This paper presents a type-2 fuzzy inference tree designed for a differential wheeled mobile robot that navigates in indoor environments. The proposal consists of a controller designed for obstacle avoidance, a controller for path recovery and goal reaching, and a third controller for the real-time selection of behaviors. The system takes as inputs the information provided for a 2D laser range scanner, i.e., the distance of nearby objects to the robot, as well as the robot position in space, calculated from mechanical odometry. The real performance is evaluated through metrics such as clearance, path smoothness, path length, travel time and success rate. The experimental results allow us to demonstrate an appropriate performance of our proposal for the navigation task, with a higher efficiency than the reference methods taken from the state of the art.

In the self-driving vehicles domain, steering control is a process that transforms information obtained from sensors into commands that steer the vehicle on the road and avoid obstacles. Although a greater number of sensors improves perception and increases control precision, it also increases the computational cost and the number of processes. To reduce the cost and allow data fusion and vehicle control as a single process, this research proposes a data fusion approach by formulating a neurofuzzy aggregation deep learning layer; this approach integrates aggregation using fuzzy measures $\mu$ as fuzzy synaptic weights, hidden state using the Choquet fuzzy integral, and a fuzzy backpropagation algorithm, creating a data processing from different sources. In addition, implementing a previous approach, a self-driving neural model is proposed based on the aggregation of a steering control model and another for obstacle detection. This was tested in an ROS simulation environment and in a scale prototype. Experimentation showed that the proposed approach generates an average autonomy of $95\%$ and improves driving smoothness by $9\%$ compared to other state-of-the-art methods.

In the field of image processing, noise represents an unwanted component that can occur during signal acquisition, transmission, and storage. In this paper, we introduce an efficient method that incorporates redescending M-estimators within the framework of Wiener estimation. The proposed approach effectively suppresses impulsive, additive, and multiplicative noise across varied densities. Our proposed filter operates on both grayscale and color images; it uses local information obtained from the Wiener filter and robust outlier rejection based on Insha and Hampel’s tripartite redescending influence functions. The effectiveness of the proposed method is verified through qualitative and quantitative results, using metrics such as PSNR, MAE, and SSIM.

A common factor in road accidents is due to inattention in the driving task (drowsiness, distraction, etc.). Therefore, areas such as intelligent transportation systems are in continuous development to provide greater security. An example are the assistance systems that focus on improving occupant safety by merging information from sensors that recognize the environment, processing with methods and algorithms that detect risk situations that are addressed with the activation of actuators and/or recommendations to the driver. This article proposes an assistance system that detects the driver's inattention level and displays a series of alerts. The system obtains information through computer vision and performs the inference with fuzzy logic, the system is implemented on the embedded NVIDIA Jetson TX2 platform. Real-time experiments show that the proposed system is highly efficient to find drowsiness and alert the driver, obtaining a detection rate > 0.90 and a precision > 0.88.