The paper investigates the numerical reliability of gradients in differentiable physics-based optimization for robotic material manipulation. Using two Material Point Method benchmarks, it identifies three key issues: GPU many-to-one sums that alter gradient signs, reduced reliability of finite-difference checks for long rollouts, and the impact of observation and loss definitions on optimization outcomes. The study recommends reproducible accumulation, finite-difference validation, and explicit objective reporting to improve robustness in robotic optimization.
arXiv:2607. 20653v1 Announce Type: cross Abstract: Predicting how deformable objects evolve under robotic manipulation is a longstanding challenge.
arXiv:2606. 27895v1 Announce Type: cross Abstract: Differentiable partial differential equation (PDE) solvers underpin solver-in-the-loop ML training, gradient-based optimal control, and inverse problems, yet the practical cost of obtaining correct, usable gradients from a given solver on a given problem is largely undocumented.
arXiv:2607. 19060v1 Announce Type: cross Abstract: Fast prediction of the response of adhesive soft viscoelastic contacts represents a current challenge in soft robotics and for gripping and manipulation tasks.
arXiv:2607. 04234v1 Announce Type: cross Abstract: Deformable object manipulation poses challenges beyond task completion: successful execution must also maintain safe physical interaction, holding the object stably without slip or drop while avoiding excessive deformation.
arXiv:2607. 04234v2 Announce Type: replace-cross Abstract: Deformable object manipulation poses challenges beyond task completion: successful execution must also maintain safe physical interaction, holding the object stably without slip or drop while avoiding excessive deformation.
arXiv:2608. 06650v1 Announce Type: cross Abstract: Reduced-order models based on Cosserat-rod theory are now well established, and modeling theory is no longer the primary bottleneck in soft-robot control.
arXiv:2606. 00383v1 Announce Type: cross Abstract: While Model Predictive Control (MPC) provides strong stability and robustness, it imposes a significant computational burden on real-time systems.
arXiv:2607. 09866v1 Announce Type: cross Abstract: Offline-to-online reinforcement learning is promising for generalizable robotic manipulation, yet its full-stack complexity obscures reproduction and diagnosis.
arXiv:2511. 06667v2 Announce Type: replace-cross Abstract: With the explosive growth of rigid-body simulators, policy learning in simulation has become the de facto standard for most rigid morphologies.
arXiv:2609.08800v1 Announce Type: cross Abstract: Three properties determine whether a differentiable simulator can drive gradient-based optimization through contact: simulation accuracy, gradient re...
arXiv:2607. 16921v1 Announce Type: cross Abstract: Non-prehensile manipulation enables flexible material handling with part carriers, but friction-based support makes high-speed motions failure-prone, while slower operation increases cycle time.
This paper introduces an energy-aware approach to robotic manipulation by defining a joint-space mechanical-work proxy based on joint torque and angular displacement. A differentiable energy predictor is trained to estimate this work from robot states and actions, enabling it to serve as a regularizer that fine‑tunes a pretrained manipulation policy. Applied to RVT‑2 on RLBench, the method reduces average mechanical work from 208.8 J to 204.4 J (a 2.1 % drop) while slightly improving task success from 86.2 % to 86.9 % across 12 manipulation tasks.