AAAI 2021 Symposia

March 22–24, 2021

Sponsored by the Association for the Advancement of Artificial Intelligence
In cooperation with the Stanford University Computer Science Department

Call for Participation

Important Deadlines

• November 1, 2020: Submissions due to organizers (unless otherwise noted in individual descriptions)
• December 3, 2020: Notifications of acceptance sent by organizers

AAAI Spring Symposium Submission Site

Most organizers have elected to use the AAAI Spring Symposium EasyChair site for receipt of submissions. If specified in the individual symposium description, please submit your work via the AAAI Spring Symposium EasyChair site. Please be sure to select the appropriate symposium when submitting your work.

The titles of the nine symposia are as follows:

• Artificial Intelligence for K-12 Education
• Artificial Intelligence for Synthetic Biology
• Challenges and Opportunities for Multi-Agent Reinforcement Learning*
• Combining Machine Learning and Knowledge Engineering*
• Combining Machine Learning with Physical Sciences
• Implementing AI Ethics
• Leveraging Systems Engineering to Realize Synergistic AI/ML Capabilities
• Machine Learning for Mobile Robot Navigation in the Wild
• Survival Prediction: Algorithms, Challenges and Applications

*Combined Spring 2021 and Spring 2020 meetings.

Artificial Intelligence for K-12 Education

Artificial intelligence (AI) is now achieving great successes in various real-world applications and made our life more convenient and safe. AI is now shaping the way businesses, governments, and educational institutions do things and is making its way into K-12 classrooms, schools and districts across many countries.

In fact, the increasingly digitalized education tools and the popularity of online learning have produced an unprecedented amount of data that provides us with invaluable opportunities for applying AI in K-12 education. Recent years have witnessed growing efforts from AI research community devoted to advancing our education and promising results have been obtained in solving various critical problems in K-12 education. For examples, AI tools are built to ease the workload for teachers. Instead of grading each piece of work individually, which can take up a bulk of extra time, intelligent scoring tools allow teachers the ability to have their students work automatically graded. What’s more, various AI based models are trained on massive student behavioral and exercise data to have the ability to take note of a student’s strengths and weaknesses, identifying where they may be struggling. These models can also generate instant feedback to instructors and help them to improve their teaching effectiveness.

Despite gratifying achievements have demonstrated the great potential and bright development prospect of introducing AI in K-12 education, developing and applying AI technologies to educational practice is fraught with its unique challenges, including, but not limited to, extreme data sparsity, lack of labeled data, and privacy issues. Hence, this symposium will focus on introducing research progress on applying AI to K-12 education and discussing recent advances of handling challenges encountered in AI educational practice. This symposium builds upon our continued efforts (AAAI-20 workshop, IJCAI-20 tutorial, KDD-20 tutorial) in bringing the AI community members together for the above-mentioned themes. This symposium will bring together AI researchers, learning scientists, educators and policymakers to exchange problems and solutions and build possible collaborations in the future.

Topics

We encourage keynote speeches on a broad range of AI domains for K-12 education. Topics of interest include (in no particular order) but are not limited to following topics:

• Emerging technologies in K-12 education
• Evaluation of K-12 education technologies
• Immersive learning and multimedia applications
• Implications of big data in K-12 education
• Self-adaptive learning
• Individual and personalized K-12 education
• Intelligent learning systems
• Intelligent tutoring and monitoring systems
• Automatic assessment in K-12 education
• Automated grading of assignments
• Automated feedback and recommendations
• Big data analytics for K-12 education
• Analysis of communities of learning
• Computer-aided assessment
• Course development techniques
• Data analytics and big data in K-12 education
• Mining and web mining in K-12 education
• Learning tools experiences and cases of study
• Social media in K-12 education
• Smart K-12 education
• Digital libraries for learning
• K-12 education analytic approaches, methods, and tools
• Knowledge management for learning
• Learning analytics and K-12 educational data mining
• Learning technology for lifelong learning
• Tracking learning activities
• Uses of multimedia for K-12 education
• Wearable computing technology in e-learning
• Smart classroom
• Dropout prediction
• Knowledge tracing

Format

The symposium will include invited talks, presentations of accepted papers, group and panels. Invited speakers and presentations will be announced after the submissions. More information will appear on the supplementary symposium website.

