Spatial Attention Point Network for Deep-learning-based Robust Autonomous Robot Motion Generation
This addresses the need for data-efficient and robust autonomous robot motion generation in industrial applications, representing an incremental improvement over existing deep learning approaches.
The paper tackles the problem of deep learning-based robot motion generation requiring large amounts of training data for different object positions, proposing a method that uses spatial attention points to achieve robustness to object position changes with minimal data, demonstrated on picking and pick-and-place tasks with a robot arm.
Deep learning provides a powerful framework for automated acquisition of complex robotic motions. However, despite a certain degree of generalization, the need for vast amounts of training data depending on the work-object position is an obstacle to industrial applications. Therefore, a robot motion-generation model that can respond to a variety of work-object positions with a small amount of training data is necessary. In this paper, we propose a method robust to changes in object position by automatically extracting spatial attention points in the image for the robot task and generating motions on the basis of their positions. We demonstrate our method with an LBR iiwa 7R1400 robot arm on a picking task and a pick-and-place task at various positions in various situations. In each task, the spatial attention points are obtained for the work objects that are important to the task. Our method is robust to changes in object position. Further, it is robust to changes in background, lighting, and obstacles that are not important to the task because it only focuses on positions that are important to the task.