Kshitij Goel Robotics Researcher
Kshitij Goel

Kshitij Goel

Project Scientist, Robotics Institute, Carnegie Mellon University, USA

I create large-scale robot teams that operate reliably for days to months in environments too harsh or unpredictable for today's systems.

My research develops multi-robot systems that scale to thousands of agents and sustain long-duration autonomy in uncertain, contested, and adversarial settings, with applications from search and rescue to security, household assistance, and low-cost manufacturing.

I earned my Ph.D. in Robotics from Carnegie Mellon University, where I developed a memory- and communication-efficient multi-modal perception framework for teams of low-cost aerial robots, and deployed it in caves.

I am actively seeking faculty roles in robotics.

Research

Interactive, Affordable, and Resilient Multi-Robot Systems with Thousands of Robots

Several threads running through my research, from the core foundations of the subject to real-world applications in complex environments.

Distributed Decision-Making for Robot Teams in the Wild

Decentralized coordination and active search that keep robot teams effective in unknown, hazardous, and communication-denied environments.

Continuous World Models for Perception and Planning

Modeling the world as continuous probability distributions — compact generative maps that unify reconstruction, registration, occupancy, and planning queries.

Flying Fast through Places Never Seen Before

Planning, control, and learned policies that let aerial robots move at speed through cluttered environments they have no map of.

Learning Robot Control from Simulated Experience

Training control policies in high-throughput differentiable simulators — with privileged information available only at training time — and deploying them directly on real robots.

Shared Autonomy for Human-Robot Teams

Implicit coordination and wearable sensing that let humans and robots share one exploration task without explicit commands.
Selected publications

Recent work

Filter by research area. Author of this page in bold. Full list on Google Scholar.

Decentralized Uncertainty-Aware Active Search with a Team of Aerial Robots

Decentralized Uncertainty-Aware Active Search with a Team of Aerial Robots

Wennie Tabib, John Stecklein, Caleb McDowell, Kshitij Goel, Felix Jonathan, Abhishek Rathod, Meghan Kokoski, Edsel Burkholder, Brian Wallace, Luis Ernesto-Navarro-Serment, Nikhil Angad Bakshi, Tejus Gupta, Norman Papernick, David Guttendorf, Erik E. Kahn, Jessica Kasemer, Jesse Holdaway, and Jeff Schneider

ISER 2025
Open Toolkits

Open-source software for robotics

Toolkit

gira3d

An open-source, GPU-accelerated C++/CUDA toolkit for Gaussian Mixture Models in robot perception and autonomy — unified reconstruction, registration, occupancy modeling, and collision queries from a single compact representation.

Explore
Honors

Awards & recognition

2024

Alan J. Perlis SCS Graduate Student Teaching Award

Carnegie Mellon University

2024

Best Paper Award

IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)

2022

Best Paper Award

IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)

2022

King-Sun Fu Memorial Best Paper Award (Honorable Mention)

IEEE Transactions on Robotics

2021

National Science Foundation (NSF) Ph.D. Student Travel Award

International Symposium on Experimental Robotics (ISER)

2021

Uber Carnegie Mellon Presidential Fellowship

Carnegie Mellon University

Teaching & writing

Learning resources

Courses and materials for learning robotics.

Course · CMU

16-362: Mobile Robot Algorithms Laboratory

Designed and co-instructed this graduate level laboratory course focusing on the implementation of state estimation, mapping, planning, and control algorithms on physical mobile robots.

Open
News

Recent updates