2018/03/04 by Dongwon Park, Park, Dongwon, Se Young Chun +1 · 32 citations
Computer Science · Engineering · Mathematics · #Advanced Neural Network Applications #Algorithm #Artificial intelligence #Artificial neural network #Computation #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Deep learning #Engineering #FOS: Computer and information sciences #GRASP #Hand Gesture Recognition Systems #Machine learning #Mathematics #Observability #Pattern recognition (psychology) #Robot #Robot Manipulation and Learning #Robotics (cs.RO) #Transformer #Voltage #cs.CV #cs.RO
paper · pdf · doi:10.48550/arxiv.1803.01356
published in arXiv (Cornell University) (Cornell University) · 6 pages, 10 figures, Under review
arxiv created 2018/03/04 · openalex publication_date 2018/03/04 · arxiv updated 2018/03/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Robotic grasp detection task is still challenging, particularly for novel objects. With the recent advance of deep learning, there have been several works on detecting robotic grasp using neural networks. Typically, regression based grasp detection methods have outperformed classification based detection methods in computation complexity with excellent accuracy. However, classification based robotic grasp detection still seems to have merits such as intermediate step observability and straightforward back propagation routine for end-to-end training. In this work, we propose a novel classification based robotic grasp detection method with multiple-stage spatial transformer networks (STN). Our proposed method was able to achieve state-of-the-art performance in accuracy with real- time computation. Additionally, unlike other regression based grasp detection methods, our proposed method allows partial observation for intermediate results such as grasp location and orientation for a number of grasp configuration candidates.