Welcome to my Research page! I’m currently a 3rd Year Ph.D. student with the LIS Group within MIT CSAIL. I’m officially advised by Leslie Kaelbling and Tomás Lozano-Pérez, though I frequently collaborate with Dylan Hadfield-Menell, Josh Tenenbaum, and many other wonderful people within CSAIL’s Embodied Intelligence Initiative. I also spend time at the Boston Dynamics AI Institute where I primarily work with Jennifer Barry. I’m extremely grateful for support from the NSF Graduate Research Fellowship.

Resume | CV | Google Scholar | Bio | GitHub | Twitter

Research Areas

I’m broadly interested in enabling robots to operate robustly in long-horizon, multi-task settings so that they can accomplish tasks like multi-object manipulation, cooking, or even performing household chores. To this end, I’m interested in combining classical AI planning and reasoning approaches with modern machine learning techniques. My research draws on ideas from reinforcement learning, task and motion planning (TAMP), deep learning, and neurosymbolic AI.

Publications

Conference Papers

Preference-Conditioned Language-Guided Abstractions

Andi Peng, Andreea Bobu, Belinda Z. Li, Theodore R. Sumers, Ilia Sucholotsky, Nishanth Kumar, Thomas L. Griffiths, Julie A. Shah.
Human-Robot Interaction (HRI), 2024.
paper

Introduces a method for enabling a robot to learn state abstractions for solving tasks that are tailored to a human's specific preferences.

Learning Efficient Abstract Planning Models that Choose What to Predict

Nishanth Kumar*, Willie McClinton*, Rohan Chitnis, Tom Silver, Tomás Lozano-Pérez, Leslie Pack Kaelbling.
Conference on Robot Learning (CoRL), 2023. Also appeared at RSS Workshop on Learning for Task and Motion Planning

(Best Paper Award)

.
website / OpenReview

Shows that existing methods of learning operators for TAMP/bilevel planning struggle in complex environments with large numbers of objects. Introduces a novel operator learning approach based on local search that encourages operators to only model changes *necessary* for high-level search.
[* denotes equal contribution]

Predicate Invention for Bilevel Planning

Tom Silver*, Rohan Chitnis*, Nishanth Kumar, Willie McClinton, Tomás Lozano-Pérez, Leslie Pack Kaelbling, Joshua Tenenbaum
AAAI, 2023

(Oral)

. Also appeared at RLDM, 2022

(Spotlight Talk)

.
arxiv / code

Introduces a new, program-synthesis inspired approach for learning neuro-symbolic relational state and action abstractions (predicates and operators) from demonstrations. The abstractions are explicitly optimized for effective and efficient bilevel planning.
[* denotes equal contribution]

Just Label What You Need: Fine-Grained Active Selection for Perception and Prediction through Partially Labeled Scenes

Nishanth Kumar*, Sean Segal*, Sergio Casas, Mengye Ren, Jingkang Wang, Raquel Urtasun
Conference on Robot Learning (CoRL), 2021.
OpenReview / arXiv / poster

Introduces fine-grained active selection via partial labeling for efficient labeling for perception and prediction.
[* denotes equal contribution. Work was done while at Uber ATG]

Building Plannable Representations with Mixed Reality

Eric Rosen, Nishanth Kumar, Nakul Gopalan, Daniel Ullman, George Konidaris, Stefanie Tellex
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020.
paper / video

Introduces Action-Oriented Semantic Maps (AOSM's) and a system to specify these with mixed reality, which robots can use to perform a wide-variety of household tasks.

Multi-Object Search using Object-Oriented POMDPs

Arthur Wandzel, Yoonseon Oh, Michael Fishman, Nishanth Kumar, Lawson L.S Wong, Stefanie Tellex
IEEE International Conference on Robotics and Automation (ICRA), 2019.
paper / video

Introduces the Object-Oriented Partially Observable Monte-Carlo Planning (OO-POMCP) algorithm for efficiently solving Object-Oriented Partially Observable Markov Decision Processes (OO-POMDPs) and shows how this can enable a robot to efficiently find multiple objects in a home environment.

