Sampo Kuutti
Papers
2
Total Citations
14
H-Index
2
About
Sampo Kuutti is a researcher at the forefront of deep learning for autonomous systems, with a focus on control policies and mobile robotics. His work addresses critical challenges in deploying neural networks for real-world tasks, particularly in validating their safety and robustness. Kuutti’s 2020 paper, "Training Adversarial Agents to Exploit Weaknesses in Deep Control Policies," has garnered 9 citations and stands out for its novel approach to stress-testing deep control systems—such as those used in robotic manipulation and autonomous vehicles—by generating adversarial agents that reveal hidden vulnerabilities. This contribution is vital for improving the reliability of AI-driven control. In 2021, he extended his research to unstructured environments with "Deep Learning Traversability Estimator for Mobile Robots," earning 5 citations for enabling robots to navigate challenging terrains more effectively. Kuutti’s work not only advances the theoretical understanding of deep learning in control but also has practical implications for safer, more adaptable autonomous systems. His research is a must-read for students and engineers interested in bridging the gap between deep learning theory and robust robotic deployment.
Research Focus
Key Achievements
Top Papers
- 1
- 2