Deepen understanding of attention control as a key determinant of human and machine performance.
-
Deepen understanding of the neuro-cognitive mechanisms of attention control, task engagement and their role in learning.
-
Use underlying theory to develop new algorithms to enable powerful new approaches to enhance warfighter proficiency during training and operations and advance the state of the art (SOA) in artificial intelligence (AI).
Research Concentration Areas
- Attention and Learning
- Attention and the dynamics of its deployment through learning are fundamental to human performance. Current SOA AI systems lack adequate mechanisms of attentional processing, a shortfall undermining the performance of AI relative to biological systems in complex tasks. Advances in our understanding of attentional dynamics can provide the foundation for novel techniques to improve the information-processing both of human operators and of AI systems.
- Research Focus:
- Develop and validate a comprehensive neurocognitive model of the mechanisms of attention and its control
- Determine where and how in the brain the mechanisms of attention exert their modulatory impacts
- Develop AI algorithms and architectures that implement the functionality of the neuro-cognitive mechanisms of attention and it’s control
- Develop measures that capture the variability of attention control across individuals
- Create and validate an efficient set of training techniques to enhance cognitive control capacity
- Assess and mitigate the impacts of stress and fatigue on attention control and understand why these differ among individuals
- Adaptive Training
- Exploit a deep understanding of attentional dynamics to create adaptive training (AT) design principles that reinforce its capacity to engage individuals and teams and support attention management (where, when, what to focus on) during skill acquisition.
- Research Focus:
- Exploit understanding of attention control to develop and evaluate alternative approaches for optimizing learner engagement and attention management in AT
- Extend optimized AT techniques for use in training of interactive teams
- Exploit these optimized techniques to support experiential (e.g., scenario based) VC and LVC training
- Create and comparatively evaluate alternative AI algorithms for automatically adapting training content to meet learner needs
- Devise and assess alternative approaches for the adaptive training of attention management (where, when to attend) during skill acquisition
How to Submit
For detailed application and submission information for this research topic, please refer to our broad agency announcement (BAA) No. N0001425SB001.
Contracts: All white papers and full proposals for contracts must be submitted through FedConnect; instructions are included in the BAA.
Grants: All white papers for grants must be submitted through FedConnect, and full proposals for grants must be submitted through grants.gov; instructions are included in the BAA.