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...
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...
The purpose of this dissertation was to estimate the extent to which group-level synchrony predicts specific group outcomes. Synchrony is broadly defined as the coordination of biological and behavioral processes during social contact (Feldman, 2017). In this dissertation, biological coordination is defined as, “the spontaneous synchronization of physiological signals (e.g.,...
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...
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...
Human-robot teams are invaluable for mapping unknown environments, exploring difficult-to-reach areas, and manipulating inaccessible equipment. However, guiding autonomous robots requires dealing with these dynamic domains while synthesizing a significant amount of data and balancing competing objectives. Current mission planning methods often involve manually specifying low-level parameters of the mission, such...
This paper discusses opportunities for developments in spatial clustering methods to help leverage broad scale community science data for building species distribution models (SDMs). SDMs are critical tools that inform the science and policy needed to mitigate the impacts of climate change on biodiversity. Community science data span spatial and...
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...
Habitat restoration projects are vital for recovering ecosystems, but they can be expensive. One way to help justify the price tag is to value the economic benefits provided by the restored habitat. The issue is that many ecosystem services and the flow of benefits they produce are complex, requiring careful...