Project lead: Kostas Alexis
Summary: This project aims to investigate the problems of a) sensing, localization and mapping, as well as b) path planning that would enable a small aerial robot to explore the visually-degraded (dark, dusty, smoke-filled) environments of underground tunnels and mines. Simultaneous Localization And Mapping (SLAM) in benign, well-lit, feature-full, and geometrically well-conditioned environments is an established technology using both vision and LiDAR sensing. However, it remains particularly challenging with only few and weak visual features, self-similar geometry (such as inside a tunnel), or strong presence of smoke, fog or dust. At the same time, despite the significant progress in path planning for exploration, current state-of-the-art presents conservative, slowly exploring behaviors. Furthermore, path planning algorithms rarely account or consider possible inaccuracies and imperfections of the perception system. The result is that when the robot is tasked to navigate in a very challenging environment, researchers resort to more conservative approaches or slower and more careful navigation. An intuitive alternative would be that of inherently accounting for any inaccuracy of the perception system during the planning process and therefore select the next actions of the robot in a manner that is informed about how well it estimates its position and the map of its environment.
For aerial robots to be able to robustly operate and efficiently explore underground tunnel-like and mine environments, and therefore provide rapid means of searching and mapping, the aforementioned technical challenges have to be resolved. To achieve this goal, in this project we envision research in a) specialized sensing and multi-modal sensor fusion, as well as b) geometric reasoning-based exploration path planning. Research investigations will relate to defining the most appropriate sensor suite, developing state estimation algorithms and robust localization and mapping pipelines, as well as studies in sampling-based motion planning and reinforcement learning. In addition, the student teams working in the field of path planning will be asked to design a user interface system that would provide seamless and intuitive utilization of autonomously exploring underground robots by the untrained user.
Student Involvement: REU students will begin by observing current University research in subterranean robotic navigation and mapping, and learn how to replicate that work. The students will then select if they will work on the field of perception or planning and will proceed with relevant literature review. A focused discussion that aims to identify the limitations of the current state-of-the-art will follow. Subsequently, the students will design their own solution and approach to the problems of GPS-denied degraded visual environments navigation, exploration and mapping. The implementation phase will follow with students simultaneously building algorithmic, hardware and software development, as well as system integration skills. Finally, students will conduct the necessary experiments with participants on campus and document the results for presentation to the lab with an eye on future relevant investigations.
Project lead: David Feil-Seifer
Summary: This project will investigate how human-robot interaction is best structured for everyday interaction. Possible scenarios include work, home, and other care settings where socially assistive robotics may be used as educational aids, provide aid for persons with disabilities, and act as therapeutic aids for children with developmental disorders. In order for robots to be integrated smoothly into our daily lives, a much clearer understanding of fundamental human-robot interaction principles is required. Human-human interaction demonstrates how collaboration between humans and robots may occur. This project will study how socially appropriate interaction and, importantly, socially-inappropriate interaction can affect human-robot collaboration.
In order to explore the nature of collaborative HRI for long-term interaction, REU participants will work with project personnel to develop controlled experiments which isolate individual aspects of collaborative HRI such as conformity, honesty, mistreatment, and deference. Students will examine these factors in a single-session experiment that they design. The results from these experiments will be used to focus multi-session follow-up studies that will be conducted in-between summers. The results of this research project will be a compendium of data demonstrating how humans and robots interact in situations of daily life, such as manufacturing, education, and daily living.
Student Involvement: REU students will begin by observing current University research in human-robot teaming, and learning how to replicate that work. The students will then select an aspect of collaboration that is interesting to them and conduct a literature review on research in human-human and human-robot interaction. The students will then design their own study based on experiment design observed from this literature review and then modify existing autonomous robot code to account for changes to the experiment design. Finally, students will conduct the necessary experiments with participants on campus and document the results for presentation to the lab with an eye for a multi-session follow-up study.
