María Gabriela Mendoza

Ph.D. Candidate · Mechanical Engineering · UC Berkeley
Multi-agent systems · Decentralized coordination · Humanitarian robotics

Email Google Scholar GitHub LinkedIn CV
Portrait of María Gabriela Mendoza
About

I am a Ph.D. candidate in Mechanical Engineering at UC Berkeley, advised by Prof. Shankar Sastry.

Before UC Berkeley, I worked as a Research Scientist at Lockheed Martin for 5 years, then I taught engineering at Cañada College. At Lockheed Martin, I performed aerothermal analysis and design for hypersonic vehicles earlier in my career, and towards the end, I conducted AI and robotics research. I hold a B.S. in Mechanical Engineering from the University of Southern California and an M.S. in Aeronautics and Astronautics from Purdue.

Research interests

My research develops algorithmic frameworks for multi-agent cyber-physical systems operating under uncertainty in complex, dynamic environments. I combine learning-based methods with control theory, optimization, game theory, and mechanism design. I am interested in the safety and alignment of multi-agent intelligent systems and their interactions, for problems requiring efficient, sustained coordination and incentive design among self-interested agents. Applications of my work include next-generation air mobility and multi-robot systems for disaster response.

I co-organize the Berkeley–Hopkins Seminar Series on Learning-Enabled Multi-Agent Systems (LEMAS) and its weekly study group.

News
  • UpcomingPresenting “Dynamic Multi-Robot Task Allocation under Uncertainty and Communication Constraints: A Game-Theoretic Approach” at IEEE CDC 2026 in Honolulu, Hawaiʻi.
  • UpcomingPresenting “Privacy-Preserving Mechanisms for Coordinating Airspace Usage in Advanced Air Mobility” at the INFORMS Annual Meeting.
  • Our poster “Resilient Decentralized Ergodic Coverage for Scalable Multi-Robot Systems in Unknown Time-Varying Environments” won the Runner-Up Best Poster Award at the IROS 2026 Humanitarian Assistance and Disaster Response (HADR) Workshop. Presented by Dr. Victoria Tuck. Poster (PDF)
  • Presented “Decentralized Ergodic Coverage Control in Unknown Time-Varying Environments” at the AAMAS 2026 Autonomous Robots and Multirobot Systems (ARMS) Workshop in Paphos, Cyprus (oral).
  • Presented “Hierarchical Generative Agents for Simulating Sequential Human Behavior” at the ICLR 2026 Workshop on Multi-Agent Learning in the Era of Generative AI in Rio de Janeiro, Brazil (poster).
  • Graduate Student Instructor for EE 290: Learning-Enabled Multi-Agent Systems at UC Berkeley.
  • Presented “Coordinated Autonomous Drones for Human-Centered Fire Evacuation in Partially Observable Urban Environments” at the IEEE Global Humanitarian Technology Conference (GHTC) in Boulder, Colorado.
Publications

* indicates equal contribution. For an updated list, see my Google Scholar.

Under review

Persistent LLM Orchestration of Heterogeneous Robot Teams via Partial Delegation to Multi-Agent Protocols
M. G. Mendoza*, V. M. Tuck*, Z. Ravichandran, S. Sastry, G. J. Pappas
Under review, 2026
arXiv video demo
Dynamic Auction Mechanisms in a Closed-Credit Economy: Sequential Slot Reallocation in Air Traffic Management
J. Kim, P.-Y. Su, M. G. Mendoza, V. M. Tuck, C. Maheshwari, S. S. Sastry
Under review, 2026
Resilient Decentralized Ergodic Coverage for Scalable Multi-Robot Systems in Unknown Time-Varying Environments
M. G. Mendoza, V. M. Tuck, C. Maheshwari, S. Sastry
journal under review, 2026
Runner-Up Best Poster Award, IROS 2026 HADR Workshop
paper poster

Journal articles

Privacy-Preserving Mechanisms for Coordinating Airspace Usage in Advanced Air Mobility
C. Maheshwari*, M. G. Mendoza*, V. M. Tuck*, P.-Y. Su, V. L. Qin, S. A. Seshia, H. Balakrishnan, S. Sastry
ACM Journal of Autonomous Transportation Systems, 2025
paper

Conference papers

Dynamic Multi-Robot Task Allocation under Uncertainty and Communication Constraints: A Game-Theoretic Approach
M. G. Mendoza*, P.-Y. Su*, B. L. Ferguson, S. S. Sastry
IEEE Conference on Decision and Control (CDC), 2026 (to appear)
arXiv
Coordinated Autonomous Drones for Human-Centered Fire Evacuation in Partially Observable Urban Environments
M. G. Mendoza, A. Kalanther, D. Bostwick, E. Stephan, C. Maheshwari, S. Sastry
IEEE Global Humanitarian Technology Conference (GHTC), 2025
paper
Resolving Conflicting Constraints in Multi-Agent Reinforcement Learning with Layered Safety
J. Choi, J. Aloor, J. Li, M. G. Mendoza, C. Tomlin, H. Balakrishnan
Robotics: Science and Systems (RSS), 2025
arXiv

Workshop papers

Hierarchical Generative Agents for Simulating Sequential Human Behavior
M. G. Mendoza*, L. Waldburger*, J. Lee, S. Sastry
ICLR Workshop on Multi-Agent Learning in the Era of Generative AI, 2026 (poster)
OpenReview
Decentralized Ergodic Coverage Control in Unknown Time-Varying Environments
M. G. Mendoza, V. Tuck, C. Maheshwari, S. Sastry
AAMAS Autonomous Robots and Multirobot Systems (ARMS) Workshop, 2026 (oral)
arXiv
Invited talks & presentations
Teaching
Professional experience
Leadership & mentoring