This paper observes the exploration of Genetic Network Programming Two-Stage ReinforcementLearning for mobile robot navigation. The proposed method aims to observe its exploration when inexperienced environments used in the implementation. In order to deal with this situation, individuals are trained firstly in the training phase, that is, they learn the environment with ϵ-greedy policy and learning rate α parameters. Here, two cases are studied, i.e., case A for low exploration and case B for high exploration. In the implementation, the individuals implemented to get experience and learn a new environment on-line. Then, the performance of learning processes are observed due to the environmental changes.

-The innovation of robot technology attracts students to study and participate in many robot contests. Thus, robotic trainer is very urgent to be developed, especially an animaloid robot, which can encourage both of robotics course and robot contest. Here, the trainer was developed using seven steps of ten steps, i.e., (1) potential and problem, (2) data collection, (3) product design, (4) design validity, (5) design revision, (6) product trials, and (7) product revision. The developed trainer is a sixlegged animaloid robot, which consists of five learning modules, i.e., (1) master-slave communication, (2) ultrasonic ranger, (3) motor servos, (4) flame sensors, and (5) extinguisher. The trainer was evaluated by media and material experts, where the validation results are 94% and 90%, respectively, while the validation result in the implementation stage is 87.31%. The result can be concluded that developed trainer is feasible and can be used as the learning media.

Sea water lobster is a commodity from the sea resources that have high selling price and already encroaches international market. However, the cultivators of marine fisheries have less incentive to cultivate the sea water lobster because it is very sensitive to the environmental changes in its habitat. The environmental changes cause the decreasing appetite, vulnerable to disease, cannibalism, and lower lifespan. To prevent these problems, the researchers propose an integrated embedded system using the internet of things that can do automation process to monitor the lobster ponds. The automation system consists of temperature adjustment, pH adjustment, salinity concentration, and an automatic draining system. Beside it, this system is also equipped with a mobile application which is integrated by using internet of thing (IoT) so that the monitoring and control system of the pond can be accessed everywhere. This research aims to test the accuracy of data from the pH sensor and temperature sensor on the prototype. The test is conducted by comparing the data from the pH sensor with litmus paper and thermometer for water temperature. Based on the test result, the researcher can conclude that the data from the pH sensor is reliable and shows the actual value of pH. While, the test for temperature sensor shows the insignificant difference with a thermometer that is only 0,9ºC and 1ºC. This difference is very marginal thus the system can work properly.

No abstract

No abstract