A Single Multi-Task Deep Neural Network with Post-Processing for Object Detection with Reasoning and Robotic Grasp Detection
This work addresses the need for robots to efficiently grasp specific objects in complex, cluttered environments using a unified approach, though it appears incremental as it builds on existing multi-task methods.
The paper tackled the problem of combining robotic grasp detection, object detection, and relationship reasoning into a single multi-task deep neural network with post-processing, achieving state-of-the-art performance with accuracies of 98.6% and 74.2% on VMRD and Cornell datasets, and grasp success rates of 95.3% for single novel objects and 86.7% in cluttered scenes.
Recently, robotic grasp detection (GD) and object detection (OD) with reasoning have been investigated using deep neural networks (DNNs). There have been works to combine these multi-tasks using separate networks so that robots can deal with situations of grasping specific target objects in the cluttered, stacked, complex piles of novel objects from a single RGB-D camera. We propose a single multi-task DNN that yields the information on GD, OD and relationship reasoning among objects with a simple post-processing. Our proposed methods yielded state-of-the-art performance with the accuracy of 98.6% and 74.2% and the computation speed of 33 and 62 frame per second on VMRD and Cornell datasets, respectively. Our methods also yielded 95.3% grasp success rate for single novel object grasping with a 4-axis robot arm and 86.7% grasp success rate in cluttered novel objects with a Baxter robot.