快速预测机器人在不同形态下的可达空间，支持自动优化设计。
RAM: Reachability Across Morphologies
- 用隐式神经网络建模可达性，输入机器人形态即可输出可达区域。
- 在十亿级数据上训练，推理速度达纳秒级，准确率86%且比基线高14%。
- 适用于机器人形态与轨迹优化，显著提速，适合研发高效智能机器人系统。
机器人生命周期中的形态设计与操作等环节，都依赖于可达工作空间的准确估计。然而现有方法存在计算慢、精度低或仅适用于单一形态的问题。本文提出跨形态可达性（RAM）：一种形态条件化的隐式神经表示，可快速、可微分地预测姿态可达性，能泛化到未见形态并自动处理自碰撞问题。为训练该模型，我们发布了仅通过正向运动学生成的3×10¹⁰样本大规模数据集。实验表明，模型在纳秒级推理下达到86% F₁分数，优于基线14%，推理时间降低三个数量级。此外，在基于梯度的形态与轨迹优化中分别实现一到两个数量级的速度提升。官网：https://timwalter.github.io/ram。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。