6 papers
Co-training with Ego-centric Video and Demonstration for Robot Navigation Task
Shoya Kuno, Yumo Ouchi, Kanata Suzuki
Vision-language-action (VLA) models are promising for diverse robotic tasks, but their performance heavily depends on large-scale high-quality training data, whose collection on re…
How to Utilize Failure Demo Data?: Effective Data Selection for Imitation Learning Using Distribution Differences in Attention Mechanism
Kana Miyamoto, Kanata Suzuki, Tetsuya Ogata
Imitation learning for robotic tasks has relied primarily on policies trained only on successful demonstrations, although failures are unavoidable during human data collection. Man…
From Dialogue to Execution: Mixture-of-Agents Assisted Interactive Planning for Behavior Tree-Based Long-Horizon Robot Execution
Kanata Suzuki, Kazuki Hori, Haruka Miyoshi +2
Interactive task planning with large language models (LLMs) lets robots generate high-level action plans from natural language, but over long horizons it asks many questions, and t…
Compact Task-Aligned Imitation Learning for Laboratory Automation
Kanata Suzuki, Hanon Nakamurama, Hanon Nakamura +2
Robotic laboratory automation has traditionally relied on carefully engineered motion pipelines and task-specific hardware interfaces, resulting in high design cost and limited fle…
Proprioception Enhances Vision Language Model in Generating Captions and Subtask Segmentations for Robot Task
Kanata Suzuki, Shota Shimizu, Tetsuya Ogata
From the perspective of future developments in robotics, it is crucial to verify whether foundation models trained exclusively on offline data, such as images and language, can und…
Learning Multimodal Attention for Manipulating Deformable Objects with Changing States
Namiko Saito, Mayu Tatsumi, Ayuna Kubo +4
To support humans in their daily lives, robots are required to autonomously learn, adapt to objects and environments, and perform the appropriate actions. We tackled on the task of…