A neural BRAT framework trained with curriculum-driven MPC supervision approximates HJ reach-avoid value functions and deploys them via gradient and augmented-MPC controllers, outperforming baselines on 6D and 13D docking tasks.
Artificial neural networks for solving ordinary and partial differential equations
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
-
Neural Backward Reach-Avoid Tubes with MPC Supervision for High-Dimensional Systems: An Application to Safe Spacecraft Docking
A neural BRAT framework trained with curriculum-driven MPC supervision approximates HJ reach-avoid value functions and deploys them via gradient and augmented-MPC controllers, outperforming baselines on 6D and 13D docking tasks.