Make key innovations in data quality assurance methodology for robotics anomaly detection problems based on AI-model-enhanced multimodal data fusion machine learning
Ended Cooperative Agreement Awarded Last action
- Award ID
- 70NANB24H115
- Recipient
-
Virginia Polytechnic Institute & State University UEI QDE5UHE5XD16
- Awarding agency
-
National Institute of Standards and Technology
Department of Commerce
- Obligated
- $118,000
Award facts
- Assistance listing
- 11.609 Measurement and Engineering Research and Standards
- Completion date
- Originally
- Place of performance
- Blacksburg, VA 24061, USA
Award details come from USAspending.gov.
Description
- Purpose
- The purpose of this grant is to make key innovations in data quality assurance methodology for robotics anomaly detection problems based on AI-model-enhanced multimodal data fusion machine learning. The research will significantly lower the barriers to effective dataset preparation for AI training and online updating for robotics AI methods.
- Activities
- The proposal will perform the following three activities:1) quality-assured multimodal data preparation by unified diffusion models ? They will investigate a data sampling and synthesis method to collect both NORMAL and anomalous data for anomaly detection. IT addresses the data measurement challenge by investigating the impact and the improvements of data quality on anomaly detection performance metrics as well as reducing ineffective but redundant robotics measurement efforts. Particularly, limited anomaly data are collected during the regular operation phases, which cause severe class imbalance. 2) anomaly detection via sampling-efficient inverse reinforcement learning ? They will create an effective anomaly detection method, adaptive to the specific robotic and operations scenarios. The method aims to learn the underlying objective functions and intentions that characterize the robotic system behavior, thus facilitating learning from both optimal (NORMAL) and sub-optimal (ABNORMAL) operational conditions.3) validation via real datasets and simulation: they will undertake a rigorous validation process for the proposed anomaly detection methods using real datasets and simulation to show the effectiveness of the proposed data quality assurance methods.
- Expected outcomes
- The deployment of the proposed methodologies will reduce the workload of data scientists and automation engineers, alleviating their shortage problem nationwide. The developed methodology can be applied in various manufacturing industries deploying AI methods for robotics operations.
- Intended beneficiaries
- Robot end users, robot vendors, robot systems integrators, manufacturers, U.S. Industrysubrecipient activities: the recipient does not intend to subaward funds.
Transactions
| Action | Obligated | Date |
|---|---|---|
| Amendment | $0 | |
| Original award | $118,000 |
Quick answers
Who received award 70NANB24H115?
70NANB24H115 was awarded to Virginia Polytechnic Institute & State University by National Institute of Standards and Technology (Department of Commerce) on October 1, 2024.
How much is award 70NANB24H115 worth?
$118,000 has been obligated on 70NANB24H115.
On GovTribe
See this award's full record
- Every transaction and subaward
- The recipient's other awards and teaming partners
- Similar grant awards
- Ask GovTribe AI about this award