Embedded Files
日本語 / English
September 2019 - March 2021
September 2019 - March 2021
6D Pose Estimation Based on Sparse Modeling for Bin Picking
6D Pose Estimation Based on Sparse Modeling for Bin Picking
We propose a novel method for 6D pose estimation of randomly piled up objects based on sparse estimation. In this research, we convert the pose estimation problem to an optimization problem represented by Least Absolute Shrinkage and Selection Operator (LASSO). Since the proposed method estimates the pose by solving a convex optimization problem, the proposed method can avoid the local minimum problem and do not need a lot of tuning parameters and training data.
April 2021 -
April 2021 -
Nursing Care Teaching System Based on Mixed Reality for Effective Caregiver-Patient Interaction
Nursing Care Teaching System Based on Mixed Reality for Effective Caregiver-Patient Interaction
In the nursing care tasks such as assistance for transferring and walking, it is necessary to provide appropriate nursing care movements depending on factors such as the patient's pose and the degree of disability. However, for novice caregivers to practice and learn appropriate nursing care, they must practice for a long time under the guidance of skilled caregivers. To solve this problem, we propose a novel framework for a system that teaches appropriate nursing care actions according to the current situation. The realization of such a teaching system requires technology to recognize the current situation and effectively teach the interaction between the caregiver and the patient. In this research, we propose a system that integrates depth camera-based pose estimation of the patient and Mixed Reality technology to present the target motion of the patient to a caregiver.
Page updated
Google Sites
Report abuse