Submissions

The symposium solicits paper submissions from participants (2-6 pages). Abstracts of the following flavors will be sought: (1) research ideas, (2) case studies (or deployed projects), (3) review papers, (4) best practice papers, and (5) lessons learned. The format is the standard double-column AAAI Proceedings Style. We will encourage submissions of works-in-progress and extended abstracts, in addition to full length papers. All submissions will be peer-reviewed. Some will be selected for spotlight talks, and some for the poster session.

Organizing Committee

Zitao Liu (main contact, liuzitao@100tal.com) (TAL Education Group), Jiliang Tang (Michigan State University), Yi Chang (Jilin University) , Xiangen Hu (University of Memphis), Diane Litman (University of Pittsburgh)

For More Information

For more information about the symposium, please see the supplementary symposium website.

Artificial Intelligence for Synthetic Biology

With the success of the AI for Synthetic Biology at prior AAAI Symposia Series, we aim to capitalize on the former discourse and bring together researchers from AI and synthetic biology communities to cultivate a multidisciplinary research community that can benefit both areas of expertise. For AI researchers, it will be a never before explored novel domain with unique challenges, whereas for the synthetic biology community it will be an opportunity to break the complexity barrier it is facing. Our primary goal remains the same — to begin to connect and build mutually beneficial collaborations between the AI and the synthetic biology communities.

Synthetic biology is the systematic design and engineering of biological systems. Synthetic biology holds the potential for revolutionary advances in medicine, environmental remediation, and many more. Many times the design of synthetic organisms occurs at a low level (for example, DNA level) in a manual process that becomes unmanageable as the size and complexity of a design grows. This is analogous to writing a computer program in assembly language, which also becomes difficult quickly as the size of the program grows. Many of the emerging techniques and tools in synthetic biology produce large amounts of data. Understanding and processing this data provides more avenues for AI techniques to make a big impact.

Topics

Topics of interest include (but not limited to) the following:

• Research that did or could have had an impact on COVID-19
• Machine-assisted gene circuit design
• Flexible protocol and automation
• Assay interpretation and modeling
• Representation and exchange of designs
• Representation and exchange of protocols
• Data driven modeling of biological systems

Format

The symposium will include brief introductions to each domain to ensure it is accessible to attendees with both backgrounds; focus groups looking at some of the open problems and challenges in the intersection of AI and Synthetic Biology; contributed talks; and panel discussions. We plan to highlight research in the AI/synthetic biology intersection that did or could have had an impact on COVID-19.

We plan to continue the working group format that we used in the 2019 symposia, as well as focus groups looking at some of the open problems and challenges in the intersection of AI and synthetic biology. Ideally there will be contributed talks, and panel discussions (potentially including government agencies).

Submissions

Details pending.

Organizing Committee

Aaron Adler (BBN Technologies), Rajmonda Caceres (MIT Lincoln Laboratory), Mohammed Ali Eslami (Netrias, LLC), Fusun Yaman (BBN Technologies)

For More Information

For more information about the symposium, please see the supplementary symposium website.

Challenges and Opportunities for Multi-Agent Reinforcement Learning

We live in a multiagent world and to be successful in that world intelligent agents will need to learn to take into account the agency of others. They will need to compete in marketplaces, cooperate in teams, communicate with others, coordinate their plans, and negotiate outcomes. Examples include self-driving cars interacting in traffic, personal assistants acting on behalf of humans and negotiating with other agents, swarms of unmanned aerial vehicles, financial trading systems, robotic teams, and household robots.

Topics

There has been a lot of great work on multiagent reinforcement learning in the past decade, but significant challenges remain, including the following:

• The difficulty of learning an optimal model or policy from a partial signal
• Learning to cooperate/compete in nonstationary environments with distributed, simultaneously learning agents
• The interplay between abstraction and influence of other agents
• The exploration versus exploitation dilemma
• The scalability and effectiveness of learning algorithms
• Avoiding social dilemmas
• Learning emergent communication.

