---

	Shashank Shekhar, Ph.D. (शशांक शेखर)         Chercheur Contractuel at IRIT-CNRS         Research Interests: Multi-Agent Systems, Automated Planning, Decision Making under Uncertainty, Human-Robot Interaction         Université Paul Sabatier         118 Route de Narbonne         31062 Toulouse Cedex 9, France
	Email: first-name dot last-name at irit dot fr         Phone: (M) +33 6 52 60 38 83 (WhatsApp: +972 5 86 30 42 78)         DBLP   Google Scholar   Linkedin   Twitter

Relying on a single agent system that is managed by an entity and has access to all data is impractical in real-world situations. It is crucial to promote both uniqueness and teamwork in order to accomplish successful partnership. My research focuses on tackling problems that require a meaningful integration of perspectives, problem-solving skills, and knowledge representation and reasoning from various agents or organizations. This is done through studying planning and decision-making for multi-agent systems. Taking on complex problems that are beyond the scope of one organization is the goal.

Bio

I have joined IRIT-CNRS as a Chercheur Contractuel in the LILaC team. I will be working with Dr. Andreas Herzig (EurAI Fellow). My research interests include automated planning, decision-making under uncertainty, multi-agent systems, human-robot interaction, heuristic search, and their real-world applications. Additionally, I aim to expand my expertise in multi-agent planning/pathfinding problems under temporal and spatial uncertainty and their applications.

Prior to that, I worked at LAAS-CNRS as a postdoc researcher in human-robot collaboration and (multi-robot) task planning. I was a part of the Robotics and InteractionS (RIS) research team and worked with Dr. Rachid Alami.

I was a postdoctoral fellow (for half a year) in The Department of Computer Science, Ben-Gurion University of the Negev, Beer-Sheva, Israel, working with Professor Ronen I. Brafman (Fellow of AAAI and EurAI). I received my Ph.D. in Computer Science from this university. I was very fortunate to be advised by Professor Brafman. The focus of my Ph.D. thesis - Collaborative Multi-agent Planning with Partial Observability and Interacting Actions (pdf) was on devising plausible frameworks and algorithms for solving collaborative multi-agent planning problems with interacting actions.

I received my M.S. (by research) in artificial intelligence planning, heuristic search, and learning (my master's thesis - Learning and strengthening meta-heuristics in plan-space planning (pdf)) from Department of Computer Science & Engineering, Indian Institute of Technology Madras (IIT Madras), India, advised by Professor Deepak Khemani (retired). I received my Bachelor of Technology (B.Tech.) (with distinction) in 2011 from Guru Gobind Singh Indraprastha University, New Delhi. I joined Infosys Ltd. as a software engineer after my bachelor's and later quit my job to join IITM.

Fellowships/Awards/Grants

• CIMI Fellowship for Postdoctoral Research (Individual Research Grant) Awarded funding to support independent research under the supervision of Dr. Andreas Herzig at IRIT-CNRS, Toulouse, France.
• (Best student paper - honourable mention) A. Favier, S. Shekhar, R. Alami. Models and Algorithms for Human-Aware Task Planning with Integrated Theory of Mind. In proc. of IEEE RO-MAN 2023.

Newsworthy

• 2024/09: I have accepted a position as a teacher-researcher -- Maître de conférences (MCF) -- at the Department of Computer Science of the University of Caen Normandie (France) and I will be conducting research activities at the CNRS GREYC UMR 6072 Laboratory.
• 2024/09: Our paper, titled An Epistemic Human-Aware Task Planner which Anticipates Human Beliefs and Decisions, has been accepted at International Social Robotics Conference (ICSR) 2024.
• 2024/05: A paper was accepted at HAXP 2024 (the ICAPS workshop), titled - Human-Aware Epistemic Task Planning for Human-Robot Collaboration
• 2023/08: SGAI 2023 has accepted our paper titled - A knowledge rich task planning framework for human-robot collaboration
• 2023/06: A paper was accepted at RO-MAN 2023, titled - Models and Algorithms for Human-Aware Task Planning with Integrated Theory of Mind.
• 2023/05: A paper was accepted at PlanRob 2023 (the ICAPS workshop), titled - Anticipating False Beliefs and Planning Pertinent Reactions in Human-Aware Task Planning with Models of Theory of Mind.

Research

At present, I am working on the following topics:

• Intended towards cognitive robotic applications in human-robot interaction tasks, I am interested in planning with (higher order) false beliefs, which is challenging due to the need for belief revision.
• I am working on extending the Dynamic Epistemic Logic (DEL) framework in the context of multi-agent planning. This involves the ability to reason and plan with false beliefs and interacting concurrent physical actions.

• (Planning with Human in The Loop & Human-Aware Collaborative Planning) For a planning framework to effectively collaborate with humans in achieving a shared task, it needs to anticipate and emulate humans' possible decisions, actions, and reactions to estimate their cooperation. While humans are generally rational and consistent, autonomous systems cannot always predict their next moves or the evolution of their mental states during task execution. Therefore, planning under uncertainty about various factors—such as human reactions, behaviors, and mental models—is essential. In this direction, I am focused on:
  • Developing novel planning frameworks for human-aware planning in cognitive robotics, particularly for robots collaborating with humans, incorporating Theory of Mind and false beliefs.
  • Defining new metrics, designing innovative heuristics and online algorithms for real-time systems, and conducting user studies.

