CarePLUS is shown at CES 2020. We developed an AI-empowered system which integrating several modules including human pose estimation, object tracking and activity recognition.
Winner of the The Robotic Vision Probabilistic Object Detection Challenge Champion at CVPR 2019.
Implement Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects and train on self-created synthetic bottle dataset.
We developed a multimodal smart home system, which uses an end-to-end trainable hierarchical Recurrent Neural Network (RNN) to continuously learn and anticipate users’ intention without manual data labeling.