Format

We aim to organize an active symposium, with many interactive (brainstorm/breakout) sessions. We are hopeful that this will form the basis for ongoing collaborations on these challenges between the attendants and we aim for several position papers as concrete outcomes.

Submissions

Authors can submit papers of 1-4 pages that will be reviewed by the organizing committee. We are looking for position papers that present a challenge or opportunity for multiagent reinforcement learning research, which should be on a topic the authors not only wish to interact on but also work on with other participants during the symposium. We also welcome (preliminary) research papers that describe new perspectives to dealing with multiagent reinforcement learning challenges, but we are not looking for summaries of current research — papers should clearly state some limitation(s) of current methods and potential ways these could be overcome. Submissions will be handled through the AAAI Spring Symposium EasyChair site.

Organizing Committee

Christopher Amato (Northeastern University), Frans Oliehoek (Delft University of Technology), Shayegan Omidshafiei (Google DeepMind), Karl Tuyls (Google DeepMind)

For More Information

For more information about the symposium, please see the supplementary symposium website.

Combining Machine Learning and Knowledge Engineering

The Combining Machine Learning and Knowledge Engineering AAAI Symposium aims to bring together practitioners and researchers from various companies, research centers, and academia of machine learning and knowledge engineering. Furthermore, participants should reflect on the progress made on combining machine learning and knowledge engineering approaches now two years later, after being raised in the AAAI spring symposium series in 2019 for the first time. The participants should continuously work together on joint AI for practice that is being explainable and grounded in domain knowledge. Last but not least, participants shall benefit from each other to avoid pitfalls on the one hand and provide the ground for synergetic co-operations to identify the most promising areas for better results.

Topics

Among relevant topics are the following:

• Enterprise AI
• Machine Learning
• Knowledge Engineering and Management
• Knowledge Representation and Reasoning
• Hybrid AI
• Explainable AI
• Conversational AI
• Deep Learning and Neural Networks
• Rule-based Systems
• Recommender Systems
• Scene Interpretation Systems
• Ontologies and Semantic Web
• Data Science

Use cases, application scenarios, and requirements from the industry would be highly beneficial and most welcome. Because this is a dedicated symposium on the combination of machine learning and knowledge engineering, the contributions must address both AI domains.

Format

The symposium involves presentations of accepted position, full and short papers, side-tutorial events from industry, (panel) discussions, demonstrations and plenary sessions.

Submissions

We solicit papers that can include recent or ongoing research, business cases, application scenarios, and surveys. Furthermore, proposals for industrial side-tutorial events, demonstrations and (panel) discussions are very welcome too.

Position/full papers (5 to 12 pages) and short papers (2 to 4 pages) will be peer-reviewed by the program committee to ensure academic integrity.

Industrial side-tutorial event or demonstration proposals (1 to 2 pages) should have a focus on business or research related to the symposium topics excluding undesired extensive product advertising.

Discussion proposals (1 to 2 pages) should contain a description of the specific topic.

All submissions must reflect the formatting instructions provided in the Author Kit and be submitted through EasyChair. Accepted papers will be published on the established open-access proceedings site, CEUR-WS.

Symposium Cochairs

Andreas Martin (main contact) and Knut Hinkelmann, FHNW University of Applied Sciences and Arts Northwestern Switzerland, School of Business, Riggenbachstrasse 16, 4600 Olten, Switzerland.

Organizing Committee

Hans-Georg Fill (University of Fribourg, Switzerland), Aurona Gerber (University of Pretoria, South Africa), Knut Hinkelmann (FHNW University of Applied Sciences and Arts Northwestern Switzerland), Doug Lenat (Cycorp, Inc., Austin, TX, USA), Andreas Martin (FHNW University of Applied Sciences and Arts Northwestern Switzerland), Reinhard Stolle (Argo AI GmbH, München, Germany), Frank van Harmelen(VU University, Amsterdam, Netherlands

For More Information

For more information about the symposium, please see the supplementary symposium website.

