253 citations · 277 across the 9 of their papers we have counts for
10 papers
H-SAUR: Hypothesize, Simulate, Act, Update, and Repeat for Understanding Object Articulations from Interactions
Kei Ota, Hsiao-Yu Tung, Kevin A. Smith +5
The world is filled with articulated objects that are difficult to determine how to use from vision alone, e.g., a door might open inwards or outwards. Humans handle these objects…
Object Memory Transformer for Object Goal Navigation
Rui Fukushima, Kei Ota, Asako Kanezaki +2
This paper presents a reinforcement learning method for object goal navigation (ObjNav) where an agent navigates in 3D indoor environments to reach a target object based on long-te…
CTRMs: Learning to Construct Cooperative Timed Roadmaps for Multi-agent Path Planning in Continuous Spaces
Keisuke Okumura, Ryo Yonetani, Mai Nishimura +1
Multi-agent path planning (MAPP) in continuous spaces is a challenging problem with significant practical importance. One promising approach is to first construct graphs approximat…
Training Larger Networks for Deep Reinforcement Learning
Kei Ota, Devesh K. Jha, Asako Kanezaki
The success of deep learning in the computer vision and natural language processing communities can be attributed to training of very deep neural networks with millions or billions…
Deep Reactive Planning in Dynamic Environments
Kei Ota, Devesh K. Jha, Tadashi Onishi +5
The main novelty of the proposed approach is that it allows a robot to learn an end-to-end policy which can adapt to changes in the environment during execution. While goal conditi…
Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering
Wonjik Kim, Asako Kanezaki, Masayuki Tanaka
The usage of convolutional neural networks (CNNs) for unsupervised image segmentation was investigated in this study. In the proposed approach, label prediction and network paramet…