Vision-driven autonomous flight and obstacle avoidance of Unmanned Aerial Vehicles (UAVs) along complex riverine environments for tasks like rescue and surveillance requires a robust navigation policy, which is yet difficult to obtain due to the shortage of trainable riverine environment simulators. To easily verify the vision-based navigation controller performance for the river following task before real-world deployment, we developed a trainable photo-realistic dynamics-free riverine simulation environment using Unity. In this paper, we address the shortcomings that vanilla Reinforcement Learning (RL) algorithm encounters in learning a navigation policy within this partially observable, non-Markovian environment. We propose a synergistic approach that integrates RL and Imitation Learning (IL). Initially, an IL expert is trained on manually collected demonstrations, which then guides the RL policy training process. Concurrently, experiences generated by the RL agent are utilized to re-train the IL expert, enhancing its ability to generalize to unseen data. By leveraging the strengths of both RL and IL, this framework achieves a faster convergence rate and higher performance compared to pure RL, pure IL, and RL combined with static IL algorithms. The results validate the efficacy of the proposed method in terms of both task completion and efficiency. The code and trainable environments are available1.

Autonomous Underwater Vehicles (AUVs) are a vital element for ocean exploration in various applications; however, energy sustainability still limits long-term operations. An option to overcome this problem is using underwater docking for power and data transfer. To robustly guide an AUV into a docking station, we propose an underwater vision algorithm for short-distance detection. In this paper, we present a Convolutional Neural Network architecture to accurately estimate the dock position during the terminal homing stage of the docking. Additionally, to alleviate the lack of available underwater datasets, two methods are proposed to generate synthetic datasets, one using a CycleGAN network, and another using Artistic Style transfer network. Both methods are used to train the same CNN architecture to compare the results. Finally, implementation details of the CNN are presented under the backseat architecture and ROS framework, running on an IVER3 AUV.

The paper discusses how robots enable occupant-safe continuous protection for students when schools reopen. Conventionally, fixed air filters are not used as a key pandemic prevention method for public indoor spaces because they are unable to trap the airborne pathogens in time in the entire room. However, by combining the mobility of a robot with air filtration, the efficacy of cleaning up the air around multiple people is largely increased. A disinfection co-robot prototype is thus developed to provide continuous and occupant-friendly protection to people gathering indoors, specifically for students in a classroom scenario. In a static classroom with students sitting in a grid pattern, the mobile robot is able to serve up to 14 students per cycle while reducing the worst-case pathogen dosage by 20%, and with higher robustness compared to a static filter. The extent of robot protection is optimized by tuning the passing distance and speed, such that a robot is able to serve more people given a threshold of worst-case dosage a person can receive.

The use of human-interactive robots in industry and daily life has become more prevalent throughout society as more people are using collaborative, and assistive robots to accomplish a task. To demonstrate the utility and importance of assistive robots to middle school students, a unique educational platform called Neu-pulator (neurally-controlled manipulator) was designed and fabricated to introduce their application in improving the quality of life. This robotic manipulator consists of low-cost components, which reflect the characteristics of a human arm, and is actuated by signals from the students neuromuscular system. During summer 2016, a 5-day program introduced students to the engineering design process as they designed, programmed, manufactured, and tested the Neu-pulator robot. A series of surveys and group interviews were performed to understand how each students attitude and opinion towards different STEM-related topics evolved throughout the course, both quantitatively and qualitatively. We observed that the students confidence, attitude, and excitement towards STEM improved over the course of the week, especially when they could see the robot they developed in action. With the use of this unique educational platform, a bridge can be made from learning fundamental STEM concepts to real-world application of human interactive and assistive robots.

