Tatsuya Harada
Tatsuya Harada studies AI that joins perception with action, combining visual, language and physical information to understand the world. Harada coauthored Intend to Move, a dataset for intention- and scene-aware human-motion prediction. I2-NeRF studied neural radiance fields under physically grounded interactions with surrounding media. Both projects connected learned representations with physical context. Harada directs RIKEN’s Real-World Intelligence Team. The team combines vision, language, touch, force and action to study systems that can understand surroundings, predict changes and act adaptively.
- Now at
- RIKEN and University of Tokyo
- Works
- 449
- Citations
- 12,577
- h-index
- 46
Publication numbers from OpenAlex, as of 14 October 2026.
Timeline
-
2025
Describing motion and image formation
Harada coauthored Intend to Move, a dataset for intention- and scene-aware human-motion prediction. I2-NeRF studied neural radiance fields under physically grounded interactions with surrounding media. Both projects connected learned representations with physical context.
-
2026
Learning across robot forms
His shared research included offline reinforcement learning across robot datasets from different embodiments and methods for more stable policy optimization in two-player games. His work also includes R2-Dreamer, a study of reduced-redundancy world models.
-
2026
Images and three-dimensional scenes
Harada coauthored work on panoramic image generation, sparse-view scene reconstruction and physically based noise in astronomical images. These papers show the range of visual information addressed by his research group.
-
As of October 2026
Real-world intelligence
Harada directs RIKEN’s Real-World Intelligence Team. The team combines vision, language, touch, force and action to study systems that can understand surroundings, predict changes and act adaptively.
Sources and credits
Photo: www.riken.jp; creator not stated. License: Not stated by source. Source: riken.jp. Cropped to a square and resized. Ask us to remove or replace this photo.