Dennis Sinder
Papers
1
Total Citations
2
H-Index
1
About
Dennis Sinder’s research lies at the intersection of robotics, neural networks, and motor control, with a focus on how artificial systems can learn and plan complex physical actions. His most cited work, “Combining neural networks and optimization techniques for visuokinesthetic prediction and motor planning” (2008, 2 citations), introduces a novel method for robotic motor planning that integrates a forward model—implemented through multi-layer perceptrons—with differential evolution optimization. This approach enables a robot arm to iteratively predict and refine its movements in a block-pushing task, effectively bridging the gap between sensory feedback and motor execution. While his citation count is modest, Sinder’s contribution is notable for its early synthesis of neural network-based prediction and evolutionary optimization, a combination that anticipates later developments in model-predictive control and reinforcement learning for robotics. His work demonstrates a principled effort to endow robots with the ability to plan actions through internal simulation, a key challenge in autonomous manipulation. For students and researchers exploring visuomotor coordination or bio-inspired robotics, Sinder’s paper offers a clear, foundational example of how neural forward models can guide physical interaction.
Research Focus
Key Achievements
Top Papers
- 1