Papers
9
Total Citations
35
H-Index
4
About
Luis Pantoja-García is a robotics and control systems researcher whose work sits at the intersection of reinforcement learning, adaptive control, and intelligent robot manipulation. His research focuses primarily on developing novel actor-critic reinforcement learning architectures for robot motor control, with particular emphasis on constrained manipulators, continuum soft robots, and force-position control systems. Among his most notable contributions is the development of actor-critic learning frameworks that integrate sliding mode control and integral invariant manifolds, enabling robots to operate robustly under uncertain or rapidly changing dynamics without requiring persistent excitation — a longstanding challenge in adaptive control. His 2023 work on pneumatic-driven continuum soft robots, which applies closed-form Lagrangian dynamics within a reinforcement learning framework, represents a significant advance in model-compliant soft robotics control, earning 10 citations since publication. Pantoja-García's research consistently addresses the practical limitations of traditional model-based approaches, offering model-free neurocontrol alternatives that guarantee stability in continuous time. With publications spanning 2021 to 2025 and a growing citation record across multiple venues, his contributions are increasingly recognized by the robotics and intelligent control communities as meaningful steps toward adaptive, self-learning robotic systems capable of safe environmental interaction.
Research Focus
Key Achievements
Top Papers
- 1A Novel Actor—Critic Motor Reinforcement Learning for Continuum Soft Robots10 citations · 2023
- 2
- 3
- 4
- 5
- 6
- 7Stability Guaranteed Actor-Critic Learning for Robots in Continuous Time2 citations · 2023
- 8Adaptive actor-critic control of robots with integral invariant manifold2 citations · 2021
- 9