Combining Machine Learning with Physical Sciences

With recent advances in scientific data acquisition and high-performance computing, AI, and machine learning have received significant attention from applied mathematics and physics science community. From successes reported by industry, academia, and research communities, we observe that AI and machine learning have great potential to leverage scientific domain knowledge to support new scientific discoveries and enhance the development of physical models for complex natural and engineering systems.

For example, deep learning supports discovery of new materials and high-energy physics from numerous computer simulations and experiments and let us learn low-dimensional manifolds underlying the acquired data in order to represent the system of interest parsimoniously and effectively. Machine learning has offered new insights on adaptive numerical discretization schemes and numerical solvers, which are clearly distinct from traditional mathematical theories. AI also provides a new way of generalizing constitutive physics laws based on big scientific data sets.

Despite the progress, there are still many open questions. Our current understanding is limited regarding how and why AI/ML work and why they can be predictive. AI has been shown to outperform traditional methods in many cases especially with high-dimensional, inhomogeneous data sets. However, a rigorous understanding of when AI/machine learning is the right approach is largely lacking: for what class of problems, underlying assumptions, available data sets, and constraints are these new methods best suited? The lack of interpretability in AI-based modeling and related scientific theories makes them insufficient for high-impact, safety-critical applications such as medical diagnoses, national security, and environmental contamination. With transparency and a clear understanding of the data-driven mechanism, desirable properties of AI should be best utilized to extend current methods in physical and engineering modeling. Handling expensive training costs and large memory requirements for ever-increasing scientific data sets becomes also important to guarantee scalable science machine learning.

This symposium will aim to present the current state of the art and identify opportunities and gaps in AI/machine learning based physics science. The symposium will focus on challenges and opportunities for increasing the scale, rigor, robustness, and reliability of physics-informed AI necessary for routine use in science and engineering applications and discuss potential researcher-AI collaborations to significantly advance diverse scientific areas and transform the way science is done.

Topics

Authors are strongly encouraged to present papers that combine and blend physical knowledge and artificial intelligence/machine learning algorithms. Topics of interest include but are not limited to the following:

• Artificial intelligence/machine learning framework that can seamlessly synthesize models, governing equations and data
• Approaches to encode scientific knowledge in machine learning method and architecture
• Architectural and algorithmic improvements for scalable physics-informed learning
• Stability and error analysis for physics-informed learning
• Software development facilitating the inclusion of physics domain knowledge in learning
• Discovery of physically interpretable laws from data
• Applications incorporating domain knowledge into machine learning

Format

The symposium is organized by the invited talks, presentations, and posters.

Submissions

Interested participants should submit either extended abstracts (2-4 pages) or full papers (6 pages maximum) for position and work-in-progress pieces. Submissions should be formatted according to the AAAI template and submitted via the AAAI Spring Symposium EasyChair site.

Organizing Committee

Main Contact: Jonghyun Harry Lee (University of Hawai’i at Mãnoa) ( jonghyun.harry.lee@hawaii.edu)/>

Committee: Jonghyun Harry Lee (University of Hawai’i at Mãnoa), Eric Darve (Stanford University), Peter Kitanidis (Stanford University), Michael Mahoney (University of California, Berkeley), Anuj Karpatne (Virginia Tech), Matthew Farthing (U.S. Army Engineer Research and Development Center), Tyler Hesser (U.S. Army Engineer Research and Development Center)

For More Information

For more information about the symposium and a full list of organizers and program committee members, please see the supplementary symposium website.

Implementing AI Ethics

This symposium will facilitate a deeper discussion on how intelligence, agency, and ethics may intermingle in organizations and in software implementations. For example, ethical behavior can be formulated as rules, values, quantitative measures, principles, regulations, and in a number of other ways. What are the consequences of implementing each approach? How can AI ethics take advantage of technologies for building explainable, interpretable, robust, safe, and secure AI? Can AI ethics help people make more ethical choices when grappling with the choices they already make regularly?

Practitioners, companies, policy makers, professional bodies, technology providers, researchers, and academics with an interest in the implications of concrete implementations of machine ethics are welcome to participate. We particularly encourage speakers from diverse fields since we view the ethics of AI to be a collaborative, bottom-up exercise. We would like to be a venue for disparate approaches (technical, legal, philosophical and sociological) rather than a closed venue where only optimization with regard to specific functions are discussed.

