Papers
7
Total Citations
166
H-Index
5
About
Richard Linares is a prominent researcher at the intersection of aerospace engineering, autonomous systems, and machine learning, with particular expertise in spacecraft guidance, robotic autonomy, and intelligent decision-making for space applications. His most influential work centers on applying deep reinforcement learning and neural network architectures to solve complex guidance problems, most notably demonstrated in his highly cited 2020 paper on adaptive ZEM-ZEV feedback guidance for planetary landing, which has garnered over 100 citations and represents a landmark contribution to autonomous precision landing technology — a critical capability for future human and robotic solar system exploration. Linares has also made significant contributions to large-scale robotic systems, developing decentralized Hilbert map frameworks for gas sensing, environmental mapping, and information-driven path planning across distributed sensor networks. His more recent work pushes the frontier further, exploring Vision-Language Models as autonomous operator agents in space domains and developing constraint-informed learning methods to accelerate trajectory optimization for resource-limited spacecraft. Collectively, his research portfolio reflects a sustained commitment to making autonomous space systems faster, smarter, and more capable — bridging theoretical machine learning advances with real-world aerospace engineering challenges.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5Visual Language Models as Operator Agents in the Space Domain6 citations · 2025
- 6Constraint-Informed Learning for Warm-Starting Trajectory Optimization3 citations · 2025
- 7Constraint-Informed Learning for Warm Starting Trajectory Optimization2 citations · 2023