We present TerraPN, a novel method that learns the surface properties (traction, bumpiness, deformability, etc.) of complex outdoor terrains directly from robot-terrain interactions through self-supervised learning, and uses it for autonomous robot navigation. Our method uses RGB images of terrain surfaces and the robot's velocities as inputs, and the IMU vibrations and odometry errors experienced by the robot as labels for self-supervision. Our method computes a surface cost map that differentiates smooth, high-traction surfaces (low navigation costs) from bumpy, slippery, deformable surfaces (high navigation costs). We compute the cost map by non-uniformly sampling patches from the input RGB image by detecting boundaries between surfaces resulting in low inference times (47.27% lower) compared to uniform sampling and existing segmentation methods. We present a novel navigation algorithm that accounts for a surface's cost, computes cost-based acceleration limits for the robot, and dynamically feasible, collision-free trajectories. TerraPN's surface cost prediction can be trained in ~25 minutes for five different surfaces, compared to several hours for previous learning-based segmentation methods. In terms of navigation, our method outperforms previous works in terms of success rates (up to 35.84% higher), vibration cost of the trajectories (up to 21.52% lower), and slowing the robot on bumpy, deformable surfaces (up to 46.76% slower) in different scenarios.
翻译:我们提出TerraPN, 这是一种新颖的方法, 通过自我监督的学习, 直接从机器人-地形相互作用中学习复杂的户外地形的表面特性( 吸引、 沮丧、 变形等), 通过自我监督的学习, 并用于自动的机器人导航。 我们的方法使用 RGB 地形表面图像和机器人速度的RGB 图像作为输入, 以及 IMU 的振动和偏差, 作为自我监督的标签。 我们的方法计算了一个地表成本图, 将平滑、 高减色表面( 低导航成本) 与起伏的、 滑滑滑的、 可变形表面( 高导航成本) 区分开来。 我们计算成本图, 通过非统一的 RGB 图像的不统一采样补格, 与统一的采样和现有分解方法相比, 我们用新的导航算算出地表成本, 以成本为基础的加速度限制, 和动态的、无碰撞的轨迹的加速度( ) 35. TerPN's 的地平面成本预测, 以不同的方法, 25 以前的平流的平流法, 以前的平流的平流法 方法, 以前的平流的平流法, 以前的平流法的平流法, 以前的平流法 方法的平流法, 以前的平流的平流的平流法方法的平流法, 以前的平流法 。