publications

2024

1. arxiv

   Dialogue with Robots: Proposals for Broadening Participation and Research in the SLIVAR Community

   Kennington, Casey, Alikhani, Malihe, Pon-Barry, Heather, Atwell, Katherine, Bisk, Yonatan, Fried, Daniel, Gervits, Felix, Han, Zhao, Inan, Mert, Johnston, Michael, and others,

   2024

   arXiv
2. arxiv

   Are Generative AI systems Capable of Supporting Information Needs of Patients?

   Rajagopal, Shreya, Hazarika, Subhashis, Kim, Sookyung, Chiou, Yan-ming, Sohn, Jae Ho, Subramonyam, Hari, and Mohan, Shiwali

   2024

   arXiv
3. ICAPS Demo

   Self-adaptive Mission Planning using High-Fidelity Open World Simulation

   Piotrowski, Wiktor Mateusz, Chao, James, Grover, Sachin, Stern, Roni, Mohan, Shiwali, and Lange, Douglas S.

   ICAPS 2024 System’s Demonstration track 2024

   HTML
4. ICAPS Demo

   A Demonstration of Natural Language Understanding in Embodied Planning Agents

   Grover, Sachin, and Mohan, Shiwali

   ICAPS 2024 System’s Demonstration track 2024

   HTML
5. AIJ

   A domain-independent agent architecture for adaptive operation in evolving open worlds

   Mohan, Shiwali, Piotrowski, Wiktor, Stern, Roni, Grover, Sachin, Kim, Sookyung, Le, Jacob, Sher, Yoni, and Kleer, Johan

   Artificial Intelligence 2024

   Abs arXiv HTML

   Model-based reasoning agents are ill-equipped to act in novel situations in which their model of the environment no longer sufficiently represents the world. We propose HYDRA, a framework for designing model-based agents operating in mixed discrete-continuous worlds that can autonomously detect when the environment has evolved from its canonical setup, understand how it has evolved, and adapt the agents’ models to perform effectively. HYDRA is based upon PDDL+, a rich modeling language for planning in mixed, discrete-continuous environments. It augments the planning module with visual reasoning, task selection, and action execution modules for closed-loop interaction with complex environments. HYDRA implements a novel meta-reasoning process that enables the agent to monitor its own behavior from a variety of aspects. The process employs a diverse set of computational methods to maintain expectations about the agent’s own behavior in an environment. Divergences from those expectations are useful in detecting when the environment has evolved and identifying opportunities to adapt the underlying models. HYDRA builds upon ideas from diagnosis and repair and uses a heuristics-guided search over model changes such that they become competent in novel conditions. The HYDRA framework has been used to implement novelty-aware agents for three diverse domains - CartPole++ (a higher dimension variant of a classic control problem), Science Birds (an IJCAI competition problem) and PogoStick (a specific problem domain in Minecraft). We report empirical observations from these domains to demonstrate the efficacy of various components in the novelty meta-reasoning process.

2023

1. ICAPS

   Heuristic search for physics-based problems: angry birds in PDDL+

   Piotrowski, Wiktor, Sher, Yoni, Grover, Sachin, Stern, Roni, and Mohan, Shiwali

   Proceedings of the International Conference on Automated Planning and Scheduling 2023

   HTML
2. AAMAS

   Learning to operate in open worlds by adapting planning models

   Piotrowski, Wiktor, Stern, Roni, Sher, Yoni, Le, Jacob, Klenk, Matthew, deKleer, Johan, and Mohan, Shiwali

   Proceedings of the International Conference on Autonomous Agents and Multi-Agent Systems 2023

   arXiv

2022

1. Modeling and simulating thermostat behaviors of office occupants: are values more important than comfort?

   Dongre, Poorvesh, Gračanin, Denis, Mohan, Shiwali, Mostafavi, Saman, and Ramea, Kalai

   In Proceedings of the 9th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation 2022

