I am a Senior Research Scientist at FieldAI, where I work on refining safe whole-body loco-manipulation policies for humanoid robots.
Research Overview: My research focuses on building autonomous systems that can safely operate in shared autonomy settings. I work on neurosymbolic approaches to decision-making under uncertainty, combining learned models with formal safety specifications and rule-based reasoning. My work spans behavior prediction, risk-aware planning, out-of-distribution robustness, and learning from failure data. Application domains include aerial autonomy, autonomous driving, and embodied AI.
During my PhD, I collaborated with NVIDIA Research (Dr. Marco Pavone) and Microsoft Research (Dr. Ashish Kapoor).
Education: I received my PhD in Robotics from the Robotics Institute at Carnegie Mellon University in May 2025, advised by Dr. Sebastian Scherer. I hold a Masters in Robotics from Carnegie Mellon University and a Masters and Bachelors in Aerospace Engineering from IIT Kanpur.
Beyond Research: I am passionate about aviation. I hold an FAA Private Pilot License and am the Founding President of The Flying Club at CMU.
Research in News
- AI-Powered Vision System Helps Drones Navigate Safely, CMU News, July 2025 [Link]
- Move over, autopilot: This AI can avoid other planes, Popular Science, Sept 2022 [Link]
- CMU's AI pilot lands in the news, Practical AI – Episode #189, Sept 2022 [Link]
- Drones bearing parcels deliver big carbon savings, Nature, Aug 2022 [Link]
- Researchers Develop AI Pilot for Navigating Crowded Airspace, Aviation Today, Aug 2022 [Link]
- AI Pilot Can Navigate Crowded Airspace, CMU School Of Computer Science, Aug 2022 [Link]
- Flying Club To Promote Aviation at CMU, The Piper, June 2021 [Link]
- The Flying Club Has Taken Off The Piper, October 2022 [Link]
- CMU-Africa Students Explore Aviation Collaborations with CMU Pittsburgh Club, The Piper, November 2023 [Link]
Experience
-
2025 - Present
Remote / USA
FieldAI
Senior Research Scientist
Safe whole-body loco-manipulation policies for humanoid robots
-
January 2024 - December 2024
Santa Clara, CA - USA
NVIDIA Research
Research Intern
-
Summer 2022
Bellevue, WA - USA
Microsoft Research
Research Intern
Education
-
2020 - 2025
PA - USA
Carnegie Mellon University
Robotics - Doctor of Philosophy (PhD)
-
2018 - 2020
PA - USA
Carnegie Mellon University
Robotics - Master of Science in Robotics (MSR)
-
2017 - 2018
Kanpur - India
Indian Institute of Technology Kanpur
Department of Aerospace Engineering - Masters in Technology (MTech)
-
2013 - 2017
Kanpur - India
Indian Institute of Technology Kanpur
Department of Aerospace Engineering - Bachelors in Technology (BTech)
Licenses
-
2022
Private Pilot License
Part 61
Federal Aviation Administration
-
2019
Remote Pilot License
Part 107
Federal Aviation Administration
Publications
For a full list, please visit Google Scholar.
