cs.RONov 2, 2026

Self-Consistent Neural Control: Learning Trajectories for Implicit Equilibrium

Authors: Hengyi Zhou, Haobo Fang, Xiaonan Huang, Dezhong Tong, M. Khalid Jawed

Organizations: University of Michigan, Ann Arbor, MI, USA · Carnegie Mellon University, Pittsburgh, PA, USA · University of California, Los Angeles, CA, USA

Abstract

One big challenge in physical AI is interacting with systems whose states are defined by implicit equilibrium. Learning in these systems is difficult because their responses can be multistable, path-dependent, and sensitive over long horizons. Adjoint learning provides an efficient way to optimize trajectories without unrolling iterative equilibrium solvers, but its gradient relies on the frozen-tangent approximation, which neglects higher-order sensitivity terms and can become inaccurate when the local equilibrium varies rapidly. In this work, we introduce Self-Consistent Neural Control (SCNC), optimizing trajectories along which sensitivity variations are explicitly controlled. We derive a mathematical bound on the resulting gradient error and develop a practical finite-difference approximation. We validate the framework on deformable objects, which are representative of implicit equilibrium systems, ranging from simple quadratic energy models such as elastic rods to complex systems including thin-walled tubes, measuring tapes, and Slinky-like structures. Compared with the adjoint learning and the gradient-free iCEM baselines, SCNC achieves faster convergence and more stable optimization by reducing switching to undesirable equilibrium branches, doubling the stable optimization rate over adjoint learning 83.3% vs. 41.7% and reducing the average loss by more than 1.5 orders of magnitude on thin-walled tubes, where sensitivity variations are pronounced.

Figures & tables

Explore similar work

May 5, 2026

Neural Control: Adjoint Learning Through Equilibrium Constraints

Many physical AI tasks require sequential implicit computation: at each step, boundary controls are applied, and the resulting configuration is obtained by solving an equilibrium problem. This setting arises naturally in deformable object manipulation, where even bending a deformable linear object (DLO) to a target shape can be nonlinear and multistable: identical boundary conditions may produce different configurations depending on actuation history. Unlike explicit transition models, the control-to-configuration relation is implicit and history-dependent, making long-horizon learning and control brittle; backpropagating through iterative solves is also memory- and compute-intensive. We propose Neural Control, a boundary-control framework that propagates gradients through branch-dependent sequences of equilibrium solves rather than a single fixed point. Neural Control computes trajectory-dependent proxy gradients by differentiating equilibrium conditions with an adjoint formulation, avoiding solver unrolling while keeping forward rollouts on converged equilibria. Combined with receding-horizon continuation, Neural Control re-anchors optimization to realized equilibria and mitigates basin switching. We validate Neural Control on simulated and real DLO manipulation, compare against SPSA and iCEM, and demonstrate applicability to a learned DEQ-style implicit equilibrium model.
May 7, 2026

Learned Lyapunov Shielding for Adaptive Control

We augment the Slotine--Li adaptive controller for Euler--Lagrange systems with three learned components: a structured-quadratic Lyapunov function VψV_ψ whose positive-definiteness follows from a Cholesky parameterization, a residual Soft Actor--Critic policy that adds bounded torque corrections to the analytic baseline, and a physics-informed neural network that estimates unmodeled dynamics. A closed-form safety filter, derived from the single affine constraint V˙ψ+αVψ≤0\dot V_ψ+ αV_ψ\le 0, projects every policy output onto the safe set without requiring an online QP solver. We prove: global feasibility of the filter under a drift-decay condition on the control-degeneracy set; exponential stability under exact shielding, with a robust extension whose margin depends on the PINN approximation error; almost-sure convergence of the three-timescale policy--certificate--multiplier updates to a KKT point; and a PAC generalization bound for the certificate over compacts. On a 2-DOF manipulator with nonlinear friction and variable payload, the learned certificate accounts for most of the empirical gain: tracking error drops by 41% on nominal friction and 24% on aggressive friction at the centroid of the training distribution. A 7-DOF scalability study on a Franka Emika Panda confirms clean convergence of the full pipeline at industrial scale, identifies the conditions under which gains over exact model-based baselines should and should not be expected, and documents a warm-start pathology of the learned certificate that has practical implications for deployment.
Mar 8, 2026

Stability-Aligned Residual Adaptation for Rapid Recovery from Dynamics Shifts

Robotic systems deployed beyond controlled environments encounter abrupt and unobserved dynamics shifts that induce substantial transient performance loss, even when the nominal closed loop remains locally stabilizing. We formulate rapid inference-time recovery for physical AI as a constrained residual learning problem, in which an online correction added to a frozen reinforcement learning policy is regulated to minimize recovery time while remaining inside the robustness margin of the nominal controller. We specifically focus upon the regulation of residual's corrective authority relative to an already competent frozen policy. The learned residual produces bounded action-space corrections online, and a Stability Alignment Gate regulates this corrective authority through magnitude constraints, directional coherence, performance-conditioned regulation, and adaptive gain modulation. The method requires no environment resets, policy retraining, explicit system identification, or privileged shift information. Across mid-episode changes in actuation, mass, and contact conditions, it reduces recovery time relative to frozen SAC by up to 87% on Go1, 48% on Cassie, 30% on H1, and 20% on Scout in simulation, while preserving near-nominal steady-state performance. The framework is also characterized on two physical robots, a Trossen ViperX manipulator and an AgileX Scout Mini, cutting recovery time by 19.5% on hardware without modifying onboard controller or accessing shift information.