2021

1. ICAPS Demo

   Playing Angry Birds with a Domain-Independent PDDL+ Planner

   Piotrowski, Wiktor, Stern, Roni, Klenk, Matthew, Perez, Alexandre, Mohan, Shiwali, Kleer, Johan, and Le, Jacob

   Proceedings of the 31st International Conference on Automated Planning Systems (demo track) 2021

   arXiv HTML
2. IEEE RO-MAN

   Unpacking Human Teachers’ Intentions For Natural Interactive Task Learning

   Ramaraj, Preeti, Ortiz Jr, Charles L, and Mohan, Shiwali

   30th IEEE International Conference on Robot and Human Interactive Communication 2021

   Abs arXiv

   Interactive Task Learning (ITL) is an emerging research agenda that studies the design of complex intelligent robots that can acquire new knowledge through natural human teacher-robot learner interactions. ITL methods are particularly useful for designing intelligent robots whose behavior can be adapted by humans collaborating with them. Various research communities are contributing methods for ITL and a large subset of this research is robot-centered with a focus on developing algorithms that can learn online, quickly. This paper studies the ITL problem from a human-centered perspective to provide guidance for robot design so that human teachers can interact with ITL robots naturally. In this paper, we present 1) a cognitive task analysis of an interactive teaching study (N=10) that extracts and classify various actions intended and executed by human teachers when teaching a robot; 2) in-depth discussion of the teaching approach employed by two participants to understand the need for personal adaptation to individual styles; and 3) requirements for ITL robot design based on our analyses informed by plan-based theories of dialogue, specifically SharedPlans.

3. ACM TiiS

   Exploring the Role of Common Model of Cognition in Designing Adaptive Coaching Interactions for Health Behavior Change

   Mohan, Shiwali

   ACM Transactions on Interactive Intelligent Systems 2021

   Abs arXiv HTML

   Our research aims to develop intelligent collaborative agents that are human-aware - they can model, learn, and reason about their human partner’s physiological, cognitive, and affective states. In this paper, we study how adaptive coaching interactions can be designed to help people develop sustainable healthy behaviors. We leverage the common model of cognition - CMC [26] - as a framework for unifying several behavior change theories that are known to be useful in human-human coaching. We motivate a set of interactive system desiderata based on the CMC-based view of behavior change. Then, we propose PARCoach - an interactive system that addresses the desiderata. PARCoach helps a trainee pick a relevant health goal, set an implementation intention, and track their behavior. During this process, the trainee identifies a specific goal-directed behavior as well as the situational context in which they will perform it. PARCcoach uses this information to send notifications to the trainee, reminding them of their chosen behavior and the context. We report the results from a 4-week deployment with 60 participants. Our results support the CMC-based view of behavior change and demonstrate that the desiderata for proposed interactive system design is useful in producing behavior change.

2020

1. CMC

   A Case Study of Knowledge Integration Across Multiple Memories in Soar

   Laird, John E, and Mohan, Shiwali

   Common Model of Cognition Bulletin 2020

   Abs HTML

   In this paper, we describe a complex Soar agent that uses and learns multiple types of knowledge while interacting with a human in a real-world domain. Our hypothesis is that a diverse set of memories is required for the different types of knowledge. We first present the agent’s processing, highlighting the types of knowledge used for each phase. We then present Soar’s memories and identify which memory is used for each type of knowledge. We also analyze which properties of each memory make it appropriate for the knowledge it encodes. We conclude with a summary of our analysis.

