28 citations · 132 across the 19 of their papers we have counts for
5 papers · 1 filter
Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations
Akira Sakai, Taro Sunagawa, Spandan Madan +7
The training data distribution is often biased towards objects in certain orientations and illumination conditions. While humans have a remarkable capability of recognizing objects…
Annotation Cost Reduction of Stream-based Active Learning by Automated Weak Labeling using a Robot Arm
Kanata Suzuki, Taro Sunagawa, Tomotake Sasaki +1
Stream-based active learning (AL) is an efficient training data collection method, and it is used to reduce human annotation cost required in machine learning. However, it is diffi…
Embodying Pre-Trained Word Embeddings Through Robot Actions
Minori Toyoda, Kanata Suzuki, Hiroki Mori +2
We propose a promising neural network model with which to acquire a grounded representation of robot actions and the linguistic descriptions thereof. Properly responding to various…
In-air Knotting of Rope using Dual-Arm Robot based on Deep Learning
Kanata Suzuki, Momomi Kanamura, Yuki Suga +2
In this study, we report the successful execution of in-air knotting of rope using a dual-arm two-finger robot based on deep learning. Owing to its flexibility, the state of the ro…
Stable deep reinforcement learning method by predicting uncertainty in rewards as a subtask
Kanata Suzuki, Tetsuya Ogata
In recent years, a variety of tasks have been accomplished by deep reinforcement learning (DRL). However, when applying DRL to tasks in a real-world environment, designing an appro…