幻覚ロボット：部分的なレーザー計測から障害物距離を推定
Hallucinating robots: Inferring Obstacle Distances from Partial Laser Measurements
2Dレーザースキャナの生データのみから、ガラスやテーブルなど見えない障害物までの距離をオートエンコーダ型ニューラルネットで推定する手法を提案し、Care-O-bot 4で実時間動作を実証した。
著者: Jens Lundell, Francesco Verdoja, Ville Kyrki
分類: cs.RO, eess.SP, stat.ML
原文アブストラクト
Many mobile robots rely on 2D laser scanners for localization, mapping, and navigation. However, those sensors are unable to correctly provide distance to obstacles such as glass panels and tables whose actual occupancy is invisible at the height the sensor is measuring. In this work, instead of estimating the distance to obstacles from richer sensor readings such as 3D lasers or RGBD sensors, we present a method to estimate the distance directly from raw 2D laser data. To learn a mapping from raw 2D laser distances to obstacle distances we frame the problem as a learning task and train a neural network formed as an autoencoder. A novel configuration of network hyperparameters is proposed for the task at hand and is quantitatively validated on a test set. Finally, we qualitatively demonstrate in real time on a Care-O-bot 4 that the trained network can successfully infer obstacle distances from partial 2D laser readings.
