Xinyang Geng

Xinyang Geng
Are you Xinyang Geng?

Claim your profile, edit publications, add additional information:

Contact Details

Xinyang Geng

Pubs By Year

Pub Categories

Computer Science - Learning (2)
Computer Science - Robotics (2)
Computer Science - Graphics (1)
Computer Science - Computer Vision and Pattern Recognition (1)
Computer Science - Artificial Intelligence (1)

Publications Authored By Xinyang Geng

Reinforcement learning is a powerful technique to train an agent to perform a task. However, an agent that is trained using reinforcement learning is only capable of achieving the single task that is specified via its reward function. Such an approach does not scale well to settings in which an agent needs to perform a diverse set of tasks, such as navigating to varying positions in a room or moving objects to varying locations. Read More

We propose a deep learning approach for user-guided image colorization. The system directly maps a grayscale image, along with sparse, local user "hints" to an output colorization with a Convolutional Neural Network (CNN). Rather than using hand-defined rules, the network propagates user edits by fusing low-level cues along with high-level semantic information, learned from large-scale data. Read More

Tensegrity robots, composed of rigid rods connected by elastic cables, have a number of unique properties that make them appealing for use as planetary exploration rovers. However, control of tensegrity robots remains a difficult problem due to their unusual structures and complex dynamics. In this work, we show how locomotion gaits can be learned automatically using a novel extension of mirror descent guided policy search (MDGPS) applied to periodic locomotion movements, and we demonstrate the effectiveness of our approach on tensegrity robot locomotion. Read More