2. DX

   Model-Based Novelty Adaptation for Open-World AI

   Klenk, Matthew, Piotrowski, Wiktor, Stern, Roni, Mohan, Shiwali, and Kleer, Johan

   Proceedings of the 31st International Workshop on Principles of Diagnosis 2020

   HTML
3. ACM TiiS

   Designing an AI Health Coach and Studying its Utility in Promoting Regular Aerobic Exercise

   Mohan, Shiwali, Venkatakrishnan, Anusha, and Hartzler, Andrea

   ACM Transactions on Interactive Intelligent Systems (TiiS) 2020

   Abs arXiv HTML

   Our research aims to develop interactive, social agents that can coach people to learn new tasks, skills, and habits. In this paper, we focus on coaching sedentary, overweight individuals (i.e., trainees) to exercise regularly. We employ adaptive goal setting in which the intelligent health coach generates, tracks, and revises personalized exercise goals for a trainee. The goals become incrementally more difficult as the trainee progresses through the training program. Our approach is model-based - the coach maintains a parameterized model of the trainee’s aerobic capability that drives its expectation of the trainee’s performance. The model is continually revised based on trainee-coach interactions. The coach is embodied in a smartphone application, NutriWalking, which serves as a medium for coach-trainee interaction. We adopt a task-centric evaluation approach for studying the utility of the proposed algorithm in promoting regular aerobic exercise. We show that our approach can adapt the trainee program not only to several trainees with different capabilities, but also to how a trainee’s capability improves as they begin to exercise more. Experts rate the goals selected by the coach better than other plausible goals, demonstrating that our approach is consistent with clinical recommendations. Further, in a 6-week observational study with sedentary participants, we show that the proposed approach helps increase exercise volume performed each week.

4. ACS

   Characterizing an Analogical Concept Memory for Architectures Implementing the Common Model of Cognition

   Mohan, Shiwali, Klenk, Matt, Shreve, Matthew, Evans, Kent, and Maxwell, John

   In Proceedings of the Annual Conference on Advances in Cognitive Systems 2020

   arXiv
5. RSS Workshops

   Understanding Intentions in Human Teaching to Design Interactive Task Learning Robots

   Ramaraj, Preeti, Klenk, Matt, and Mohan, Shiwali

   In RSS Workshops 2020 2020

   Abs HTML

   The goal of Interactive Task Learning (ITL) isto build robots that can be trained in new tasks by humaninstructors. In this paper, we approach the ITL research problemfrom a human instructor perspective. The research questionthat we address here ishow do we understand and leveragethe intentionality of the instructors to enable natural and flexibleITL. We propose a taxonomy based onCollaborative DiscourseTheorythat organizes human teaching intentions in a humanrobot teaching interaction. This taxonomy will provide guidancefor ITL robot design that leverages a human’s natural teachingskills, and reduces the cognitive burden of non-expert instructors.We propose human participant studies to validate this taxonomyand gain a comprehensive understanding of teaching interactionsin ITL.

2019

1. JAIR

   Acceptable planning: Influencing Individual Behavior to Reduce Transportation Energy Expenditure of a City

   Mohan, Shiwali, Rakha, Hesham, and Klenk, Matt

   Journal of Artificial Intelligence Research 2019

   Abs HTML

   Our research aims at developing intelligent systems to reduce the transportation-related energy expenditure of a large city by influencing individual behavior. We introduce Copter - an intelligent travel assistant that evaluates multi-modal travel alternatives to find a plan that is acceptable to a person given their context and preferences. We propose a formulation for acceptable planning that brings together ideas from AI, machine learning, and economics. This formulation has been incorporated in Copter that produces acceptable plans in real-time. We adopt a novel empirical evaluation framework that combines human decision data with a high fidelity multi-modal transportation simulation to demonstrate a 4% energy reduction and 20% delay reduction in a realistic deployment scenario in Los Angeles, California, USA.

2. AIES

   On Influencing Individual Behavior for Reducing Transportation Energy Expenditure in a Large Population

   Mohan, Shiwali, Yan, Frances, Bellotti, Victoria, Rakha, Hesham, and Klenk, Matthew

   In AAAI/ACM Conference on AI, Ethics, and Society 2019

   Abs HTML

   Our research aims at developing intelligent systems to reduce the transportation-related energy expenditure of a large city by influencing individual behavior. We introduce Copter - an intelligent travel assistant that evaluates multi-modal travel alternatives to find a plan that is acceptable to a person given their context and preferences. We propose a formulation for acceptable planning that brings together ideas from AI, machine learning, and economics. This formulation has been incorporated in Copter producing acceptable plans in real-time. We adopt a novel empirical evaluation framework that combines human decision data with high-fidelity simulation to demonstrate a 4% energy reduction and 20% delay reduction in a realistic deployment scenario in Los Angeles, California, USA.

