Search Results - Software

23 Results

Sort By:

Sequence-to-Sequence Language Grounding of Non-Markovian Task Specifications

Overview There are existing ways to translate a person’s instructions for a robot into a series of logical functions that the machine can execute to achieve the goal, such as Linear Temporal Logic (LTL). Such approaches are powerful, but they are also technical and complex; a non-expert could not be expected to learn this language to communicate...

Published: 6/6/2024 | Inventor(s): Stefanie Tellex

Keywords(s):

Category(s): Robotics, Software

Probabilistic Object Models for Robust, Repeatable Pick-and-Place

Overview Picking up an object is one of the simplest tasks a person can perform. For a robot, however, such a task requires a suite of surprisingly complex abilities. The machine must have a capable grasping hand capable of exerting just the right amount of force—enough to avoid dropping the object, but not so much as to crush it. The robot must...

Published: 6/6/2024 | Inventor(s): Stefanie Tellex, John Oberlin

Keywords(s):

Category(s): Robotics, Software

Multi-Object Search Using Object-Oriented POMDPs

Overview The robots of the future may be called upon to search for a variety of objects and to do so in unfamiliar territory. An established method called Partially Observable Markov Decision Processes (POMDPs) allows a robot to make decisions in the correct order even faced with uncertain conditions. However, these POMDPs struggle to keep pace...

Published: 6/6/2024 | Inventor(s): Stefanie Tellex, Arthur Richard Wandzel

Keywords(s):

Category(s): Robotics, Software, Natural Language Processing

Accurately and Efficiently Interpreting Human-Robot Instructions of Varying Granularities

Overview Robots that work alongside humans must be able to understand directions and instructions in natural language. But not all instructions are created equal. For example, a human operating a forklift intuitively understands the difference between what researchers would call a high-level action, like “grab a pallet,” and a low-level...

Published: 6/6/2024 | Inventor(s): Stefanie Tellex, Lawson Wong, Nakul Gopalan, Dilip Arumugam, Siddharth Karamcheti

Keywords(s):

Category(s): Robotics, Natural Language Processing, Software

Context-Aware Self-Calibration for Autonomous Control of Assistive Devices

Overview Existing assistive devices for people with severe motor disabilities rely heavily on residual motor function. Recent brain-computer interfaces (BCIs), which decode neural activity directly from the brain, provide disabled persons with limited ability to autonomously control assistive devices. We have invented a neural interface system that...

Published: 5/21/2023 | Inventor(s): Beata Jarosiewicz, Nicolas Masse, Daniel Bacher, Anish Sarma

Keywords(s):

Category(s): Software, Neurotechnology

iBCI System to Control Multiple Devices

Overview Until now, brain computer interface (BCI) systems have allowed people with paralysis to control only a single device, often under the guidance of a caretaker or secondary operator. Our novel BCI system enables users to control multiple devices, switching among them under their own volition. Market Opportunity Numerous intracortical...

Published: 12/21/2022 | Inventor(s): Leigh Hochberg, Tyler Singer-Clark, Ronnie Gross, Anastasia Kapitonava, John Simeral, Thomas Hosman

Keywords(s):

Category(s): Software, Neurotechnology

MyCOVIDRisk Mobile App—A Novel Risk Estimation and Mitigation Tool

Overview Launched in Oct. 2020, our publicly available MyCOVIDRisk mobile app has been accessed more than 1.3 million times, demonstrating high acceptance of a free and simple web-based mobile app to estimate and mitigate risk of SARS-CoV-19 transmission. Market Opportunity During the COVID-19 pandemic, the rapidly changing science and public health...

Published: 11/1/2022 | Inventor(s): Megan Ranney

Keywords(s):

Category(s): Software

SOCKS (Statistical Outlier Curation Kernel Software): A Modern, Efficient Tool for Outlier Detection and Curation

Overview Real-world signal acquisition through sensors is at the heart of the modern digital world, yet almost every signal acquisition system is contaminated with noise and outliers. Our data “sanitizer” tool provides a way to obtain uncorrupted observations. Market Opportunity It is increasingly evident that clarity of digital information...

Published: 11/1/2022 | Inventor(s): Prasanta Pal, Judson Brewer

Keywords(s):

Category(s): Research Tools, Software

A novel technology-augmented intervention to prevent peer violence and depressive symptoms among at-risk emergency department adolescents iDove2 Intervention Protocol (Adolescent)

Digital Health Intervention to Improve Well-Being and Reduce Depression Among Adolescents Seen in Emergency Department Overview Depressive symptoms and related problems are increasingly common among American youth. Yet no one has developed a mobile app that provides accessible, effective prevention interventions that teens will actually use....

Published: 6/2/2022 | Inventor(s): Megan Ranney

Keywords(s):

Category(s): Software

Intervention to Prevent Adolescent Cyber-victimization through App-messaging (IMPACT)

Digital Health Intervention to Improve Well-being and Reduce Cyberbullying Among Adolescents Overview Cyberbullying and depressive symptoms are increasingly common, interrelated problems among American youth; COVID has only heightened the reliance of youth on social media, as well as their mental distress. Our novel two-part app-based cybervictimization...

Published: 6/2/2022 | Inventor(s): Megan Ranney

Keywords(s):

Category(s): Software

1 2 3