Hi! I am a PhD Candidate in the Robotics Institute at Carnegie Mellon University advised by Prof. Maxim Likhachev. I work on solving challenging non-prehensile manipulation planning problems in cluttered scenes where the robot may need to rearrange some objects in order to access others. My research relies on a key insight that abstracts this problem of manipulation among movable objects to multi-agent pathfinding.
Before my PhD, I obtained a Masters in Robotics degree, also from CMU RI. I worked with Prof. Martial Hebert on learning recovery maneuevers for perception system failures during monocular quadrotor flight in dense forests (thesis pdf, url).
You can email me at dhruvmsaxena [at] gmail [dot] com
.
News
- [Feb '23] One paper accepted to ICAPS 2023!
- [Jan '23] One paper accepted to ICRA 2023!
- [Dec '22] One paper accepted to the AAAI 2023 Workshop on Multi-Agent Path Finding!
- [May '22] Presented AMRA* at ICRA 2022. You can watch the presentation video here.
Publications
-
Planning for Manipulation Among Movable Objects: Deciding Which Objects Go Where, In What Order, And How
Dhruv Mauria Saxena, Maxim Likhachev
Accepted to the International Conference on Automated Planning and Scheduling (ICAPS), 2023
[pdf] -
Planning for Complex Non-prehensile Manipulation Among Movable Objects by Interleaving Multi-Agent Pathfinding and Physics-Based Simulation
Dhruv Mauria Saxena, Maxim Likhachev
Accepted to the IEEE International Conference on Robotics and Automation (ICRA), 2023
[pdf] -
Human-Scale Mobile Manipulation Using RoMan
Chad Kessens et al.
Field Robotics; Special Issue on Robotics Collaborative Technology Alliance (RCTA) Program
[pdf] -
AMRA*: Anytime Multi-Resolution Multi-Heuristic A*
Dhruv Mauria Saxena, Tushar Kusnur, Maxim Likhachev
IEEE International Conference on Robotics and Automation (ICRA), 2022
[bibtex] [pdf] -
Manipulation Planning Among Movable Obstacles Using Physics-Based Adaptive Motion Primitives
Dhruv Mauria Saxena, Muhammad Suhail Saleem, Maxim Likhachev
IEEE International Conference on Robotics and Automation (ICRA), 2021
[bibtex] [pdf] -
Search-based Planning for Active Sensing in Goal-Directed Coverage Tasks
Tushar Kusnur, Dhruv Mauria Saxena, Maxim Likhachev
IEEE International Conference on Robotics and Automation (ICRA), 2021
[bibtex] [pdf] -
Driving in Dense Traffic with Model-Free Reinforcement Learning
Dhruv Mauria Saxena, Sangjae Bae, Alireza Nakhaei, Kikuo Fujimura, Maxim Likhachev
IEEE International Conference on Robotics and Automation (ICRA), 2020
[bibtex] [pdf] -
Cooperation-Aware Lane Change Maneuver in Dense Traffic based on Model Predictive Control with Recurrent Neural Network
Sangjae Bae, Dhruv Mauria Saxena, Alireza Nakhaei, Chiho Choi, Kikuo Fujimura, Scott Moura
IEEE American Control Conference (ACC), 2020
[bibtex] [pdf] -
Bidirectional Heuristic Search for Motion Planning with an Extend Operator
Allen Cheng, Dhruv Mauria Saxena, Maxim Likhachev
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019
[bibtex] [pdf] -
A Planning Framework for Persistent, Multi-UAV Coverage with Global Deconfliction
Tushar Kusnur, Shohin Mukherjee, Dhruv Mauria Saxena, Tomoya Fukami, Takayuki Koyama, Oren Salzman, Maxim Likhachev
Springer Field and Service Robotics (FSR), 2019
[bibtex] [pdf] -
An experiment to evaluate robotic grasping of occluded objects
Arnon Hurwitz, Marshal Childers, Andrew Dornbush, Dhruv Mauria Saxena, Maxim Likhachev, Craig Lennon
SPIE Unmanned Systems Technology XX, 2018
[bibtex] [pdf] -
Learning Robust Failure Response for Autonomous Vision Based Flight
Dhruv Mauria Saxena, Vince Kurtz, Martial Hebert
IEEE International Conference on Robotics and Automation (ICRA), 2017
[bibtex] [pdf]
Workshop Papers
-
Imagine All Objects Are Robots: A Multi-Agent Pathfinding Perspective on Manipulation Among Movable Objects
Dhruv Mauria Saxena, Maxim Likhachev
Workshop on Multi-Agent Path Finding at 37th AAAI Conference on Artificial Intelligence (AAAI-23), 2023
[bibtex] [pdf] -
Learning Contextual Actions for Heuristic Search-Based Motion Planning
Dhruv Mauria Saxena, Maxim Likhachev
Fourth Machine Learning in Planning and Control of Robot Motion Workshop at IEEE International Conference on Robotics and Automation (ICRA), 2020
[bibtex] [pdf] -
Deep Flight: Autonomous Quadrotor Navigation with Deep Reinforcement Learning
Ratnesh Madaan, Rogerio Bonatti, Dhruv Mauria Saxena, Sebastian Scherer
Workshop on Learning Perception and Control for Autonomous Flight: Safety, Memory, and Efficiency at Robotics: Science and Systems (RSS), 2017
[bibtex] [pdf]