Unmanned aerial vehicle (UAV) technology has grown out of traditional research and military applications and has captivated the commercial and consumer markets, showing the ability to perform a spectrum of autonomous functions. This technology has the capability of saving lives in search and rescue, fighting wildfires in environmental monitoring, and...
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...
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...
Deep pressure therapy (DPT) is a method of anxiety relief that uses pressure sensations to lower the stress response produced in the brain, and functions in a manner similar to a hug. Heavily weighted blankets and weighted vests are most commonly used to apply DPT, though recent work has shown...
There are at least fifteen types of upper extremity tendon transfer procedures for combined peripheral nerve injuries that involve re-routing a single donor muscle to multiple recipient tendons. As a result, force and movement across finger joints become coupled, resulting in limited grasping abilities. Quantification and modeling of the donor...
Artificial Intelligence has gained resurgence in popularity through machine learning methods. This thesis investigates the current use of AI, the impact it will have on the economy and the ethical considerations for developing this technology. In the coming decade AI could increase global economic output over $10 Trillion. AI will...
The Jetson Artificial Intelligence Tool chain (JAI-TC) is a set of packages, APIs and libraries for Artificial Intelligence applications to be deployed on the NVidia SOC, Jetson TX2. JAI-TC automates the installation of these items allowing for a wider set of users to leverage these technologies. Prior to this, the...
Reinforcement learning has emerged as a popular tool for solving control tasks, with multiple works focusing on the complex and dynamic task of locomotion. However, the naive application of reinforcement learning to this problem often produces maladaptive policies that exploit the model or reward function. This results in behavior that...
Deep learning has recently revolutionized robot perception in many canonical robotic applications, such as autonomous driving. However, a similar transformation has yet to occur in more harsh environments including underwater and underground. This is due in part to the difficulty in deploying robots in these environments, which lack large real...