3. IUI Workshops

   Exploring How to Personalize Travel Mode Recommendations For Urban Transportation.

   Mohan, Shiwali, Klenk, Matthew, and Bellotti, Victoria

   In IUI Workshops 2019

   Abs HTML

   The diverse transportation services of today’s cities pose a signif-icant opportunity for personalizing route planning user’s experi-ences. To understand what people are taking into account in mo-bility decisions, we present a pair of human studies. First, we con-ducted interviews to explore what factors people consider to makedecisions about their travel. Then, we designed, ran, and analyzeda survey to study which of those factors are crucial to model forunderstanding mobility decisions and behavior. Our analysis in-dicates that people’s mobility decisions incorporate considerablymore information than current applications support. Also, differ-ences in people’s experience, personality, and requirements signif-icantly impact their mode choice preferences. We close with a dis-cussion about how these findings go beyond trip planning to otherpotential smart cities problems.

4. IUI Workshops

   Building Jarvis - A Learner-Aware Conversational Trainer

   Mohan, Shiwali, Ramea, Kalai, Price, Bob, Shreve, Matthew, Eldardiry, Hoda, and Nelson, Les

   In In 2019 ACM IUI Workshops 2019

   Abs HTML

   Our long-term research goal is to develop intelligent sys-tems that can support human learning. We are particularly interested in developing an approach toapprenticeship learning which occurs during the physical context of task execution and is known to be very effective in learning procedural tasks such as equipment maintenance or artifact assembly. We describe our initial progress in building such system - Jarvis - that leverages real-time computer vision, high-level inference, and augmented reality technology to monitor andsupport human task learning through apprenticeship.

2018

1. JMIR

   Leveraging Self-Affirmation to Improve Behavior Change: a Mobile Health App Experiment

   Springer, Aaron, Venkatakrishnan, Anusha, Mohan, Shiwali, Nelson, Lestr, Silva, Michael, and Pirolli, Peter

   JMIR mHealth and uHealth 2018

   Abs HTML

   Background: mHealth interventions can help to improve the physical well-being of participants. Unfortunately, mHealth interventions often have low adherence and high attrition. One possible way to increase adherence is instructing participants to complete self-affirmation exercises. Self-affirmation exercises have been effective in increasing many types of positive behaviors. However, self-affirmation exercises often involve extensive essay writing, a task that is not easy to complete on mobile platforms. Objective: This study aimed to adapt a self-affirmation exercise to a form better suited for delivery through a mobile app targeting healthy eating behaviors, and to test the effect of differing self-affirmation doses on adherence to behavior change goals over time. Methods: We examined how varied self-affirmation doses affected behavior change in an mHealth app targeting healthy eating that participants used for 28 days. We divided participants into the 4 total conditions using a 2×2 factorial design. The first independent variable was whether the participant received an initial self-affirmation exercise. The second independent variable was whether the participant received ongoing booster self-affirmations throughout the 28-day study. To examine possible mechanisms through which self-affirmation may cause positive behavior change, we analyzed three aspects of self-affirmation effects in our research. First, we analyzed how adherence was affected by self-affirmation exercises. Second, we analyzed whether self-affirmation exercises reduced attrition rates from the app. Third, we examined a model for self-affirmation behavior change. Results: Analysis of 3556 observations from 127 participants indicated that higher doses of self-affirmation resulted in improved adherence to mHealth intervention goals (coefficient 1.42, SE 0.71, P=.04). This increased adherence did not seem to translate to a decrease in participant attrition (P value range .61-.96), although our definition of attrition was conservative. Finally, we examined the mechanisms by which self-affirmation may have affected intentions of behavior change; we built a model of intention (R2=.39, P<.001), but self-affirmation did not directly affect final intentions (P value range .09-.93). Conclusions: Self-affirmations can successfully increase adherence to recommended diet and health goals in the context of an mHealth app. However, this increase in adherence does not seem to reduce overall attrition. The self-affirmation exercises we developed were simple to implement and had a low cost for both users and developers. While this study focused on an mHealth app for healthy eating, we recommend that other mHealth apps integrate similar self-affirmation exercises to examine effectiveness in other behaviors and contexts.

