RIKEN Center for Advanced Intelligence Project 3D Environmental Information Understanding Team
Team Director: Asako Kanezaki (Ph.D.)
Research Summary
In recent years, AI for embodied agents such as robots has been actively studied. To understand and act in the real world, agents must comprehend 3D environmental information. Our team tackles recognition tasks such as object recognition, mapping, and graph network construction using machine learning. We also focus on Embodied AI research, including robot navigation and manipulation based on this information. We develop algorithms such as supervised learning, reinforcement learning, and inverse reinforcement learning to address diverse real-world information processing challenges.
Main Research Fields
- Informatics
Related Research Fields
- Engineering
- Intelligent Robotics
- Intelligent Machine Learning and Mechanical Systems
Keywords
- 3D Object Recognition
- Semantic Environmental Maps
- Visual Navigation
- Robot Manipulation
- Embodied AI
Selected Publications
Papers with an asterisk(*) are based on research conducted outside of RIKEN.
- 1.
*Haruyuki Nakagawa and Asako Kanezaki
"Multi-Agent Visual Coordination using Optical Wireless Communication"
IEEE Robotics and Automation Letters (RA-L), vol. 8, no. 11, pp. 7857-7864, 2023 - 2.
*Asako Kanezaki, Yasuyuki Matsushita, and Yoshifumi Nishida
"RotationNet for Joint Object Categorization and Unsupervised Pose Estimation from Multi-view Images"
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Vol.43, Issue 1, pp. 269-283, 2021 - 3.
*Asako Kanezaki, Wonjik Kim, and Masayuki Tanaka
"Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering"
IEEE Transactions on Image Processing, pp. 8055-8068, 2020 - 4.
*Asako Kanezaki, Jirou Nitta, and Yoko Sasaki
"GOSELO: Goal-Directed Obstacle and Self-Location Map for Robot Navigation using Reactive Neural Networks"
IEEE Robotics and Automation Letters (RA-L), Vol.3, Issue 2, pp. 696-703, 2018 - 5.
*Yuchen Che, Ryo Furukawa, and Asako Kanezaki
"OP-Align: Object-level and Part-level Alignment for Self-supervised Category-level Articulated Object Pose Estimation"
The 18th European Conference on Computer Vision (ECCV), oral, 2024 - 6.
*Haruyuki Nakagawa, Yoshitaka Miyatani, and Asako Kanezaki
"Linking Vision and Multi-Agent Communication through Visible Light Communication using Event Cameras"
Int. Joint Conf. on Autonomous Agents & Multiagent Systems (AAMAS), 2024 - 7.
*Haru Kondoh and Asako Kanezaki
"Multi-goal Audio-visual Navigation using Sound Direction Map"
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023 - 8.
*Hao Zheng, Runqi Wang, Jianzhuang Liu, and Asako Kanezaki
"Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classification"
International Conference on Learning Representations (ICLR), 2023 - 9.
*Kei Ota, Hsiao-Yu Tung, Kevin A. Smith, Anoop Cherian, Tim K. Marks, Alan Sullivan, Asako Kanezaki, and Joshua B. Tenenbaum
H-SAUR: Hypothesize, Simulate, Act, Update, and Repeat for Understanding Object Articulations from Interactions
IEEE International Conference on Robotics and Automation (ICRA), 2023 - 10.
*Asako Kanezaki, Yasuyuki Matsushita, and Yoshifumi Nishida
RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5010-5019, 2018
Related Links
Lab Members
Principal investigator
- Asako Kanezaki
- Team Director
Contact Information
West Bldg 8E, Room E502,
W8-64, 2-12-1 Ookayama,
Meguro-ku, Tokyo,
152-8550, Japan
Email: asako.kanezaki@riken.jp