Igor Ansoategui
Papers
1
Total Citations
13
H-Index
1
About
Igor Ansoategui is a researcher in robotics and artificial intelligence, specializing in the safe and adaptive control of complex robotic systems. His work focuses on integrating reinforcement learning with safety mechanisms, particularly for linked-multicomponent robots—systems where multiple interconnected parts must coordinate precisely. In his most-cited paper, "Reinforcement Learning endowed with safe veto policies to learn the control of Linked-Multicomponent Robotic Systems" (2015, 13 citations), Ansoategui introduced a novel framework that allows robots to learn control policies through trial and error while a "veto" safety layer overrides dangerous actions. This contribution addresses a critical challenge in autonomous robotics: balancing exploration for learning with operational safety. By enabling robots to acquire complex behaviors without risking damage to themselves or their environment, Ansoategui's work has implications for industrial automation, assistive robotics, and autonomous vehicles. His research bridges the gap between theoretical reinforcement learning and practical deployment, offering a pathway toward more reliable and intelligent robotic systems. With his focus on safe learning, Ansoategui is advancing the frontier of autonomous control in high-stakes applications.
Research Focus
Key Achievements
Top Papers
- 1