Naman Shah

Naman Shah

PhD Student

Arizona State Univeristy


I am a 2nd year Ph.D. student working in Autonomous Agent and Intelligent Robots (AAIR) lab under the guidance of Dr. Siddharth Srivastava at Arizona State University, Tempe, USA.

My research interest lies in using abstraction to efficiently perform hierarchical planning to solve complex robotics tasks under uncertainty. I use concepts of hierarchical abstractions to solve different problems such as hierarchical planning and mobile manipulation in stochastic settings.



  • Artificial Intelligence
  • Robotics
  • Reinforcement Learning
  • Machine Learning


  • Ph.D. in Computer Science, 2019 - Present

    Arizona State University

  • M.S. in Computer Science, 2017 - 2019

    Arizona State University

  • B.Eng. in Computer Engineering, 2013 - 2017

    Gujarat Technological University



Research Intern

Palo Alto Research Center

May 2019 – Aug 2019 Palo Alto, California
Focused on using Qulitative Spatial Relations (QSRs) to autonomsly identify structures from the visual inputs and compute task plans to build those structures using physical robots.

Research Assistant


May 2018 – Present Arizona
Performing research on core AI concepts like sequential decision making under uncertainity using abstractions under the guidance of Dr. Siddharth Srivastava.

Teaching Assistant

Arizona State University

Jan 2016 – Dec 2016 Arizona

Assisted Dr. Siddarth Srivastava for a grauate level Aritificial Intelligene course (CSE 571).

Responsibilites include:

  • Developing projects.
  • Creating and evaluating homeworks.
  • Holding office hours to help students with the course material.


Learning and Using abstractions for Robot Planning

In this paper, we propose unified framework based on deep learning that learns sound abstractiosn for complex robot planning problems and uses it to efficiently perform hierarchical planning.

Anytime Task and Motion Policies for Stochastic Envrionments

In this paper, we provide and efficient abstraction based methods to compute task and motion policies for complex robotics task for stochastic environments.

Recent & Upcoming Talks

Learning and Using Abstractions for Robot Planning

The talk was given at PlanRob 2021. It talks about the framework we developed to learn and use abstractions hierarchies for efficient robot planning.

Anytime Task and Motion Policies for Stochastic Environments

In this talk, I have presented my paper of abstraction and hierarchical refinement based combined task and motion planning approach at ICRA 2020.