Topics

The symposium will facilitate discussion on the following topics:

• When are ethical systems expressible in algorithmic form? What are the mechanisms, and how do specific philosophies of ethics differ in machine implementations?
• What methods can guarantee or verify improved ethical behavior, assuming algorithms are part of the solution?
• How can we ensure that developers of AI systems act ethically?
• What challenges and opportunities do organizations face in implementing ethical AI, and how do organizations manage them?
• What policy changes will be required as regulations or as best practices within companies to ensure responsible use of AI?

The objectives of the symposium are as follows:

• Synthesize the key AI principles for widespread adoption by individuals, corporations, policy makers
• Operationalize these principles into concrete changes required in policies, governance, processes, skills and capabilities of people, tools, techniques and technologies across different areas of society
• Establish a research agenda for outstanding issues to be tackled in operationalizing ethical values in AI (for example, AI/machine learning model engineering, AI/machine learning model development methodology, AI/machine learning model validation and verification, reasoning about conflict between values)
• Bring researchers, policy makers, and executives together to facilitate joint efforts and long-term collaborations

Submissions

We invite anyone who would like to attend and participate in the discussions to provide a 1-2 page brief on their interest in the topic, how they would contribute to the advancement of the topic, and list any relevant publications, implementations, or policy formulations on the subject. We encourage academics – both post-graduate students and seasoned researchers, policy makers, and practitioners from companies to participate.

Organizing Committee

Virginia Dignum (UMEA University, virginia@cs.umu.se), Kay Firth-Butterfield (World Economic Forum, Kay.Firth-Butterfield@weforum.org), Graham Finlay (University College Dublin, graham.finlay@ucd.ie), Steven Greidinger (4sjgcombined@gmail.com), Vivek Nallur (University College Dublin, vivek.nallur@ucd.ie), Anand S. Rao (PwC, anand.s.rao@pwc.com)

For More Information

For more information about the symposium, please see the supplementary symposium website.

Leveraging Systems Engineering to Realize Synergistic AI/Machine Learning Capabilities

Jay Forrester, creator of system dynamics, remarked we “live in a complex world of nested feedback loops,” involving cascading interdependencies across these loops that vary in complexity, space, and time. Many if not most of current AI/machine learning processes and data and information fusion processes (and perhaps other methods) are attempting, in software, to estimate conditions (situations) in this complex world that Forrester describes, and thus face the challenges of dealing with nested feedback loops and associated interdependencies.

To realize effective and efficient designs of these computational systems, a systems engineering and a systems thinking perspective may provide a framework for seeing interrelationships between parts and for seeing patterns of change rather than static snapshots, as systems engineering methods are about seeing wholes. The increasing prevalence of intelligent systems within society will reveal yet more interdependencies, in that AI-enabled intelligent systems have both upstream processes impacting them and downstream processes they affect. The benefits of studying cascading interdependencies through an systems engineering perspective is essential to understanding their behavior and for the adoption of complex system-of-systems in society. Knowledge about the world is needed for multiple applications.

Models of complex situations (patterns of life) are typically attacked with reductionism. However, in the absence of modeling dynamic and evolving feedback and interrelationships, these strategies fall short. If causal motivations for feedback and interrelations can be developed, system modeling, and the ability to estimate system dynamics, will be as correct as possible. But real-world situations for Forrester’s “nested feedback loops” involve uncertainty and incompleteness, impeding accurate estimates. These problems continue to be addressed by data and information fusion communities, whose processes form snapshots and estimates about component entities and situational states. However, data and information fusion communities should seek opportunities for AI/machine learning beyond these component-level estimates, toward modeling synergies and dependencies within and across estimation loops to achieve maximum situational awareness.

