cs.RONov 14, 2026

PSK: A Matrix-Free Single-Loop Method for K-Level Physics-Based Control

Authors: Zherong Pan

Organizations: Meta Reality Labs.

Abstract

Physics-based control is central to robot learning, but differentiating through implicit physics steps typically requires Hessian or Karush--Kuhn--Tucker (KKT) linear solves; we ask whether gradient steps suffice. Each simulation step minimizes an energy under many contact and collision constraints. Without constraints, we view control over KK steps as KK-level optimization with strongly convex lower levels, recast as one min--max problem. Our Penalized Single-loop KK-level method (PSK) uses only gradients and a projection, updates all levels in parallel, and reaches an εε-stationary control in O(ε−3)O(ε^{-3}) iterations, with a KK-independent exponent but a KK-dependent constant. Contact-rich constraints, however, typically violate a constraint qualification (CQ). We replace each constraint by a smooth wall that acts on a band of constant width. Under mild assumptions that need no CQ, every exact solution of the banded lower levels is then feasible and banded Fritz--John, and PSK keeps the O(ε−3)O(ε^{-3}) complexity. Without a CQ that is uniform in the band width, however, a shrinking band loses the KK-independent exponent: with width εε and fixed K≥2K\geq2, deterministic zero-respecting methods need Ω(ε−(K+3)/4)Ω(ε^{-(K+3)/4}) calls on a hard instance whose control dimension grows with 1/ε1/ε. We prove our assumptions for smoothed kinematic and dynamic multi-robot navigation among segment obstacles. In navigation experiments, PSK, tuned per case, reaches every goal with sixteen levels and, at equal time, reaches a lower loss than tuned unrolling in 17 of 18 cases, while implicit differentiation is lower in 10.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. ElastiQP: An Always-Feasible QP Solver for Constrained Robot Control

    Sep 16, 2026Daniel Morton, Jon Arrizabalaga, Zachary Manchester +1Robotic ControlConstrained Optimization

  2. LEAP: Gradient Flow Augmented Lagrangian Trajectory Optimization for Contact Constrained Robots

    Oct 14, 2026César E. Ramos Chuquiure, Ryan Tsai, Yutong Zhou +8Hypergradient OptimizationTrajectory Optimization

  3. Large-Scale Hierarchical Decision-Making in Robot Control via ADMM

    Nov 8, 2026Kai Pfeiffer, Jia Wang, Gordon Owusu Boateng +3Robotic OptimizationHierarchical Robot Control