2. AAAI

   Learning Fast and Slow: Levels of Learning in General Autonomous Intelligent Agents.

   Laird, John, and Mohan, Shiwali

   In Proeedings of the AAAI Conference on Artificial Intelligence 2018
3. ICAPS Workshops

   Collaborative Optimization and Planning for Transportation Energy Reduction

   Dvorak, Filip, Mohan, Shiwali, Bellotti, Victoria, and Klenk, Matthew

   In ICAPS Proceedings of the 6th Workshop on Distributed and Multi-Agent Planning (DMAP 2018

2017

1. IAAI/AAAI

   On Designing a Social Coach to Promote Regular Aerobic Exercise

   Mohan, Shiwali, Venkatakrishnan, Anusha, Silva, Michael, and Pirolli, Peter

   In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence 2017
2. IEEE. Int. Sys.

   Interactive Task Learning

   Laird, John E, Gluck, Kevin, Anderson, John, Forbus, Kenneth D, Jenkins, Odest Chadwicke, Lebiere, Christian, Salvucci, Dario, Scheutz, Matthias, Thomaz, Andrea, Trafton, Greg, Wray, Robert, Mohan, Shiwali, and Kirk, James

   IEEE Intelligent Systems 2017
3. JMIR

   Implementation intention and reminder effects on behavior change in a mobile health system: a predictive cognitive model

   Pirolli, Peter, Mohan, Shiwali, Venkatakrishnan, Anusha, Nelson, Les, Silva, Michael, and Springer, Aaron

   Journal of medical Internet research 2017
4. AAAI Workshops

   Collaborative autonomy through analogical comic graphs

   Klenk, Matthew, Mohan, Shiwali, De Kleer, Johan, Bobrow, Daniel G, Hinrichs, Thomas R, and Forbus, Kenneth D

   In 31st AAAI Conference on Artificial Intelligence, AAAI 2017 2017

2016

1. ACS

   Towards an Indexical Model of Situated Language Comprehension for Cognitive Agents in Physical Worlds

   Mohan, Shiwali, Mininger, Aaron, and Laird, John

   Advances in Cognitive Systems 2016
2. EMBC

   Acceptability of a team-based mobile health (mHealth) application for lifestyle self-management in individuals with chronic illnesses

   Hartzler, Andrea, Venkatakrishnan, Anusha, Mohan, Shiwali, Silva, Michael, Lozano, Paula, D. Ralston, James, Ludman, Evette, Rosenberg, Dori, M. Newton, Katherine, Nelson, Lester, and Pirolli, Peter

   In Conference proceedings: 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2016

2015

1. UM

   From Verbs to Tasks: An Integrated Account of Learning Tasks from Situated Interactive Instruction

   Mohan, Shiwali

   2015

2014

1. AAAI

   Learning Goal-Oriented Hierarchical Tasks from Situated Interactive Instruction

   Mohan, Shiwali, and Laird, John

   In Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence 2014
2. BICA

   A Case Study of Knowledge Integration Across Multiple Memories in Soar

   Laird, John, and Mohan, Shiwali

   Biologically Inspired Cognitive Architectures 2014

2013

1. ICCM

   A Computational Model for Situated Task Learning with Interactive Instruction

   Mohan, Shiwali, Kirk, James, and Laird, John

   In Proceedings of the 2013 International Conference on Cognitive Modeling 2013

2012

1. ACS

   Acquiring Grounded Representations of Words with Situated Interactive Instruction

