Same Physics, Different Gradients: A State-of-the-Art Report on Differentiable Physics Simulation
Differentiable simulation propagates derivatives through a physics simulator, turning animation, system identification, control, and computational design into gradient-based optimization. Engines differ in the physics they model and, less visibly, in which mathematical object they differentiate. We separate two questions the literature conflates. The referent is which object the returned derivative belongs to: the finite computation that executed, the converged equation it approximates, or the continuous dynamics. The realization describes the organization of the backward pass: automatically generated differentiation, an equation-level adjoint solve, or a custom adjoint. The referent defines the target against which exactness is assessed; the implementation determines how accurately that target is approximated. Cost depends on the realization together with how the states needed by the backward pass are retained or recovered. Crossing the axes places every method and engine we classify in a cell, separates claims the literature merges, and shows that the apparent trade-off between exactness and memory follows from how methods have been built rather than from a constraint. A…
State-of-the-art report on differentiable physics simulation.
- arXiv
- 2611.12162
- Authors
- Lei Shu, Zizhou Huang, Yunuo Chen, Yifei Li, Tao Du and 13 more
- Categories
- cs.GR · cs.CV · cs.LG · cs.RO · math.NA