Papers
4
Total Citations
29
H-Index
3
About
Todd Jenkins is a researcher at the forefront of embodied artificial intelligence, focusing on bridging the gap between simulated algorithms and real-world robotic systems. His primary research areas include neuromorphic computing, reinforcement learning for robotics, and biologically-inspired navigation. Jenkins’s most notable contribution is his work on implementing associative memory in spiking neural network form on neuromorphic hardware, a key step toward creating autonomous agents that can learn and adapt with the energy efficiency of the biological brain. His work on transfer reinforcement learning, demonstrated through evaluations from the game "Sonic" to physical robotic platforms, directly addresses the critical challenge of deploying AI on embodied systems. With a total of 29 citations across his top papers, Jenkins is also recognized for his innovative educational approach, creating a research and development ecosystem that connects lab work with industry internships to train the next generation of autonomous systems engineers. His recent implementation of Simultaneous Localization and Mapping (SLAM) using Dynamic Field Theory showcases his commitment to reducing computational overhead in spatial awareness, making his work highly relevant for resource-constrained robotic applications.
Research Focus
Key Achievements
Top Papers
- 1
- 2Sonic to knuckles: Evaluations on transfer reinforcement learning8 citations · 2020
- 3
- 4