A real-time FPGA-based reinforcement learning controller, trained on the fly with the optical reflection signal as reward, adapts laser power to surface roughness and reports reward gains of up to 23% over constant-power baselines.
Laser-based manufacturing concepts for efficient production of tailor welded sheet metals,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Reinforcement Learning on Reconfigurable Hardware: Overcoming Material Variability in Laser Material Processing
A real-time FPGA-based reinforcement learning controller, trained on the fly with the optical reflection signal as reward, adapts laser power to surface roughness and reports reward gains of up to 23% over constant-power baselines.