Autonomous robotic agents are on their way to becoming in-home personal assistants, construction assistants, and warehouse workers. The degree of autonomy of such systems is reflected by the manner in which we specify goals to them; the abstraction of low-level commands to high-level goals goes hand-in-hand with increased autonomy. In...
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...
To facilitate the design of Natural and Nature-Based Features (NNBF) for flood protection, this thesis expands an existing engineering design methodology to NNBF systems. The existing approach is a Level III reliability method for the performance-based design of traditional coastal engineering systems. The expanded methodology incorporates uncertainties inherent to both...
Various natural language processing (NLP) tasks necessitate deep models that are fast, efficient, and small based on their ultimate application at the edge or elsewhere. While significant investigation has furthered the efficiency and reduced the size of these models, reducing their downstream latency without significant trade-offs remains a difficult task....
Simultaneous speech translation (SimulST) is widely useful in many cross-lingual communication scenarios, including multinational conferences and international traveling. Since text-based simultaneous machine translation (SimulMT) has achieved great success in recent years. The conventional cascaded approach for SimulST uses a pipeline of streaming ASR followed by simultaneous MT but suffers from...
Within the sagebrush steppe ecosystem, invasive annual grasses are of growing management concern as they outcompete native vegetation, change the fundamental nutrient cycling processes, decrease biodiversity, and increase frequency of wildfires. The most widely used and effective management tool to decrease invasive annual grass abundance, is the use of pre-emergent...