CISE - IIS
ROBUST INTELLIGENCE (RI)
The RI program encompasses all aspects of computational understanding and modeling of intelligence in
complex, realistic contexts, advancing and integrating across the research traditions of artificial
intelligence, computer vision, human language research, robotics, machine learning, computational
neuroscience, cognitive science, several areas of computer graphics, and related areas. In contrast to
systems that use limited-reasoning strategies or address problems in narrow contexts, robust intelligence
may be characterized by a system's flexibility, resourcefulness, use of a variety of modeling or reasoning
approaches, and use of real-world data in real time, demonstrating a level of intelligence and
adaptability seen in humans and animals.
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
- Novel advances in and integration across areas of artificial intelligence, such as machine
learning, planning and problem solving, knowledge representation, and multi-agent
- Novel approaches to longstanding 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.
- Novel advances in computer graphics and computational imaging that contribute to robust
generation and causal modeling of images and video.
- Synergistic and collaborative research on 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, healthcare robotics, social robotics, micro- and
nano-robotics, marine robotics, mobile robotics, neuro-robotics, rescue robotics, space robotics,
humanoid robotics, unmanned aerial vehicles (UAVs), and multi-robot coordination and cooperation with
novel approaches to sensing, perception, cognition, actuation, autonomous manipulation, learning
and adaptation, haptics, and multi-modal human-robot interaction.
- Fundamental research on innovative and emerging robotic technologies for monitoring and
surveillance of our environment, and to improve quality of life.
- 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
- 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 neurons and neural systems.
- Neurally-grounded computational approaches to computer vision, robotics, communication, and
reasoning, and systems that combine them and embody empirically derived neural strategies.
RI subsumes topics such as Artificial Intelligence and Cognitive Systems, Computational Neuroscience,
Computer Vision, Human Language and Communication, and Robotics.