This symposium will explore the effects of cascading interdependencies and overlap in real-world dynamics and opportunities to leverage SE principles to design and develop AI/machine learning and data and information fusion estimation processes that accurately represent such complex world states. These relationships are exacerbated by the unpredictability of human decision-makers, uncertainty in raw and fused data, and the large trade space of algorithm permutations orchestrated to solve given problems. Systems Engineering brings opportunities to address and model the full range of complex, synergistic feedback loops in modern complex systems, toward the realization of cost-effective designs.

Topics

A partial list of topics includes AI, machine learning and reasoning; data and information fusion; systems engineering; interdependence; human systems; human biases and limitations; trust and complex AI systems; ethics. For a full list, please see the supplementary symposium website listed below.

Format

The format of the symposium will include invited (60 minutes) and regular talks (30 minutes).

Submissions (Deadline Extended)

By January 15, 2021, contributors should submit to Easychair an extended abstract of up to 500 words or full papers of about 10,000 words; use APA references. A call for book chapters follows the symposium.

Organizing Committee

W.F. Lawless (Paine College), w.lawless@icloud.com (main contact) Ranjeev Mittu (U.S. Naval Research Laboratory), Don Sofge (U.S. Naval Research Laboratory), Thomas Shortell (Lockheed Martin Company), Thomas McDermott (Stevens Institute of Technology), James Llinas (University at Buffalo (North Campus)), Julie L. Marble, (Johns Hopkins University)

For More Information

For more information about the symposium, please see the supplementary symposium website.

Machine Learning for Mobile Robot Navigation in the Wild

Topics

Full papers of up to six pages and abstract papers of up to two pages are sought in the following areas:

• Learning for social navigation
• Learning for terrain-based navigation
• Learning for vision-based navigation
• Learning for interactive navigation
• Representation learning for navigation 
• Sim2real for navigation
• Zero-shot path planning
• Learning for navigation in unstructured or confined environments
• Reinforcement learning for navigation in the wild
• Imitation learning for navigation in the wild
• Active learning for navigation in the wild
• Lifelong/continual learning for navigation in the wild
• Geometric methods for learning navigation
• Real-world validation of learning for navigation
• Navigation problems, benchmarks, and metric

Format

The Machine Learning for Mobile Robot Navigation in the Wild Symposium will consist of invited talks, technical presentations, spotlight posters, robot demonstrations, industry spotlights, breakout sessions, and interactive panel discussions.

Submissions

All contributions should be submitted electronically via AAAI EasyChair site.

Organizing Committee

Xuesu Xiao (Symposium Chair and main contact) (The University of Texas at Austin, xiao@cs.utexas.edu), Harel Yedidsion (The University of Texas at Austin), Reuth Mirsky (The University of Texas at Austin,), Justin Hart (The University of Texas at Austin), Peter Stone (The University of Texas at Austin), Ross Knepper (Cornell University), Hao Zhang (Colorado School of Mines), Jean Oh (Carnegie Mellon University), Davide Scaramuzza (University of Zurich), Vaibhav Unhelkar (Rice University),

For More Information

For more information about the symposium, please see the supplementary symposium website.

Survival Prediction: Algorithms, Challenges and Applications

A survival analysis model estimates the time until a specified event will happen in the future (or related survival measure), for an individual. The event of interest could be the time to death or relapse of a patient, or time until an employee leaves a company or until the failure of a mechanical system. The key challenge in learning effective survival models is that this time-to-event is censored for some observations, which limits the direct use of standard regression techniques. This has led to a wide range of survival models, that each use the features of an instance (such as a patient), available at the start time, to produce some survival measure, which might be a risk score, the probability of survival to a specific future time (such as 1 year), or the survival probability over all future times.

This symposium focuses on approaches for learning models that estimate survival measures from survival datasets, which include censored instances. Its objective is to push the state-of-the-art in survival prediction algorithms and address fundamental issues that hinder their applicability for solving complex real-world problems. We anticipate this will foster interdisciplinary collaborations and create new research directions

Topics

We seek submissions that discuss the following topics.

Novel Algorithms — new static or dynamic machine-learning frameworks for survival prediction, algorithms to compute survival measures from multimodal and/or longitudinal datasets.

Evaluation Metrics — limitations of the data (for example, high censoring) and evaluation metrics (for example, c-index), provide new directions for comparing survival models, address model calibration and discrimination issues, and discuss model comparison strategies.