Project lead: Monica Nicolescu
Project Description: The goal of this project is to investigate the use of verbal communication as a means to enhance human-robot collaboration. In collaborative domains, in addition to being capable of performing a wide range of tasks, a successful robot team member should take actions that are supportive of and that enhance collaborations. Given the criticality of communication
in teamwork, this project will investigate human-to-robot and robot-to-human communication skills, which will provide robots with the social skills necessary for effective participation in teamwork. In particular, it is important to be able to convert instructions given by humans in natural language, into executable controllers that the robot can perform. In addition, robots should be able to convey relevant information (knowledge about the task, requests for assistance, explanations for decisions, etc.) to humans and/or other robots. Toward this end, this project will address the following two problems: 1) parsing natural language instructions into executable controllers for human-to-robot communication, and 2) developing capabilities for explicit communication for robot-to-human interaction.
Student Involvement: The students will begin by studying related work that describes our supporting research, move on to writing simple controllers using our architecture, then proceed to study the use of natural language processing tools. After this initial stage, the students will proceed with generating sentences that cover a small subset of grammatical dependencies supported by the language parsers and implement procedures for converting the sentences to executable controllers. These controllers will then be tested on physical robots (Baxter, PR2). The students will implement dynamic generation of spoken utterances and will run basic experiments to validate the robot's capabilities. This will provide the students with the understanding of both aspects of communication between the human and the robot, giving them a full representation of the challenges involved in language-based human-robot interaction.
Project lead: Shamik Sengupta
Summary: Modern robotics exhibit deployment of not just single robots but rather large numbers of robotics devices networked with each other to complete various mission-critical operations. Efficient wireless communication is of paramount importance in such networked robotics environment. This project's research plan is to mentor undergraduate students with understanding of network management of heterogeneous robotics devices in a wireless environment. In this project, the undergraduate students will be learning how to develop and evaluate spectrum efficient networked robotics environment on-the-go with the help of the programmable radios.
Project lead: Hung La
Summary: Dirt cleaning is an important task for both household and industry environments, especially in environment where toxic dirt exists that human cleaners would not want to access. Having a robot or a team of robots to do this job would be beneficial. The goal of this project is to study and propose algorithms for efficient path planning of dirt cleaning robots. There are some available dirt cleaning robots such as iRobot Roomba, Samsung POWERbot, LG Hom-Bot, etc. Some of these robots just used a simple path planning technique like "random-walk" to cover the cleaning field, but some have applied more complicated algorithms like simultaneous localization and mapping (SLAM) to estimate their position and orientation to enable them to clean the field in a more systematic manner. However, in fact visiting the entire field evenly or randomly usually time consuming and not efficient, because some areas such as doors or under office tables may quickly become more dirty than the others. Therefore, it is desirable that the robots should first estimate the distribution of dirt in the environment then generate an efficient cleaning path to allow them to focus cleaning more on the dirty parts of the environment. This project will first study the problem of estimating the dirt distribution and then propose an dirt-map driven path planning for efficiently covering the field.
In order to explore the nature of autonomous robot path planning, REU participants will work with project personnel to learn SLAM, camera and laser calibration, etc., in Robotic Operating System (ROS) environment, then develop an efficient path planning algorithm for the dirt cleaning robots. Students will conduct the experiments for their proposed algorithm in a physical i-Create robot equipped with necessary sensors including laser range finders, cameras and inertial measurement units (IMUs). The results from these experiments will be used to focus multi-session follow-up studies that will be conducted in-between summers. The results of this research project will be a compendium of data demonstrating how the robots perform the dirt cleaning/collecting task.
Student Involvement: REU students will begin by observing current UNR research in autonomous mobile robots, and learning how to replicate that work. The students will then select an aspect of collaboration that is interesting to them and conduct a literature review on research in autonomous mobile robot path planning with focusing on dirt cleaning robot applications. The students will then design their own study based on experiment design observed from this literature review and then modify existing autonomous robot code to account for changes to the experiment design. The students will work with an assigned graduate student to develop an autonomous path planning for the dirt cleaning robot platform and then conduct the necessary experiments in the dirt mock environment in the Advanced Robotics and Automation (ARA) lab. Finally, the students document the results for presentation to the lab with an eye for a multi-session follow-up study.