Workshop Papers and Extended Abstracts

Task Scoping: Generating Task-Specific Simplifications of Open-Scope Planning Problems

Michael Fishman*, Nishanth Kumar*, Cameron Allen, Natasha Danas, Michael Littman, Stefanie Tellex, George Konidaris
IJCAI Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning, 2023.
paper

Introduces a method for how large classical planning problems can be efficiently pruned to exclude states and actions that are irrelevant to a particular goal so that agents can solve very large, 'open-scope' domains that are capable of supporting multiple goals.
[* denotes equal contribution]

PDDL Planning with Pretrained Large Language Models

Tom Silver*, Varun Hariprasad*, Reece Shuttleworth*, Nishanth Kumar, Tomás Lozano-Pérez, Leslie Pack Kaelbling,
NeurIPS FMDM Workshop, 2022.
OpenReview

Investigates the extent to which pretrained language models can solve PDDL planning problems on their own, or be used to guide a planner.
[* denotes equal contribution]

Task Scoping for Efficient Planning in Open Worlds

Nishanth Kumar*, Michael Fishman*, Natasha Danas, Michael Littman, Stefanie Tellex, George Konidaris
AAAI Conference on Artificial Intelligence, Student Workshop, 2020.
paper

Introduces high-level ideas for how large Markov Decision Processes (MPDs) might be efficiently pruned to include only states and actions relevant to a particular reward function. This paper is subsumed by our arxiv preprint on task scoping.
[* denotes equal contribution]

Knowledge Acquisition for Robots through Mixed Reality Head-Mounted Displays

Nishanth Kumar*, Eric Rosen*, Stefanie Tellex
The Second International Workshop on Virtual, Augmented and Mixed Reality for Human Robot Interaction, 2019.
paper

Sketches high level ideas for how a mixed reality system might enable users to specify information for a robot to perform pick-place and other household tasks. This work is subsumed by our AOSM work.
[* denotes equal contribution]

Preprints

Practice Makes Perfect: Planning to Learn Skill Parameter Policies

Nishanth Kumar*, Tom Silver*, Willie McClinton, Linfeng Zhao, Stephen Proulx, Tomás Lozano-Pérez, Leslie Pack Kaelbling, Jennifer Barry.
arxiv, 2024.
website / arxiv

Introduces a new framework for robots to improve performance by efficiently learning online during deployment. Demonstrates that the proposed approach and framework can be implemented on a real robot and help significantly improve its ability to solve complex, long-horizon tasks in the real-world with no human intervention or environment resets!
[* denotes equal contribution]

PGMax: Factor Graphs for Discrete Probabilistic Graphical Models and Loopy Belief Propagation in JAX

Guangyao Zhou*, Nishanth Kumar*, Miguel Lázaro-Gredilla, Shrinu Kushagra, Dileep George
arXiv, 2022.
arxiv / blog post / code

Introduces a new JAX-based framework that aims to make it easy to build and run inference on probabilistic graphical models (PGM's).
[* denotes equal contribution]

Learning Deep Parameterized Skills from Demonstration for Re-targetable Visuomotor Control

Nishanth Kumar*, Jonathan Chang*, Sean Hastings, Aaron Gokaslan, Diego Romeres, Devesh Jha, Daniel Nikovski, George Konidaris, Stefanie Tellex
arXiv, 2020.
arxiv

Shows how the generalization capabilities of Behavior Cloning (BC) can be improved by learning a policy parameterized by some input that enables the agent to distinguish different goals (e.g. different buttons to press in a grid). Includes several exhaustive experiments in simulation and on two different robots.
[* denotes equal contribution. Work was done in collaboration with Mitsubishi Electric Research Laboratories]

Industry Experience and Research Collaborations

Invited Talks

Mentorship

I love mentoring students and junior researchers with interests related to my own; I find that this not only leads to cool new papers and ideas, but also helps me become a better researcher and teacher!

Mentees

Current

  • Annie Feng (Fall 2023 - Present): working on using Large Language Models (LLM’s) for model-based learning and exploration.
  • Alicia Li (Spring 2024 - Present): working at the intersection of planning and deep RL for robotics tasks.
  • Jing Cao (mentored jointly with Aidan Curtis)(Spring 2024 - Present): working on combining different Foundation Models together to solve long-horizon robotics tasks via planning.

Past

  • Kathryn Le (mentored jointly with Willie McClinton) (IAP 2023 and Spring 2023): worked on using Task and Motion Planning to solve tasks from the BEHAVIOR benchmark; currently continuing undergrad at MIT.
  • Anirudh Valiveru (IAP 2023): worked on leveraging Large Language Models (LLM’s) for efficient exploration in relational environments; currently continuing undergrad at MIT and pursuing research with a different group.
  • Varun Hariprasad (mentored jointly with Tom Silver)(Summer 2022): high-school student at MIT via the RSI program; currently an undergrad at MIT.

Awards

Teaching

Selected Press Coverage