Alejandro Carrasco
I am an MS student on the PhD track in Aeronautics and Astronautics at MIT AeroAstro, at the ARC Lab.
My research focuses on large language models, autonomous agents, and multi-embodiment robotics training and its space use-cases.
Publications
Research publications and academic contributions
GUIDE: Guided Updates for In-context Decision Evolution in LLM-Driven Spacecraft Operations
arXiv preprint arXiv:2603.27306, 2026
VibeOps: Intelligent Spacecraft Operations Co-Pilot
AIAA SCITECH 2026 Forum, 2376, 2026
Large language models as autonomous spacecraft operators in kerbal space program
Advances in Space Research, 2025
Recent trends are emerging in the use of Large Language Models (LLMs) as autonomous agents that take actions based on the content of the user text prompts. We intend to apply these concepts to the field of Control in spa…
Visual language models as operator agents in the space domain
AIAA SCITECH 2025 Forum, 1543, 2025
This paper explores the application of Vision-Language Models (VLMs) as operator agents in the space domain, focusing on both software and hardware operational paradigms. Building on advances in Large Language Models (LL…
BEAVR: Bimanual, multi-Embodiment, Accessible, Virtual Reality Teleoperation System for Robots
arXiv preprint arXiv:2508.09606, 2025
\textbf{BEAVR} is an open-source, bimanual, multi-embodiment Virtual Reality (VR) teleoperation system for robots, designed to unify real-time control, data recording, and policy learning across heterogeneous robotic pla…
Language models are spacecraft operators
arXiv preprint arXiv:2404.00413, 2024
Recent trends are emerging in the use of Large Language Models (LLMs) as autonomous agents that take actions based on the content of the user text prompts. We intend to apply these concepts to the field of Guidance, Navi…
Fine-tuning llms for autonomous spacecraft control: A case study using kerbal space program
arXiv preprint arXiv:2408.08676, 2024
Recent trends are emerging in the use of Large Language Models (LLMs) as autonomous agents that take actions based on the content of the user text prompt. This study explores the use of fine-tuned Large Language Models (…
Projects
Research and personal projects exploring artificial intelligence and robotics
BEAVR - Bimanual VR Teleoperation System
Bimanual, multi-Embodiment, Accessible VR Teleoperation for diverse robotic platforms
KSPDG 2026 Challenge - 2nd Place
2nd place solution for KSPDG 2026 with enhanced AI algorithms
KSPDG 2024 Challenge - 2nd Place
2nd place solution for KSPDG 2024 with autonomous spacecraft control
Academic & Professional Affiliations
Educational background and research positions that have shaped my academic journey
