Shiwali Mohan

I build intelligent interactive systems that model, learn, and reason about their human collaborators. My research advances methods for complex sequential decision making, intelligent agent systems, as well as hybrid AI architectures built with statistical machine learning and knowledge-rich inference algorithms. I leverage insights from economics, psychology, education, and HCI to desgin effective and robust human-agent collaboration in real-world settings.

As a Principal Investigator at SRI International, I lead technology and business development for AI research. My work spans fundamental algorithmic advances as well applications of AI.

Fundamental AI: I lead research on open-world learning agents (DARPA SAIL-ON) and on teachable agents (DARPA GAILA). Both these efforts study how agents can adapt to new situations after they are operational without the need of taking them offline and re-training. I study the role of structured representations in efficient & resilient agent architectures and investigate how they can be manipulated or adapted efficiently on-the-fly.

AI Applications: I have designed interactive, collaborative agents for a variety of domains including patient-centric, preventative healthcare, sustainable living, general purpose robots, and augmented reality. I am particularly motivated to build intelligent collaborative technology social good and public welfare.

My work is interdisciplinary and has been published at venues for research on artificial intelligence (AIJ, JAIR, AAAI, IAAI), human cognition (ICCM, ACS, BICA), human-machine interaction (ACM TiiS, IEEE RO-MAN) as well as in applications (JMIR, EMBC, ACM/AAAI AIES).

news

Sep 1, 2024	Our work on open-world learning agents is published in the AI Journal.
Jun 4, 2024	We demonstrated open-world learning for UAVs and LLM+planning for embodied agents at ICAPS 24.
Jul 31, 2023	I was invited to the DARPA AI Forward initative to identify the directions AI research should take next.
Mar 10, 2022	Giving an invited talk on cognitive science and collaborative robots at Human-Interactive Robot Learning at HRI 2022.
Mar 3, 2022	ITL research by Aaron Mininger and John Laird in the Soar group won the best demonstration award at AAAI 2022.

selected publications

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.
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.
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.
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.
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
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