   Mohan, Shiwali, Mininger, Aaron, Kirk, James, and Laird, John

   Advances in Cognitive Systems 2012

   HTML
2. ICTAI

   Object-Oriented Representation and Hierarchical Reinforcement Learning in Infinite Mario

   Joshi, Mandar, Khobragade, Rakesh, Sarda, Saurabh, Deshpande, Umesh, and Mohan, Shiwali

   In In Proceedings of the 24th IEEE International Conference on Tools with Artificial Intelligence 2012
3. STAIRS

   Hierarchical Action Selection for Reinforcement Learning in Infinite Mario

   Joshi, Mandar, Khobragade, Rakesh, Sarda, Saurabh, Deshpande, Umesh, and Mohan, Shiwali

   In In Proceedings of the 6th Starting Artificial Intelligence Research Symposium (co-located with ECAI) 2012

   HTML
4. AAAI Workshops

   Cognitive Robotics Using the Soar Cognitive Architecture

   Laird, John, Kinkade, Keegan, Mohan, Shiwali, and Xu, Joseph

   In In Proceedings of the 8th International Cognitive Robotics Workshop 2012

   HTML PDF
5. AAAI Workshops

   Situated Comprehension of Imperative Sentences in Embodied, Cognitive Agents

   Mohan, Shiwali, and Laird, John

   In Grounding Language for Physical Systems, AAAI Technical Report WS-12-07 2012

   HTML
6. AAAI

   Exploring Mixed-Initiative Interaction for Learning with Situated Instruction in Cognitive Agents

   Mohan, Shiwali, and Laird, John

   In Proceedings of the 26th AAAI Conference on Artificial Intelligence 2012

   HTML
7. AAAI

   Learning Actions and Action Verbs from Human-Agent Interaction

   Mohan, Shiwali, and Laird, John

   In 17th AAAI/SIGART Doctoral Consortium 2012

   PDF

2011

1. AAAI FSS

   Towards Situated, Interactive, Instructable Agents in a Cognitive Architecture

   Mohan, Shiwali, and Laird, John

   In Papers from the 2011 AAAI Fall Symposium Series 2011

   Abs HTML

   This paper discusses the challenge of designing instructable agents that can learn through interaction with a human expert. Learning through instruction is a powerful paradigm for acquiring knowledge because it limits the complexity of the learning task in a variety of ways. To support learning through instruction, the agent must be able to effectively communicate its lack of knowledge to the human, comprehend instructions, and apply them to the ongoing task. We identify some problems of concern when designing instructable agents. We propose an agent design that addresses some of these problems. We instantiate this design in the Soar cognitive architecture and analyze its capabilities on a learning task.

2010

1. AAAI

   Relational Reinforcement Learning in Infinite Mario

   Mohan, Shiwali, and Laird, John

   In Proceedings of the 24th AAAI Conference on Artificial Intelligence 2010

   Abs HTML

   Relational representations in reinforcement learning allow for the use of structural information like the presence of objects and relationships between them in the description of value functions. Through this paper, we show that such representations allow for the inclusion of background knowledge that qualitatively describes a state and can be used to design agents that demonstrate learning behavior in domains with large state and actions spaces such as computer games.‘

2009

1. UM

   Learning to Play Mario

   Mohan, Shiwali, and Laird, John E.

   2009

   Abs HTML

   Computer Games are interesting test beds for research in Artificial Intelligence and Machine Learning. Games usually have continuous state spaces, large action spaces and are characterized by complex relationships between components. Without applying abstraction and generalizations, learning in computer games domain becomes infeasible. Through this work, we investigate some designs that facilitate tractable reinforcement learning in symbolic agents developed using Soar architecture operating in a complex domain, Infinite Mario. Object oriented representations of the environment greatly simplify otherwise complex state spaces. We also demonstrate that imposing hierarchy in problem structure greatly reduces the complexity of the tasks and aids in learning generalized policies that can be transferred across similar tasks.