RGB-D Object Detection and Semantic Segmentation for Autonomous Manipulation in Clutter
This work addresses the problem of object perception in cluttered environments for autonomous robotics, representing an incremental improvement through method combination.
The paper tackles the challenge of perceiving a variety of objects in cluttered scenes for autonomous robotic manipulation by developing a deep-learning approach that combines object detection and semantic segmentation with RGB-D data and depth fusion. The result is reliable object perception, demonstrated by achieving second place in the Stowing task and third in the Picking task at the Amazon Picking Challenge 2016.
Autonomous robotic manipulation in clutter is challenging. A large variety of objects must be perceived in complex scenes, where they are partially occluded and embedded among many distractors, often in restricted spaces. To tackle these challenges, we developed a deep-learning approach that combines object detection and semantic segmentation. The manipulation scenes are captured with RGB-D cameras, for which we developed a depth fusion method. Employing pretrained features makes learning from small annotated robotic data sets possible. We evaluate our approach on two challenging data sets: one captured for the Amazon Picking Challenge 2016, where our team NimbRo came in second in the Stowing and third in the Picking task, and one captured in disaster-response scenarios. The experiments show that object detection and semantic segmentation complement each other and can be combined to yield reliable object perception.