Robotics and Intelligent Machines
Most robotic grippers are either powerful or gentle, rarely both. Traditional rigid designs lack adaptability and often damage fragile objects through excessive force, limiting their usage i…
Robotics and Intelligent Machines
Autonomous robots rely on Simultaneous Localization and Mapping (SLAM) to build maps and estimate their position within unknown environments. While many modern robotic systems achieve high r…
Robotics and Intelligent Machines
Aviation emergencies caused by pilot incapacitation remain a critical safety risk, particularly in regions with limited access to advanced automated systems. This project developed H.A.L.O.,…
Robotics and Intelligent Machines
What makes robots seem robotic? Traditional robots are stiff, making them precise and stable, but not agile; they have difficulty negotiating the variability of natural environments. In cont…
Robotics and Intelligent Machines
Autism Spectrum Disorder, or ASD, is a neurodevelopmental disorder that can cause significant behavioral and social challenges. The prevalence of ASD has risen over the past two decades, ref…
Robotics and Intelligent Machines
Large language models (LLMs) achieve remarkable performance on complex reasoning tasks, yet they fail unpredictably and with high confidence on seemingly simple problems, posing a critical c…
Robotics and Intelligent Machines
Kenyan Sign Language (KSL) remains absent from AI research despite serving 600,000 Deaf Kenyans. Existing recognition systems, including those for ASL and BSL, fail under real-world conditio…
Robotics and Intelligent Machines
In fields such as exploration or inspection in hazardous environments, the ability to navigate terrain safely is crucial. This is often done through robotics; however, traditional systems (r…
Robotics and Intelligent Machines
Large language models (LLMs) are increasingly trusted in domains such as education, research, and decision making. Despite their widespread adoption, fundamental questions remain about align…
Robotics and Intelligent Machines
A significant number of bridges in the United States are susceptible to failure, and one of the main factors that causes failure is overload. Severe consequences can result from bridge failu…
Robotics and Intelligent Machines
Post-hoc domain generalization (PDG) methods aim to generalize machine learning models to unseen target domains using only source-domain information leveraged after training. Unlike train-ti…
Robotics and Intelligent Machines
Between 2020 and 2024, fatal occupational falls averaged 782 annually, peaking at 865 in 2022, according to Bureau of Labor Statistics data. Many occurred in high risk environments like skys…
Robotics and Intelligent Machines
Online platforms such as social media and video games are designed to stimulate reward mechanisms in the brain, which can lead to excessive use and reduced attention control. This project in…
Robotics and Intelligent Machines
Globally, tens of millions of people suffer from lower body impairments, including spinal cord injuries, cerebral palsy, stroke, and muscular dystrophies, leading to loss of independent mobi…
Robotics and Intelligent Machines
This study proposes Purpose And Context Activate Knowledge Efficiently(PANCAKE), a novel structured Chain-of-Thought methodology for enhancing geometric problem-solving in Vision-Language Mo…
Robotics and Intelligent Machines
Using numerous task-specialized large language models in deployment is often constrained by the storage footprint of fine-tuned checkpoints and significant cold-start latency during loading.…
Robotics and Intelligent Machines
The need for efficient, actuated robotic systems has increased with modern integration, disaster relief scenarios, and stealth tech. The Perching Hybrid Omni-environment Navigation Integrate…
Robotics and Intelligent Machines
Landslides are a kind of major natural disaster that causes huge economic and life losses globally. And visual detection using satellite imagery is critical for disaster response. Landform,…
Robotics and Intelligent Machines
Trap-Neuter-Return (TNR) is a widely used strategy for managing feral cat populations. However, a major challenge in TNR programs is redundant capture, in which already neutered cats (even w…
Robotics and Intelligent Machines
Autonomous drone research has become increasingly important, yet there are many burdens which make its access limited. Especially for autonomous drone racing, high-end motion-capture systems…
Robotics and Intelligent Machines
Upper-limb prosthetic abandonment remains at 44%, a clinical failure rooted in the intractable complexity of human motor control: the approximately 20 degrees-of-freedom (DoF) of the hand cr…
Robotics and Intelligent Machines
Globally, 43 million blind and 295 million visually impaired individuals lack independent indoor mobility. Existing aids are either reactive (white canes), expensive (guide dogs), or ineffec…
Robotics and Intelligent Machines
Automated analysis of medical images offers transformative potential for clinical diagnostics, yet two persistent obstacles limit practical adoption: the high cost of expert annotation and t…
Robotics and Intelligent Machines
With the rise of Artificial Intelligence tools, society has seen a significant increase in their applications in high-stakes, sensitive industries. However, these tools often operate with op…
Robotics and Intelligent Machines
Global waste is increasing every year, and despite awareness campaigns, recycling rates remain low. Current systems rely heavily on human participation, which is often inconsistent and error…
Robotics and Intelligent Machines
A notable problem that needs to be solved is even to this day is searching for survivors in collapsed buildings. Building collapses often lead to unstable piles of rubble that could collapse…
Robotics and Intelligent Machines
Language models are increasingly explored for classifying online messages during disasters to route resources, however interpretability is demanded for opaque models. No prior work has chara…
Robotics and Intelligent Machines
Urban parking shortages impose significant economic and environmental costs, with drivers spending excessive time searching for spaces and generating substantial emissions. Shared parking, w…
Robotics and Intelligent Machines
This study aims to build an on-device edge computing system that leverages Vision-Language Models (VLMs) in place of the conventionally used Convolutional Neural Networks (CNNs) for real-tim…
Robotics and Intelligent Machines
As computer vision systems become increasingly integrated into everyday life, it is imperative to consider the deficiencies and biases present in our computer algorithms. One such bias is sp…