论文标题
神经辐射场（NERF）中无障碍梯度和反应性计划（NERF）
Sampling-free obstacle gradients and reactive planning in Neural Radiance Fields (NeRF)
论文作者
论文摘要
这项工作研究了神经隐式表示的使用，特别是神经辐射场（NERF），用于几何查询和运动计划。我们表明，通过将半径中的占用率添加到预训练的NERF中，我们正在有效地学习与欧几里得签名距离场（ESDF）的近似值。使用增强网络的向后区分，我们获得了一个基于Riemannian运动策略（RMP）框架的障碍梯度，该梯度梯度集成到障碍避免政策中。因此，我们的发现允许在隐式表示中进行非常快速的无抽样避免避免障碍计划。
This work investigates the use of Neural implicit representations, specifically Neural Radiance Fields (NeRF), for geometrical queries and motion planning. We show that by adding the capacity to infer occupancy in a radius to a pre-trained NeRF, we are effectively learning an approximation to a Euclidean Signed Distance Field (ESDF). Using backward differentiation of the augmented network, we obtain an obstacle gradient that is integrated into an obstacle avoidance policy based on the Riemannian Motion Policies (RMP) framework. Thus, our findings allow for very fast sampling-free obstacle avoidance planning in the implicit representation.
