An improved gesture recognition algorithm for human-robot collaboration

Abstract In this paper, an improved gesture recognition algorithm framework based on the improved SSD algorithm and OpenPose model for solving the robot’s mobile grasping problem in human-robot environment is proposed. Improved SSD algorithm by optimizing the front network of SSD algorithm and adjusting the prediction box is designed to identify the position of the hand rapidly, and to reduce the time for the training model. Testing experiments are perfomed for recognizing the hand’s key points information and eight designed gestures are compared with the traditional algorithm. The results show that the method can greatly improve the recognition distance of the original model under the dense environment, and also enhance the robustness and accuracy of the model, and have improved the ability of long-distance human-robot collaboration to a certain extent.