• Multi-Agent Planning (MAP) under uncertainty in the collaborative setting is a notoriously difficult problem. Often, they are modeled as Dec-POMDPs or its qualitative variant, QDec-POMDPs, a multi-agent contingent planning formalism. Solving Dec-POMDPs optimally is a combinatorially hard problem (NEXP-hard), and the qualitative model is also no easier in the worst-case but it scales better due to its non-probabilistic structure, at least when the actions are deterministic. The state-of-the-art QDec-POMDP algorithms, QDec-FP/S (presented at ICAPS'19 & AAAI'21, respectively), are based on factored planning (developed originally for classical planning) and scale much better than the recently proposed Iterative MAP algorithm. We focus on enhancing the QDec-FP/S planners, enriching the existing benchmarks, and modeling a more complex class of MAP problems under partial observability and uncertainty. We also focus on developing new techniques (e.g., factored planning-based approaches) for even better scalability and to push the state-of-the-art further.

Publications

Journal Publications

• Tomer Shahar, Shashank Shekhar, Dor Atzmon, Abdallah Saffidine, Brendan Juba, and Roni Stern, Safe Multi-Agent Pathfinding with Time Uncertainty. Journal of Artificial Intelligence, 2021.
• Shashank Shekhar and Ronen I. Brafman, Representing and planning with interacting actions and privacy. Artif. Intell. Journal, 2020.

Conference Publications

• Shashank Shekhar, Anthony Favier, and Rachid Alami, An Epistemic Human-Aware Task Planner which Anticipates Human Beliefs and Decisions. ICSR 2024.
• Shashank Shekhar, Anthony Favier, Rachid Alami, and Madalina Croitoru, A Knowledge Rich Task Planning Framework for Human-Robot Collaboration. SGAI 2023.
• Anthony Favier, Shashank Shekhar, and Rachid Alami, Models and Algorithms for Human-Aware Task Planning with Integrated Theory of Mind. RO-MAN 2023.
• Alexander Kovalchuk, Shashank Shekhar, and Ronen Brafman, Verifying Plans and Scripts for Robotics Tasks Using Performance Level Profiles. ICAPS 2021. (talk)
• Shashank Shekhar, Ronen I. Brafman, and Guy Shani, Improved Knowledge Modeling and Its use for Signaling in Multi-Agent Planning under Partial Observability. AAAI 2021.
• Shashank Shekhar, Ronen I. Brafman, and Guy Shani, A Factored Approach to Deterministic Contingent Multi-Agent Planning. ICAPS 2019. (talk (@21:40))
• Shashank Shekhar and Ronen I. Brafman, Representing and planning with interacting actions and privacy. ICAPS 2018. (talk)
• Shashank Shekhar and Deepak Khemani, Learning and tuning meta-heuristics in plan space planning. (arXiv 2016).
• Shashank Shekhar and Deepak Khemani, Improving Heuristics On-the-fly for Effective Search in Plan Space. KI 2015.
• Shashank Shekhar and Deepak Khemani, Extending and Tuning Heuristics for a Partial Order Causal Link Planner. MIKE 2015.

Workshop/Symposium Publications

• Shashank Shekhar, Anthony Favier, and Rachid Alami, Human-Aware Epistemic Task Planning for Human-Robot Collaboration. at HAXP 2024, the ICAPS workshop (paper).
• Anthony Favier, Shashank Shekhar, and Rachid Alami, Anticipating False Beliefs and Planning Pertinent Reactions in Human-Aware Task Planning with Models of Theory of Mind. PlanRob 2023, the ICAPS workshop (pdf).
• Anthony Favier, Shashank Shekhar, and Rachid Alami, Robust Planning for Human-Robot Joint Tasks with Explicit Reasoning on Human Mental State. AAAI Fall Symposium Series (FSS) 2022.
• Shashank Shekhar, Ronen I. Brafman, and Guy Shani, Signaling in Contingent Multi-Agent Planning. EpiP'20 Workshop, ICAPS 2020. (talk)
• Or Wertheim, Ronen I. Brafman, Shashank Shekhar, Tal Feiner, and Igal Pinsky, ROS-POMDP – A Platform for Robotics Planning using PLPs and RDDL in ROS. PlanRob'20 Workshop, ICAPS 2020.
• Tomer Shahar, Shashank Shekhar, Dor Atzmon, Abdallah Saffidine, Brendan Juba, and Roni Stern, Safe Multi-Agent Pathfinding with Time Uncertainty. WoMAPF'20 Workshop, IJCAI 2020.

Professional Activities and Talks

Activities

• Reviewer - International Journal of Social Robotics (SORO) 2024
• I am serving on the ECAI-2024 Program Committee
• Reviewer - the IEEE International Conference on Robotics and Automation (ICRA) 2024.
• Reviewer - the IEEE Robotics and Automation Letters journal (2022, 2023, 2024)
• Reviewer - the Springer Nature journal for CS (2022)
• I served on the Program Committee of AAAI 2021 and AAAI 2022.
• I co-organized the Workshop on Distributed and Multi-Agent Planning at ICAPS 2020. I also served on the Program Committee.

Talks

• [2019/10] - I delivered a talk on A Factored Approach to Contingent Multi-Agent Planning with Deterministic Actions at IIT Madras.
• [2018/09] - I delivered a talk on Representation and Planning with Interacting Actions and Privacy at IIT Madras, IBM IRL (Delhi), and IIT Mandi.

Miscellaneous

• Quote by Alexander Grothendieck (one of the greatest mathematicians of the 20th-century)

• A Stroke of Genius: Striving for Greatness in All You Do

• You and Your Research

• Serious Science

• Terry Tao's

• TechTalks

Personal