Mountain search and rescue is a vital form of emergency response to assist people in austere environments (e.g., extreme terrain, poor weather). Volunteer mountain search and rescue teams in the United States have begun adopting consumer- grade unmanned aerial vehicles to assist a variety of tasks (e.g., search, resource delivery);...
Motion planning is a cornerstone of autonomous robots, enabling robots to safely and efficiently perform tasks such as package delivery, infrastructure inspection, and manipulation. However, as the field of robotics matures, robotic systems are being developed that (1) are challenging to analytically model, (2) require computationally expensive model-based controllers, and...
Human-robot teams involve humans and robots collaborating to achieve tasks under various environmental conditions. Successful teaming requires robots to adapt autonomously in real-time to a human teammate's state. An important element of such adaptation is the ability for the robot to infer the tasks performed by their human teammates. Human-robot...
Legged robots have consistently captured our collective imagination through various forms of media, from Hollywood films, anime, and viral Youtube videos of robots accomplishing incredible feats of acrobatics. These robots have the potential to navigate our environments, capable of completing tasks that would otherwise require human intervention. However, developing controls...
Multiagent learning offers a rich framework to address challenging real-world problems such as remote exploration and healthcare coordination, which require autonomous agents to express elaborate interactions. To be effective in such systems, agents must collectively reason about and pursue high-level, long-term, and possibly nebulous objectives while adapting their strategy to...
Disaster response and surveillance operations will increasingly incorporate Unmanned Aerial Vehicles (UAV)s due to their cost-effectiveness and maneuverability. This trend has driven the research on small-sized quadcopters for varying indoor applications. Small-sized quadcopters' payload and computational capacity limit the usage of complex vision-based collision avoidance algorithms that are employed by...
Multiagent approaches are well suited to designing autonomous solutions for systems that feature complex interactions between many individuals such as in autonomous traffic systems and multi-robot exploration systems. However, creating autonomous agents that function effectively in these systems is a challenging task. In these complex environments, agents need informative reward...
Successful pruning relies on accurately identifying the 3D structure of tree branches and leaders. However, this task is arduous in an agricultural setting due to the complexity of scenes, the presence of clutter, and variable weather conditions. This project addresses these challenges by leveraging advancements in 2D image segmentation and...
Expressive motion has been found to be a highly effective tool in communicating intent and motivation in single robot human-robot interaction, but work in exploring how groups of robots can use motion in interactions with humans is relatively nascent. There are many additional complexities to consider expanding from single robot...
In recent years, model-free Deep Reinforcement Learning (RL) has become an increasingly popular alternative to more traditional model-based or optimization-based control methods in solving robotic legged locomotion. However, deploying RL in the real world can be a significant undertaking. Constructing reward functions which compel controllers to learn the desired behavior...
Fingered robot hands are complicated systems made of three essential system components: its morphology, its actuation, and its software control. These system components are tightly coupled to each other. Due to this, it is hard to benchmark robot hand performance in a way to understand the contributions of the individual...
This project covers the construction of a Stereo Camera System, integration with a Velodyne VLP-16 LIDAR and the creation of dataset intended to aid in the development of vision algorithms for forestry applications. This project is the first step in a future multi-stage project to implement computer vision systems for...
Multi-robot teams offer promising solutions for many long term deployments in remote and dangerous domains, such as extraterrestrial or underseas exploration. However, long term deployments present many problems preventing robot teams from operating effectively. Learning over long time scales is makes it difficult to assign credit to robots' actions, as...
Social robots benefit from a sense of humor, which requires the ability to recognize and adapt to human responses during playful interactions. Past work on humorous robots has classified audience responses with audio-based and preliminary visual-based methods following the joke punchline. Building on this progress, we conducted a survey of...
Commercial and public safety usage of Unmanned Aerial Vehicles in the National Airspace is currently restricted by federal regulation. The Federal Aeronautics Association is interested in modifying the restrictions; however, research is needed to study the human factor and required aptitude for a single human operating multiple UAVs. This Master’s...
This dissertation presents novel, field-activated smart material systems for the actuation and control of autonomous robots. Smart materials, a type of material whose properties can be changed with an external stimuli, represent a promising direction to expand upon existing robotic control and actuation methods, particularly in the sub-fields of soft...
Robotic Bipedal locomotion holds the potential for efficient, robust traversal of difficult terrain. The difficulty lies in the dynamics of locomotion which complicate control and motion planning. Bipedal locomotion dynamics are dimensionally large problems, extremely nonlinear, and operate on the limits of actuator capabilities, which limit the performance of generic...
As technologies like 3D printing increase in prevalence and capabilities, having a robot hand specifically designed for a given manipulation task also becomes more feasible. Leading to the question of how to design a robot hand for a specific manipulation task. To answer this question, I propose we need three...
We present a method for decentralized, multi-robot exploration in adverse environments where communication is minimal. A key conceptual feature of our method is enabling implicit coordination between robots by training a Convolutional Neural Network (CNN) as a heuristic for planning using Monte Carlo Tree Search (MCTS). Our method consists of...
As bipedal robots move ever closer to being integrated into all manner of real world envi-ronments there is a necessity to push their dynamic capabilities to meet or exceed those of humans and animals. Advancements must be made to address ordinary challenges that arise everyday in the same environments that...