RAM: Reachability Across Morphologies
This work provides a fast, differentiable surrogate for reachability that generalizes across morphologies, addressing a bottleneck in robot design and motion planning.
RAM introduces a morphology-conditioned implicit neural representation that predicts reachable workspace for arbitrary robot morphologies, achieving 86% F1-score at nanosecond inference, outperforming baselines by 14% while reducing inference time by three orders of magnitude, and accelerating morphology and trajectory optimization by one to two orders of magnitude.
Many stages of the robotic lifecycle, from morphology synthesis to operation, rely fundamentally on the reachable workspace. However, current methods for approximating workspaces are slow, imprecise, or tied to a single morphology. We introduce Reachability Across Morphologies (RAM): a morphology-conditioned, implicit neural representation that acts as a fast, differentiable surrogate for pose reachability, generalising to unseen morphologies while inherently accounting for self-collisions. To train RAM, we publish a large-scale dataset of $3\cdot10^{10}$ samples generated solely from forward kinematics. Experiments show that our model achieves an $ F_1$-score of $86\%$ at nanosecond inference, outperforming the baseline by $14\%$ while reducing inference time by three orders of magnitude. We further demonstrate speed-ups of one and two orders of magnitude for gradient-based morphology and trajectory optimisation, respectively. Website: https://timwalter.github.io/ram.