-
GrndCtrl: Grounding World Models via Self-Supervised Reward AlignmentPreprint (ArXiv) 2025
-
Don't Run with Scissors: Pruning Breaks VLA Models but They Can Be RecoveredPreprint (ArXiv) 2025
-
Co-Me: Confidence-Guided Token Merging for Visual Geometric TransformersPreprint (ArXiv) 2025
-
AutoODD: Agentic Audits via Bayesian Red Teaming in Black-Box ModelsConference on Robot Learning [Workshop] (CoRL) 2025
-
The Case for Negative Data: From Crash Reports to Counterfactuals for Reasonable DrivingConference on Robot Learning [Workshop] (CoRL) 2025
-
Demonstrating ViSafe: Vision-enabled Safety for High-speed Detect and AvoidRobotics: Science and Systems (RSS) 2025
-
TartanAviation: Image, Speech, and ADS-B Trajectory Datasets for Terminal Airspace OperationsScientific Data (Nature) 2025
-
AmeliaTF: A Large Model and Dataset for Airport Surface Movement ForecastingAIAA AVIATION FORUM AND ASCEND 2024 [Best Paper Award]
-
RuleFuser: An Evidential Bayes Approach for Rule Injection in Imitation Learned Planners for Robustness under Distribution ShiftsInternational Symposium on Robotics Research (ISRR) 2024
-
Pegasus simulator: An isaac sim framework for multiple aerial vehicles simulation
International Conference on Unmanned Aircraft Systems (ICUAS) 2024
-
SoRTS: Learned Tree Search for Long Horizon Social Robot Navigation
IEEE Robotics and Automation Letters 2024
-
Toward General-Purpose Robots via Foundation Models: A Survey and Meta-AnalysisPreprint (ArXiv) 2023
-
FoundLoc: Vision-based Onboard Aerial Localization in the WildPreprint (ArXiv) 2023
-
Follow the rules: Online signal temporal logic tree search for guided imitation learning in stochastic domains
IEEE International Conference on Robotics and Automation (ICRA) 2023
-
AirTrack: Onboard deep learning framework for long-range aircraft detection and tracking
2023 IEEE International Conference on Robotics and Automation (ICRA) 2023
-
Challenges in Close-Proximity Safe and Seamless Operation of Manned and Unmanned Aircraft in Shared Airspace
International Conference on Robotics and Automation (ICRA) [Workshop] 2022
-
Quantifying the Effect of Weather on Advanced Air Mobility OperationsFindings 2022
-
Drone flight data reveal energy and greenhouse gas emissions savings for very small package deliveryPatterns 2022
-
Predicting like a pilot: Dataset and method to predict socially-aware aircraft trajectories in non-towered terminal airspace
International Conference on Robotics and Automation (ICRA) 2022
-
Adaptive Safety Margin Estimation for Safe Real-Time Replanning under Time-Varying Disturbance
2021
-
In-flight positional and energy use data set of a DJI Matrice 100 quadcopter for small package deliveryScientific Data 2021
-
Cvar-based flight energy risk assessment for multirotor uavs using a deep energy model
IEEE International Conference on Robotics and Automation (ICRA) 2021
-
Wind and the city: Utilizing uav-based in-situ measurements for estimating urban wind fields
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2020
-
Real-time motion planning of curvature continuous trajectories for urban UAV operations in wind2020 International Conference on Unmanned Aircraft Systems (ICUAS) 2020
-
Sequential Auto-Landing of Multiple UAVs using Control Constrained Path FollowingAIAA Scitech Forum 2019
-
Nested saturation based guidance law for unmanned aerial vehiclesJournal of Dynamic Systems, Measurement, and Control 2019
-
MARAAL: A low altitude long endurance solar powered UAV for surveillance and mapping applications
2018 23rd International Conference on Methods & Models in Automation & Robotics (MMAR) 2018
-
Convolutional neural network based sensors for mobile robot relocalization2018 23rd International Conference on Methods & Models in Automation & Robotics (MMAR) 2018
-
A Novel Fully Quaternion based Nonlinear Attitude and Position Controller
2018 AIAA Guidance, Navigation, and Control Conference 2018
-
A low-cost tilt-augmented quadrotor helicopter: Modeling and control
2018 international conference on unmanned aircraft systems (ICUAS) 2018
2025
2024
2023
2022
2021
2020
2019
2018
Theses
-
Rethinking the Safety Case for Risk-Aware Social Embodied IntelligenceCarnegie Mellon University, 2025
-
Wind-Field Estimation and Curvature Continuous Path Planning for Low Altitude Urban Aerial MobilityCarnegie Mellon University, 2020
-
A 3D Guidance Law for Path FollowingIndian Institute of Technology Kanpur, 2018
