Ben Jeppesen

Intel (United Kingdom)

Papers

2

Total Citations

42

H-Index

2

About

Ben Jeppesen’s research sits at the intersection of hardware acceleration and intelligent robotics, with a focus on making real-time control systems faster, safer, and more adaptive. His most influential work, “Towards Hardware Accelerated Reinforcement Learning for Application-Specific Robotic Control” (2018, 32 citations), pioneers the use of FPGAs to speed up reinforcement learning for robotic decision-making—enabling agents to learn optimal policies in dynamic environments without relying on bulky, power-hungry processors. This contribution is critical for deploying RL in embedded, low-latency robotic systems. Jeppesen also advanced collaborative robotics in “An FPGA-based controller for collaborative robotics” (2017, 10 citations), addressing the need for sophisticated motion control in human-safe, low-force robots. By offloading control algorithms to reconfigurable hardware, his work helps collaborative robots react quickly and efficiently in shared workspaces. Though his citation counts reflect a focused, emerging career, Jeppesen’s contributions are foundational for researchers aiming to merge machine learning with hardware-level control. His work is especially relevant for students and engineers developing application-specific robots where speed, power, and adaptability are paramount.

Research Focus

Key Achievements

2
H-Index
2
Papers
42
Total Citations
21
Avg Citations/Paper
🏆 Most Cited Paper
Towards Hardware Accelerated Reinforcement Learning for Application-Specific Robotic Control
32 citations · 2018
📈 Most Prolific Year: 2018 (1 Papers)
🤝 Key Collaborators: 9
🏛 Institutions: Intel (United Kingdom)

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago