Neural Control: Adjoint Learning Through Equilibrium Constraints
For robotic manipulation of deformable objects with multi-stable behavior, this work provides a practical gradient-based control framework that avoids the computational cost of unrolling iterative solvers.
Neural Control introduces a memory-efficient adjoint method for computing gradients through implicit equilibrium systems, enabling trajectory-dependent control of multi-stable deformable objects. It achieves improved performance over gradient-free baselines (SPSA, CEM) in both simulation and physical robot experiments on deformable linear objects.
Many physical AI tasks are governed by implicit equilibrium: an agent actuates a subset of degrees of freedom (boundary DoFs), while the remaining free DoFs settle by minimizing a total potential energy. Even seemingly basic tasks such as bending a deformable linear object (DLO) to a target shape can exhibit strongly nonlinear behavior due to multi-stability: the same boundary conditions may yield multiple equilibrium shapes depending on the actuation trajectory. However, learning and control in such systems is brittle because the actuation-to-configuration map is defined only implicitly, and naive backpropagation through iterative equilibrium solvers is memory- and compute-intensive. We propose Neural Control, a boundary-control framework that computes trajectory-dependent, memory-efficient proxy gradients by differentiating equilibrium conditions via an adjoint formulation, avoiding unrolling of solver iterations. To improve robustness over long horizons, we integrate these sensitivities into a receding-horizon MPC scheme that repeatedly re-anchors optimization to realized equilibria and mitigates basin-switching in multi-stable regimes. We evaluate Neural Control in simulation and on physical robots manipulating DLOs, and show improved performance over gradient-free baselines such as SPSA and CEM.