Search Results for author: Sho Sakaino

Found 7 papers, 0 papers with code

Loss Function Considering Dead Zone for Neural Networks

no code implementations1 Feb 2024 Koki Inami, Koki Yamane, Sho Sakaino

The proposed method enables to increase in the amount of motion data available for training and the accuracy of the inverse dynamics computation.

Imitation Learning Inputting Image Feature to Each Layer of Neural Network

no code implementations18 Jan 2024 Koki Yamane, Sho Sakaino, Toshiaki Tsuji

However, these approaches face a critical challenge when processing data from multiple modalities, inadvertently ignoring data with a lower correlation to the desired output, especially when using short sampling periods.

Imitation Learning

Force control of grinding process based on frequency analysis

no code implementations7 Dec 2021 Yuya Nogi, Sho Sakaino, Toshiaki Tsuji

In this paper, we propose an external force estimation method based on the Mel spectrogram of the force obtained from a force sensor.

Generation Drawing/Grinding Trajectoy Based on Hierarchical CVAE

no code implementations22 Nov 2021 Masahiro Aita, Keito Sugawara, Sho Sakaino, Toshiaki Tsuji

By combining two separately trained VAE models in a hierarchical structure, it is possible to generate trajectories with high reproducibility for both local and global features.

Imitation learning for variable speed motion generation over multiple actions

no code implementations11 Mar 2021 Yuki Saigusa, Ayumu Sasagawa, Sho Sakaino, Toshiaki Tsuji

In this paper, we propose a variable speed motion generation method for multiple motions.

Imitation Learning Robotics

Motion Generation Using Bilateral Control-Based Imitation Learning with Autoregressive Learning

no code implementations12 Nov 2020 Ayumu Sasagawa, Sho Sakaino, Toshiaki Tsuji

Owing to the structure and autoregressive learning of the proposed model, the proposed method can generate the desirable motion for successful tasks and have a high generalization ability for environmental changes.

Imitation Learning

Assembly robots with optimized control stiffness through reinforcement learning

no code implementations27 Feb 2020 Masahide Oikawa, Kyo Kutsuzawa, Sho Sakaino, Toshiaki Tsuji

In this study, we propose a methodology that uses reinforcement learning (RL) to achieve high performance in robots for the execution of assembly tasks that require precise contact with objects without causing damage.

reinforcement-learning Reinforcement Learning (RL) +1

Cannot find the paper you are looking for? You can Submit a new open access paper.