Aleksei Shpilman
Papers
2
Total Citations
11
H-Index
2
About
Aleksei Shpilman is a researcher at the intersection of robotics and artificial intelligence, with a primary focus on enabling autonomous systems to operate safely and efficiently in complex, dynamic environments. His key research areas include robot navigation through human crowds and the application of reinforcement learning for humanoid locomotion. Shpilman’s major contributions lie in addressing two fundamental challenges in robotics: safe social navigation and efficient movement learning. In his highly cited work, "A Comparative Evaluation of Machine Learning Methods for Robot Navigation Through Human Crowds" (8 citations), he systematically analyzed how AI systems can balance speed and safety when moving among people—a critical capability for service and assistive robots. His notable work, "Learning to Run with Potential-Based Reward Shaping and Demonstrations from Video Data" (3 citations), tackled the notoriously difficult problem of teaching humanoid robots to run from scratch. By integrating reward shaping with video-based demonstrations, Shpilman advanced the state of the art in sample-efficient learning for complex motor skills. His research has been recognized through participation in the NIPS 2017 "Learning to Run" competition, demonstrating his commitment to solving real-world robotics challenges through innovative machine learning techniques.
Research Focus
Key Achievements
Top Papers
- 1
- 2