Papers
3
Total Citations
93
H-Index
3
About
Tim Seyde’s research bridges the gap between classical robotics and modern reinforcement learning, with a focus on humanoid locomotion, posture control, and continuous control policies. His most-cited work, “Good Posture, Good Balance” (52 citations), provides a rigorous experimental comparison between bioinspired and model-based approaches for humanoid posture control, offering key insights into balancing strategies. He advanced bipedal walking in “Inclusion of Angular Momentum During Planning for Capture Point Based Walking” (26 citations), where he developed a reference trajectory generator that accounts for centroidal angular momentum—critical for stable high-speed locomotion. In a more recent and conceptually provocative paper, “Is Bang-Bang Control All You Need?” (15 citations), Seyde explores the surprising effectiveness of Bernoulli policies in continuous control tasks, challenging conventional RL assumptions by showing that agents often favor extreme actions. This work draws theoretical connections that could simplify action representation in robotics. Across his publications, Seyde demonstrates a talent for combining theoretical rigor with practical experimentation, making contributions that inform both roboticists and reinforcement learning researchers. His work is particularly notable for its interdisciplinary approach, drawing from biomechanics, control theory, and machine learning to address fundamental challenges in robot motion and decision-making.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3