The Research of Maneuverability Modeling and Environmental Monitoring Based on a Robotic Dolphin

In this study, the C-turning, pitching, and flapping propulsion of a robotic dolphin during locomotion were explored. Considering the swimming action required of a three-dimensional (3D) robotic dolphin in the ocean, we propose a maneuverability model that can be applied to the flapping motion to provide precise and stable movements and function as the driving role in locomotion. Additionally, an added tail joint allows for the turning movement with efficient parameters obtained by a fluid-structure coupling method. To obtain a mathematical model, several disturbance signals were considered, including systematic uncertainties of the parameters, the perpetually changing environment, the interference from obstacles with effective fuzzy rules, and a sliding mode of control. Furthermore, a combined strategy of environment recognition was used for the positional control of the robotic dolphin, incorporating sonar, path planning with an artificial potential field, and trajectory tracking. The simulation results show satisfactory performance of the 3D robotic dolphin with respect to flexible movement and trajectory tracking under the observed interference factors.

The educational community and its knowledge and perceptions of native and invasive alien species

Environmental education seeks to foster an appreciation for nature and the impact of humans on it while introducing citizens to scientific thinking. Biological invasions affect different aspects of life on earth and mandate urgent management actions. Education and public awareness are strongly recommended for successful prevention and management of invasive alien species (IAS). This work presents a study on knowledge and perception of the educational community of Argentina about native species and IAS. We designed an on-line semi-structured questionnaire to examine perception of the environment, recognition of native species and IAS and awareness about biological invasions. Educators recognised an important number of biotic components, mostly represented by trees, birds and mammals. Recognition of native species and IAS, and awareness of biological invasions were different between NST (Natural Science Teachers) and non-NST. Respondents had different performances when they were exposed to recognising native species though written names or photographs. Out of 532 respondents, 56% knew what biological invasions are, 21% answered “Maybe” and 23% had never heard about them. We need to foster capacity-building and encourage a two-way communication between educators and scientists, formally and informally, to engage the participation of the whole society in recognition, prevention and management of IAS.

Intelligent Highway Traffic Detection Algorithm based on Deep Learning

In order to solve the increasingly serious traffic congestion problem, an intelligent transportation system is widely used in dynamic traffic management, which effectively alleviates traffic congestion and improves road traffic efficiency. With the continuous development of traffic data acquisition technology, it is possible to obtain real-time traffic data in the road network in time. A large amount of traffic information provides a data guarantee for the analysis and prediction of road network traffic state. Based on the deep learning framework, this paper studies the vehicle recognition algorithm and road environment discrimination algorithm, which greatly improves the accuracy of highway vehicle recognition. Collect highway video surveillance images in different environments, establish a complete original database, build a deep learning model of environment discrimination, and train the classification model to realize real-time environment recognition of highway, as the basic condition of vehicle recognition and traffic event discrimination, and provide basic information for vehicle detection model selection. To improve the accuracy of road vehicle detection, the vehicle target labeling and sample preprocessing of different environment samples are carried out. On this basis, the vehicle recognition algorithm is studied, and the vehicle detection algorithm based on weather environment recognition and fast RCNN model is proposed. Then, the performance of the vehicle detection algorithm described in this paper is verified by comparing the detection accuracy differences between different environment dataset models and overall dataset models, different network structures and deep learning methods, and other methods.

“My disability does not measure me: it is a way of living and being in the world” meanings of social inclusion from the perspective of people with visual impairment

Social inclusion involves the dynamics that link the development of capacities with access to opportunities, well-being, relationship networks, and the exercise of citizenship. This study sought to understand the meanings on social inclusion of people with visual impairment from four cities in Colombia, as well as the family dynamics that favor or hinder inclusion processes. A qualitative exploratory study was conducted, by applying 26 semi-structured interviews via telephone. The interviews were transcribed and the themes extracted by the authors. The three emerging categories were the following: (1) My disability does not measure me: it is a way of living and being in the world; (2) deconstructing imaginaries: a wager on inclusion; and (3) from the family, the most important is letting be. Our results indicate that social inclusion is mediated by the meanings they assign to their own condition of visual impairment, by the existing social imaginaries on the theme, and by the family dynamics or the nearby environment. The work recognized the following as facilitators: acceptance of the disability by those who have the condition and by their close environment; recognition of the disability as part of human diversity; the family as actor that recognizes, respects individuality, and promotes their development; and the individual skills to cope with the situation and find a support network. Barriers were the negative imaginaries and the biomedical view that persist in society, which interact with the daily lives of the people, thus generating situations of exclusion.

Pedestrian Detection in Blind Area and Motion Classification Based on Rush-Out Risk Using Micro-Doppler Radar

Various remote sensing technologies have been applied in intelligent vehicles and robots for surrounding-environment recognition. However, these technologies experience difficulties in detecting pedestrians in blind areas and their motions, such as rush-out behaviors. To address this issue, we present a radar-based technique for the detection of pedestrians in blind areas and the classification of different risks of rush-out behaviors among detected pedestrians. We verify their ability to detect pedestrian motion in blind areas by conducting experiments in two environments with blind areas formed by outdoor cars and indoor walls. Then, the classification of motions with different risks of rush-out behaviors among pedestrians detected in the blind areas is demonstrated. We use the clustering method to accurately classify several types of behaviors with different rush-out risks in both environments.

Computer Vision and Deep Learning for Environment-Adaptive Control of Robotic Lower-Limb Exoskeletons

Robotic exoskeletons require human control and decision making to switch between different locomotion modes, which can be inconvenient and cognitively demanding. To support the development of automated locomotion mode recognition systems (i.e., high-level controllers), we designed an environment recognition system using computer vision and deep learning. We collected over 5.6 million images of indoor and outdoor real-world walking environments using a wearable camera system, of which ~923,000 images were annotated using a 12-class hierarchical labelling architecture (called the ExoNet database). We then trained and tested the EfficientNetB0 convolutional neural network, designed for efficiency using neural architecture search, to predict the different walking environments. Our environment recognition system achieved ~73% image classification accuracy. While these preliminary results benchmark EfficientNetB0 on the ExoNet database, further research is needed to compare different image classification algorithms to develop an accurate and real-time environment-adaptive locomotion mode recognition system for robotic exoskeleton control.