Foundational Issues — issues such as competing risks, causality, counterfactual reasoning, comorbidities, multimorbidities and uncertainty quantification.

Applications — in medicine, healthcare, manufacturing, engineering, finance, economics, law enforcement..

Format

The symposium will include invited talks, presentations of accepted papers and posters, and discussion sessions.

Submissions

Authors can submit extended abstracts (2-4 pages) for poster sessions or full papers (4-6 pages, excluding references) for position, review and work-in-progress pieces. Papers with previously published results will be considered.

Format submissions according to the AAAI template and submit through EasyChair site. Program committee will review the submissions and accepted papers will be published on the open-access proceedings site, CEUR-WS.

Organizing Committee

Russ Greiner (University of Alberta, rgreiner@ualberta.ca,chair), Neeraj Kumar (University of Alberta), Thomas Gerds (University of Copenhagen), Mihaela van der Schaar (Cambridge University)

For More Information

For more information about the symposium, please see the supplementary symposium website. Questions should be emailed to survivalprediction2021@gmail.com.

Applied AI in Healthcare: Safety, Community, and the Environment

This symposium will discuss ways to solve health-related, real-world issues in various emerging, ongoing, and underrepresented areas. Our international team is primarily focused on AI-assisted healthcare, with specific focus on areas of improving safety, the community, and the environment through the latest technological advances in our respective fields. We also want to improve the design and deployment of new technologies by considering the broader contexts in which they will be used. Our group’s mission is to bring engineers, computer and data scientists, physician specialists, epidemiologists, public health researchers, ergonomists, ethicists, social scientists, designers, safety personnel, and other scholars and healthcare professionals together to share and foster ideas.

Topics

This symposium focuses on the following three themes related to potentially challenging issues in healthcare AI: (1) Workplace safety and the environment; (2) Caregiving in the community; and (3) Specialized applications of AI in healthcare.

Workplace Safety and the Environment: There is a significant knowledge gap in the workplace AI arena. Our current focus areas of interest (but not restricted to) revolve around the role of machine learning in optimizing workplace ergonomics, business travel, hospital ergonomics, and monitoring environmental hazards, including automating wildfire smoke or air quality predictions via proprietary Google database sets and other global satellite systems.

Caregiving in the Community:

The introduction of digital technology and AI in care work, along with the broad adoption of network infrastructures and the increasing attention to community-based care, creates opportunities to provide healthcare in novel ways. We consider how emerging AI technologies may bring different forms of care back into homes and communities through health monitoring applications, assistive robotics, telehealth platforms, automated transportation, and other innovations. We will also discuss existing technical, social, design, and practice-oriented aspects of care work and technology, and new conceptual frameworks of care work and design paradigms for assistive technologies that can enable distributed, scalable, sustainable, and maintainable healthcare in 21st-century communities.

Specialized Applications of AI in healthcare: This theme aims to share the latest progress, current challenges and potential applications related to the use of AI in healthcare. Submissions may focus on specific and technical details or bring a more general point of view on the use of AI in healthcare and improvement of public and population health.

Format

The symposium will include invited talks, presentations of accepted papers, group work sessions and panels. Use cases, current and potential application scenarios, and requirements from industry would be encouraged. Invited speakers and presentations will be announced after the submissions. More information will appear on the supplementary symposium website.

Submissions

Interested participants should submit either full papers (6–8 pages), short papers (2–4 pages) or extended abstracts (2 pages maximum). Submissions are invited from all perspectives of interest (see the Topics section) Submissions can include recent or ongoing research, position papers, and surveys or reviews.

Submissions will be handled through the AAAI Spring Symposium EasyChair site,

Organizing Committee

Rajan Puri (Stanford University, purir@stanford.edu), Samira Rahimi (McGill University, Samira.rahimi@mcgill.ca), Selma Šabanović (Indiana University, Bloomington, elmas@indiana.edu)

For More Information

For more information about the Applied AI in Healthcare: Safety, Community, and the Environment symposium, please see the supplementary symposium site.