Real-Time Grasp Detection Using Convolutional Neural Networks

9 Dec 2014  ·  Joseph Redmon, Anelia Angelova ·

We present an accurate, real-time approach to robotic grasp detection based on convolutional neural networks. Our network performs single-stage regression to graspable bounding boxes without using standard sliding window or region proposal techniques. The model outperforms state-of-the-art approaches by 14 percentage points and runs at 13 frames per second on a GPU. Our network can simultaneously perform classification so that in a single step it recognizes the object and finds a good grasp rectangle. A modification to this model predicts multiple grasps per object by using a locally constrained prediction mechanism. The locally constrained model performs significantly better, especially on objects that can be grasped in a variety of ways.

PDF Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Robotic Grasping Cornell Grasp Dataset AlexNet, MultiGrasp 5 fold cross validation 88 # 5


No methods listed for this paper. Add relevant methods here