Context-aware Learned Mesh-based Simulation via Trajectory-Level Meta-Learning
This addresses the need for fast and accurate simulations in domains like robotics and manufacturing, though it is incremental as it builds on existing learned simulators.
The paper tackled the problem of simulating object deformations by introducing a trajectory-level meta-learning approach that uses Conditional Neural Processes and movement primitives to predict fast and accurate simulations from limited data, achieving higher simulation accuracy at a fraction of the runtime cost compared to state-of-the-art Graph Network Simulators.
Simulating object deformations is a critical challenge across many scientific domains, including robotics, manufacturing, and structural mechanics. Learned Graph Network Simulators (GNSs) offer a promising alternative to traditional mesh-based physics simulators. Their speed and inherent differentiability make them particularly well suited for applications that require fast and accurate simulations, such as robotic manipulation or manufacturing optimization. However, existing learned simulators typically rely on single-step observations, which limits their ability to exploit temporal context. Without this information, these models fail to infer, e.g., material properties. Further, they rely on auto-regressive rollouts, which quickly accumulate error for long trajectories. We instead frame mesh-based simulation as a trajectory-level meta-learning problem. Using Conditional Neural Processes, our method enables rapid adaptation to new simulation scenarios from limited initial data while capturing their latent simulation properties. We utilize movement primitives to directly predict fast, stable and accurate simulations from a single model call. The resulting approach, Movement-primitive Meta-MeshGraphNet (M3GN), provides higher simulation accuracy at a fraction of the runtime cost compared to state-of-the-art GNSs across several tasks.