深層ネットワークによる中間知覚を介した障害物回避
Obstacle Avoidance through Deep Networks based Intermediate Perception
単眼画像から深度と法線を中間的に予測し、その情報を用いて軌道を推定することで、直接予測より20%高い精度で障害物回避を実現した。
著者: Shichao Yang, Sandeep Konam, Chen Ma, Stephanie Rosenthal, Manuela Veloso, Sebastian Scherer
分類: cs.RO, cs.CV
原文アブストラクト
Obstacle avoidance from monocular images is a challenging problem for robots. Though multi-view structure-from-motion could build 3D maps, it is not robust in textureless environments. Some learning based methods exploit human demonstration to predict a steering command directly from a single image. However, this method is usually biased towards certain tasks or demonstration scenarios and also biased by human understanding. In this paper, we propose a new method to predict a trajectory from images. We train our system on more diverse NYUv2 dataset. The ground truth trajectory is computed from the designed cost functions automatically. The Convolutional Neural Network perception is divided into two stages: first, predict depth map and surface normal from RGB images, which are two important geometric properties related to 3D obstacle representation. Second, predict the trajectory from the depth and normal. Results show that our intermediate perception increases the accuracy by 20% than the direct prediction. Our model generalizes well to other public indoor datasets and is also demonstrated for robot flights in simulation and experiments.
