Tomi Silander

Papers

Total Citations

H-Index

About

Tomi Silander’s research lies at the intersection of robotics, reinforcement learning, and intelligent navigation, with a focus on enabling autonomous systems to operate robustly in dynamic, real-world environments. His most prominent contribution is the development of a deep reinforcement learning controller for the Solo12 quadruped robot, a work that has garnered 41 citations since 2023. This end-to-end learning-based approach allows the robot to acquire robust locomotion skills without explicit programming, addressing the challenge of maintaining stability and adaptability on complex terrain—a significant step toward practical legged robots. Silander has also advanced transfer learning in heterogeneous, dynamic settings, demonstrating how knowledge can be efficiently reused across varying conditions, a crucial capability for long-term autonomy. In crowd-aware navigation, his DiPCAN method (10 citations) innovatively distills privileged information to integrate human motion prediction with robot planning, overcoming the limitations of decoupled approaches. Through these works, Silander has shown a consistent ability to bridge the gap between theoretical machine learning and deployed robotic systems, making his research highly relevant for students and engineers aiming to build robots that move with both intelligence and grace.