With the increased influence of automation into every part of our lives, tomorrow's engineers must be capable working with autonomous systems. The explosion of automation and robotics has created a need for a massive increase in engineers who possess the skills necessary to work with twenty-first century systems. Autonomous Systems (MEEM4707) is a new senior/graduate level elective course with goals of: 1) preparing the next generation of skilled engineers, 2) creating new opportunities for learning and well informed career choices, 3) increasing confidence in career options upon graduation, and 4) connecting academic research to the students world. Presented in this paper is the developed curricula, key concepts of the project-based approach, and resources for other educators to implement a similar course at their institution. In the course, we cover the fundamentals of autonomous robots in a hands-on manner through the use of a low-cost mobile robot. Each student builds and programs their own robot, culminating in operation of their autonomous mobile robot in a miniature city environment. The concepts covered in the course are scalable from middle school through graduate school. Evaluation of student learning is completed using pre/post surveys, student progress in the laboratory environment, and conceptual examinations.

This paper describes the details of a theme-based and hands-on STEM learning program utilizing an underwater robot called GUPPIE. Glider for Underwater Problem-solving and Promotion of Interest in Engineering (GUPPIE) is an example of a robot with oceanographic and environmental monitoring application. GUPPIE helps students to learn about fundamentals of physics (buoyancy, gravity, drag and lift force), electronics (circuitry and power distribution), programming, building (using tools and assembly), and testing in a systematic way. In this work we analyse the effects of the hands-on activities with meaningful context on students' 1) confidence level; 2) attitude towards robotics; 3) and level of interest towards STEM careers. The survey results suggest that using robots with sensible real world applications improves young students' attitudes and interests towards robotics. Based on these results, introducing young students to topics that are not part of official school curriculum, such as programming, increases the excitement and confidence in early ages, especially for girls, and can result in pursuing STEM related subjects in higher education. Results also revealed tha.t girls are more interested in building while boys are more attracted to programming.

This paper presents an architecture for the development of mobile microgrids using autonomous vehicles for the recovery of electrical power in postdisaster scenarios. The goal is to facilitate the integration of the different disciplines involved and address interrelated challenges in interaction between the disparate components of the system and the physical world. The architecture described in this paper has emerged through a combination of hardware development and experimental studies. The proposed layout will create an autonomous mobile microgrid system consisting of a team of ground robots capable of navigating in a disaster-affected area, making electrical connections, and supplying and controlling the electrical power needed by the loads in the area. This system has the scalability characteristics of an ad hoc system and can reconfigure itself depending on the changes in demanded performance of the microgrid.

An underwater glider named ROUGHIE (Research Oriented Underwater Glider for Hands-on Investigative Engineering) is designed and manufactured to provide a test platform and framework for experimental underwater automation. This paper presents an efficient multi-level motion controller that can be used to enhance underwater glider control systems or easily modified for additional sensing, computing, or other requirements for advanced automation design testing. The ultimate goal is to have a fleet of modular and inexpensive test platforms for addressing the issues that currently limit the use of autonomous underwater vehicles (AUVs). Producing a low-cost vehicle with maneuvering capabilities and a straightforward expansion path will permit easy experimentation and testing of different approaches to improve underwater automation.

Buoyancy-driven underwater gliders (UGs) have proven to be quite effective for long-range, long-term oceanographic sampling. However, current off-the-shelf UGs are large, heavy, expensive, and difficult to modify, both in hardware and software, which prevents their frequent use for lake observations and limits researchers' ability to perform multi-vehicle coordination experiments. Our current research goal is to develop UGs that would share the buoyancy-driven concept with the first generation of gliders, but are smaller in size, lighter in weight, and lower in price. Our future research goal is to design and develop an underwater glider fleet that will result in novel and transformative research capabilities in coordinated control. Along with advancing research and broadening data collection ability, UGs provide a hands-on tool for engaging students in sophisticated STEM learning. This paper describes in detail the design, manufacturing, and modeling of our inexpensive Glider for Underwater Problem-solving and Presentation in Education (GUPPIE). GUPPIE was developed using practical components such as syringes for buoyancy control and a hull made of acrylic for easy analysis. The design is both affordable and easy-to-duplicate. GUPPIE's pedagogical platform provides hands-on learning applications that demonstrate glider mechanics, mechatronics, hydrodynamics, trimming, diving and surfacing performance, and mobility in water.