Papers
6
Total Citations
73
H-Index
4
About
Takashi Yoneyama is a leading researcher at the intersection of robotics and artificial intelligence, with a primary focus on advancing autonomous decision-making and control for humanoid and small-size soccer robots. His most significant contributions lie in applying Deep Reinforcement Learning (DRL) to solve complex, real-time control problems—most notably enabling humanoid robots to dribble and maintain balance during dynamic play. His 2022 paper on DRL for humanoid behaviors, with 30 citations, stands as a key reference in the field. Yoneyama has also made substantial impacts on the RoboCup Small Size League (SSL) and IEEE Very Small Size Soccer competitions. He has developed novel Model Predictive Control (MPC) frameworks that respect motor and non-slipping constraints (11 citations) and pioneered DRL-based strategies for autonomous ball interception and penalty kicks. His work on comparing sampling-based path planners like RRT has further optimized robot navigation in competitive settings. With a cumulative citation count exceeding 70, Yoneyama’s research is instrumental in pushing the boundaries of agile, intelligent robotics, directly contributing to the global advancement of autonomous soccer-playing agents.
Research Focus
Key Achievements
Top Papers
- 1Deep Reinforcement Learning for Humanoid Robot Behaviors30 citations · 2022
- 2Deep Reinforcement Learning for Humanoid Robot Dribbling17 citations · 2020
- 3
- 4Deep Reinforcement Learning Applied to IEEE Very Small Size Soccer Strategy10 citations · 2020
- 5Comparison of Sampling-based Path Planners for Robocup Small Size League4 citations · 2020
- 6