensors on the USN nodes. Camera images are analyzed for a wide area monitoring. Audio signals from microphones are used for nearby monitoring around a node. Infrared motion sensors are utilized mainly for the detection of animal intrusion from the outside of orchards. The proposed monitoring scheme is to provide an early warning about possible intrusion and damage by wild animals and birds via the use of USN nodes in addition to the traditional devices.

Detection and classification of pipelines for mobile monitoring robots

Special types of mobile robots are necessary for the pipeline monitoring tasks. One of the bio-mimetic robot applications serves the purpose of exploring pipelines, spotting any troubled areas or malfunctions and reporting its data. Moreover, the robot is able to prepare for and react to any abnormal routes in the pipeline. In order to move effectively along a pipeline, the robots movement will resemble that of insects. When situated in massive pipelines with complex routes, the robot should have the abilities of route recognition and mobility while monitoring the pipelines. The robots have grippers to hold the pipes and four arms with three DOF joints to move on the pipelines. This monitoring task is to prevent a major system failure by preemptively recognizing any minor or partial malfunctions.