Special Notice - A-- The ADL Initiative is to develop a Personal Assistant for Learning (PAL) for effective, personalized learning content and/or job performance aids that can be accessed from multiple devices/platforms.
Notice Type: Special Notice
Posted Date: 03-SEP-14
Office Address: Department of the Army; Army Contracting Command; ACC-APG - Natick (SPS); ATTN: AMSRD-ACC-N, Natick Contracting Division (R and BaseOPS), Building 1, Kansas Street, Natick, MA 01760-5011
Subject: A-- The ADL Initiative is to develop a Personal Assistant for Learning (PAL) for effective, personalized learning content and/or job performance aids that can be accessed from multiple devices/platforms.
Classification Code: A - Research & Development
Contact: Constance Kim, 4073845516 mailto:firstname.lastname@example.org [ACC-APG - Natick (SPS)]
Description: Department of the Army
Army Contracting Command
ACC-APG - Natick (SPS)
The ADL Initiative has the mission to develop and advance the state of the art in education and training through the use of technology and innovative learning methodologies which highly leverage artificial intelligence, networking, data warehousing and recall technologies for the Department of Defense and across the Federal Government. Projects funded under this BAA will include research related to the ADL mission resulting in prototypes or prototype modules with potential for transition to the Department of Defense community, including the Department of Defense Education Activity. Projects of most interest will be in those areas that explore and develop novel applications of new and emerging educational and training technologies, explore new methods of integrating sound instructional principles with the emerging learning technologies, and maintain a learner-centric orientation. Work should avoid use of proprietary software whenever possible, and should expose application programming interfaces (APIs) to allow access to data and functionality. Web services should be loosely coupled to enable integration in a PAL service-oriented architecture. RESEARCH TOPICS We are interested in research that will support the short to mid-term vision, the long term vision, and methods to evolve the latter from the former. We are also interested in the potential socio-cultural impact and challenges of the PAL, and learner-centric approaches, in general. At this time, ADL is especially interested in research addressing one or more of the following areas: General Research Areas of Interest 1. Device Attributes Research to invigorate content authoring that will be delivered on a single platform or multiple devices and platforms. Platform agnosticism will be a key attribute of the PAL. Research into the ergonomic integration of less-invasive, human-computer devices within a training environment. This includes: customized content to the individual (user learning profile, progress and assessment, etc.); a transparent user interface that captures eye motion, body position, gestures, and other important quote mark pointing quote mark data; twice the required processing and memory; audio and visual cueing (both as an input and an output), ubiquitous access to the World Wide Web and local networking capabilities; and battery, recharging or power operations via wire or wireless energy transfers. The PAL shall be wearable with minimal interference or nuisance to the user. Mixed reality environments as the desired training end state must be part of the overall device construction considerations. New projects that investigate integrations/mashups of devices/platforms that would more effectively support social learning distributed across time, space, and media. 2. PAL Architecture Tracking experiences associated with learning or training performances across different devices and formats; adapting to the learning styles of the individual and providing customized content as appropriate. This includes progression and assessment of user learning. Discovery and retrieval models that can be used to broker just-in-time content. Social media architecture integration for content sharing and reuse, peer-to-peer communication, self-guided learning, social data formats, communication protocols and other multi-learner e-learning technologies. Scalable system architecture on par with modern massively multiplayer on-line gaming progression. Systems architecture must achieve interoperability through an automated, transparent, machine-to-machine interface. 3. Knowledge and Information Innovative learner profile management strategies and technologies for both the capture and filtered sharing of individual and team competencies as well as other pertinent data about learners. Innovative digital instruction, i.e. simulations and representations that explain themselves to learners and systems that are able to act as mentors/mentees. Competency Alignment methods to allow diverse learning applications to share information about content learning objectives and student mastery. Data mining, warehousing and recall; Assist with educational and training data mining, identifying data that is relevant for future use and highlight adaptive content and systems. PAL shall also assist the user with warehousing and recall of learned content. 4. Artificial Intelligence Intelligent tutoring and context-aware distributed systems that provide an adaptive, personalized experience for 24/7 training or learning opportunities and on-the-job performance aiding. Persistent, open independent Learner Models with reasoning capability that incorporate new methods of machine learning, common sense reasoning, cognitive modeling, and/or artificial intelligence. Intelligent systems designed to increase both cognitive adaptability and emotional resiliency. Domain independent intelligent system design. In other words, the intelligent system is not locked into one domain, but is applicable and exportable to multiple domains. Platform independent interfaces that transition from written to spoken interface; accurate speech recognition and adaptation to individual speech patterns; ability to recognize stress signals in learner speech patterns and adapt responses appropriately. This includes methodologies and techniques for the PAL to assess on-the-spot the learner's comprehensive and achievement of the desired learning Objective. Ability to retain profiles for learners and groups with a complete understanding of individual history and knowledge of what the individual/group progress goals are. 5.Virtual Environments Investigate tools and techniques to improve the user's ability to easily generate, reuse, and share 3D content in a training environment. Interoperable 3D content includes 3D models, textures, animations, scripts, and other supporting assets. Research showing the applicability of virtual environments to the next generation learner, including how the PAL will interact within virtual environments, and how live, virtual, and constructive training can be integrated within the next generation learning environment. Technologies to allow for the sharing and reuse of user-generated training in and across multiple virtual environments. Research into how virtual environments can better train an adaptive force. Progress toward long term goal of integrating virtual worlds, PAL and AI with physical world into a mixed reality suite that delivers a superior learning experience. 6. Next Generation Learner The innovative methodologies and approaches to using Social Networking for solving problems in collaborative, disparate environments in a manner that improves learning outcomes. Research to demonstrate the application of the spacing effect using current mobile technologies to reinforce learning and improve long-term retention. Design principles for instruction in distributed environments that promote learner adaptability; develop instruction that inculcates adaptivity in responses of the learner. Design principles for instruction in distributed environment that guards against regression of innate human capabilities in the absence of AI or computerized assistance. Innovative and effective assessment-based training research wherein learners engage in self-directed learning and are able to test out of training or education by successfully completing validated assessments outside of structured and formal learning instances.