Robust Intelligence Cluster (RI)
See program guidelines for contact information.
This cluster, Robust Intelligence (RI), encompasses computational understanding and modeling of the many human and animal capabilities that demonstrate intelligence and adaptability in unstructured and uncertain environments.
RI topics include, but are not limited to:
- Problem solving architectures that integrate reasoning, motor, perceptual, and language capabilities and that can learn from experience.
- Hybrid architectures that integrate or combine different methods, such as deductive, probabilistic, analogical, case-based, symbolic, or sub-symbolic reasoning.
- Computational models of human cognition, perception, and communication for commonsense or specialized domains and tasks, including acquisition and representation of ingredient knowledge.
- Novel approaches to long-standing problems in computer vision, for example concerning the recognition and modeling of contours, shapes, regions, objects, people, scenes, events, activities, in 2D images, 3D images or video.
- Vision systems that capture biological components and capabilities.
- Synergistic and collaborative research of innovative and emerging technologies to improve the intelligence, mobility, autonomy, manipulability, adaptability, and interactivity of robotic systems operating in unstructured and uncertain environments.
- Research on intelligent and assistive robotics, neuro-robotics, multi-robot coordination and cooperation, and micro- and nano-robotics with novel approaches to sensing, perception, cognition, actuation, autonomous manipulation, learning and adaptation, haptics, and multi-modal human-robot interaction.
- Computational approaches and architectures for analyzing, understanding, generating and summarizing speech, text and other communicative forms (e.g., gesture, haptic); interaction of communicative forms; and dialogue, conversation and other less formal genres (e.g., meeting minutes).
- Computational models of meaning, intent, and realization at various levels of language representation with a particular attention to semantics and pragmatics; cognitively and neuro-linguistically informed approaches for model evaluation.
- Novel approaches to longstanding language processing problems such as speaker and language recognition, machine translation, evaluation metrics, and multilingual man-machine communication, including intelligent information delivery.
- Computational approaches to language processing for underrepresented groups such as minority language groups and aging and disabled population groups.
- Functional modeling, theory, and analysis of the computational, representational, and coding strategies of neural systems.
- Neurally-grounded computational approaches to computer vision, robotics, communication, and reasoning, and systems that combine them and embody empirically derived neural strategies.
Robust Intelligence (RI) subsumes topics covered by these areas previously supported by the IIS Division: Artificial Intelligence and Cognitive Systems; Computational Neuroscience; Computer Vision; Human Language and Communication; and Robotics.
Funding Opportunities for the Robust Intelligence Cluster: