An autopilot-preserving residual Q-learning supervisor with HJB-inspired finite-action risk filtering reduces mean RMS path-tracking error from 338.617 m to 44.809 m (86.77% reduction) in fixed simulation benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Autopilot-Preserving Residual Q-Learning with HJB-Inspired Finite-Action Risk Filtering for Fixed-Wing UAV Command Supervision
An autopilot-preserving residual Q-learning supervisor with HJB-inspired finite-action risk filtering reduces mean RMS path-tracking error from 338.617 m to 44.809 m (86.77% reduction) in fixed simulation benchmarks.