This correspondence presents a new approach that utilizes evolutionary computation and proportional-integral differential (PID) control to a multi-input multioutput (MIMO) nonlinear system. This approach is demonstrated through a laboratory helicopter called the twin rotor MIMO system (TRMS). The goals of control are to stabilize the TRMS in significant cross-couplings, reach a desired position, and track a specified trajectory efficiently. The proposed control scheme includes four PID controllers with independent input. In order to reduce total error and control energy, all parameters of the controller are obtained by a real-value-type genetic algorithm (RGA) with a system performance index as the fitness function. The system performance index was applied to the integral of time multiplied by the square error criterion to build a suitable fitness function in the RGA. We also investigated a new method for the RGA to solve more than ten parameters in the control scheme. The initial search range of the RGA was obtained by a nonlinear control design (NCD) technique. The NCD provided a narrow initial search range for the RGA. This new method led chromosomes to converge to optimal solutions more quickly in a complicated hyperplane. Computer simulations show that the proposed control scheme conquers system nonlinearities and influence between two rotors successfully.

In this paper, a learning scheme using a fuzzy controller to generate walking gaits is developed. The learning scheme uses a fuzzy controller combined with a linearized inverse biped model. The controller provides the control signals at each control time instant. The algorithm used to train the controller is "backpropagation through time". The linearized inverse biped model provides the error signals for backpropagation through the controller at control time instants. Given prespecified constraints such as the step length, crossing clearance, and walking speed, the control scheme can generate the gait that satisfies these constraints. Simulation results are reported for a five-link biped robot.

This study proposes using unmanned aerial vehicles (UAVs) to carry out tasks involving path planning and obstacle avoidance, and to explore how to improve work efficiency and ensure the flight safety of drones. One of the applications under consideration is aquaculture cage detection; the net-cages used in sea-farming are usually numerous and are scattered widely over the sea. It is necessary to save energy consumption so that the drones can complete all cage detections and return to their base on land. In recent years, the application of reinforcement learning has become more and more extensive. In this study, the proposed method is mainly based on the Q-learning algorithm to enable improvements to path planning, and we compare it with a well-known reinforcement learning state–action–reward–state–action (SARSA) algorithm. For the obstacle avoidance control procedure, the same reinforcement learning method is used for training in the AirSim virtual environment; the parameters are changed, and the training results are compared.

This study proposes a marine trash detection system based on unmanned aerial vehicles (UAVs) and aims to replace manpower with UAVs to detect marine trash efficiently and provide information to government agencies regarding real-time trash pollution. Internet technology and computer–machine interaction were applied in this study, which involves the deployment of a marine trash detection system on a drone’s onboard computer for real-time calculations. Images of marine trash were provided to train a modified YOLO model (You Look Only Once networks). The UAV was shown to be able to fly along a predefined path and detect trash in coastal areas. The detection results were sent to a data streaming platform for data processing and analysis. The Kafka message queuing system and the Mongo database were used for data transmission and analysis. It was shown that a real-time drone map monitoring station can be built up at any place where mobile communication is accessible. While a UAV is automatically controlled by an onboard computer, it can also be controlled through a remote station. It was shown that the proposed system can perform data analysis and transmit heatmaps of coastal trash information to a remote site. From the heatmaps, government agencies can use trash categories and locations to take further action.