Imagen de Portada

How to Utilize Failure Demo Data?: Effective Data Selection for Imitation Learning Using Distribution Differences in Attention Mechanism

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Miyamoto, Kana, Suzuki, Kanata, Ogata, Tetsuya
Formato:	Preprint
Publicado:	2026
Materias:	Robotics
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Compact Task-Aligned Imitation Learning for Laboratory Automation
por: Suzuki, Kanata, et al.
Publicado: (2026)

Sensorimotor Attention and Language-based Regressions in Shared Latent Variables for Integrating Robot Motion Learning and LLM
por: Suzuki, Kanata, et al.
Publicado: (2024)

Proprioception Enhances Vision Language Model in Generating Captions and Subtask Segmentations for Robot Task
por: Suzuki, Kanata, et al.
Publicado: (2025)

Deep Predictive Learning: Motion Learning Concept inspired by Cognitive Robotics
por: Suzuki, Kanata, et al.
Publicado: (2023)

Learning Multimodal Attention for Manipulating Deformable Objects with Changing States
por: Saito, Namiko, et al.
Publicado: (2023)

From Dialogue to Execution: Mixture-of-Agents Assisted Interactive Planning for Behavior Tree-Based Long-Horizon Robot Execution
por: Suzuki, Kanata, et al.
Publicado: (2026)

Dual-arm Motion Generation for Repositioning Care based on Deep Predictive Learning with Somatosensory Attention Mechanism
por: Miyake, Tamon, et al.
Publicado: (2024)

Visual Spatial Attention and Proprioceptive Data-Driven Reinforcement Learning for Robust Peg-in-Hole Task Under Variable Conditions
por: Yasutomi, André Yuji, et al.
Publicado: (2023)

Visual Imitation Learning of Non-Prehensile Manipulation Tasks with Dynamics-Supervised Models
por: Mustafa, Abdullah, et al.
Publicado: (2024)

DataMIL: Selecting Data for Robot Imitation Learning with Datamodels
por: Dass, Shivin, et al.
Publicado: (2025)

Achieving Faster and More Accurate Operation of Deep Predictive Learning
por: Yoshikawa, Masaki, et al.
Publicado: (2024)

RoboManipBaselines: A Unified Framework for Imitation Learning in Robotic Manipulation across Real and Simulation Environments
por: Murooka, Masaki, et al.
Publicado: (2025)

UF-RNN: Real-Time Adaptive Motion Generation Using Uncertainty-Driven Foresight Prediction
por: Hiruma, Hyogo, et al.
Publicado: (2025)

A3RNN: Bi-directional Fusion of Bottom-up and Top-down Process for Developmental Visual Attention in Robots
por: Hiruma, Hyogo, et al.
Publicado: (2025)

DemoGen: Synthetic Demonstration Generation for Data-Efficient Visuomotor Policy Learning
por: Xue, Zhengrong, et al.
Publicado: (2025)

Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies
por: Xu, Chen, et al.
Publicado: (2025)

Demo-JEPA: Joint-Embedding Predictive Architecture for One-shot Cross-Embodiment Imitation
por: He, Jingyang, et al.
Publicado: (2026)

Stereo Multistage Spatial Attention for Real-Time Mobile Manipulation Under Visual Scale Variation and Disturbances
por: Cai, Xianbo, et al.
Publicado: (2026)

Close-Fitting Dressing Assistance Based on State Estimation of Feet and Garments with Semantic-based Visual Attention
por: Tsukakoshi, Takuma, et al.
Publicado: (2025)

Focused Blind Switching Manipulation Based on Constrained and Regional Touch States of Multi-Fingered Hand Using Deep Learning
por: Funabashi, Satoshi, et al.
Publicado: (2025)

DemoDiffusion: One-Shot Human Imitation using pre-trained Diffusion Policy
por: Park, Sungjae, et al.
Publicado: (2025)

Human-Robot Copilot for Data-Efficient Imitation Learning
por: Yan, Rui, et al.
Publicado: (2026)

An Efficient Metric for Data Quality Measurement in Imitation Learning
por: Sojib, Noushad, et al.
Publicado: (2026)

Data Scaling Laws in Imitation Learning for Robotic Manipulation
por: Hu, Yingdong, et al.
Publicado: (2024)

TaSA: Two-Phased Deep Predictive Learning of Tactile Sensory Attenuation for Improving In-Grasp Manipulation
por: Ponnivalavan, Pranav, et al.
Publicado: (2026)

CCIL: Continuity-based Data Augmentation for Corrective Imitation Learning
por: Ke, Liyiming, et al.
Publicado: (2023)

AdaDemo: Data-Efficient Demonstration Expansion for Generalist Robotic Agent
por: Mu, Tongzhou, et al.
Publicado: (2024)

A Peg-in-hole Task Strategy for Holes in Concrete
por: Yasutomi, André Yuji, et al.
Publicado: (2024)

DABI: Evaluation of Data Augmentation Methods Using Downsampling in Bilateral Control-Based Imitation Learning with Images
por: Kobayashi, Masato, et al.
Publicado: (2024)

Learning from the Best: Smoothness-Driven Metrics for Data Quality in Imitation Learning
por: Kulkarni, Soham, et al.
Publicado: (2026)

JUICER: Data-Efficient Imitation Learning for Robotic Assembly
por: Ankile, Lars, et al.
Publicado: (2024)

Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learning
por: Corrado, Nicholas E., et al.
Publicado: (2023)

Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning
por: Huang, Kevin, et al.
Publicado: (2025)

IntervenGen: Interventional Data Generation for Robust and Data-Efficient Robot Imitation Learning
por: Hoque, Ryan, et al.
Publicado: (2024)

Phase-Conditioned Imitation Learning with Autonomous Failure Recovery for Robust Deformable Object Manipulation
por: Chen, Dayuan, et al.
Publicado: (2026)

WM-DAgger: Enabling Efficient Data Aggregation for Imitation Learning with World Models
por: Yu, Anlan, et al.
Publicado: (2026)

Data-Asymmetric Latent Imagination and Reranking for 3D Robotic Imitation Learning
por: Luo, Lianghao, et al.
Publicado: (2026)

Data Scaling Laws for Imitation Learning-Based End-to-End Autonomous Driving
por: Zheng, Yupeng, et al.
Publicado: (2024)

Data Retrieval with Importance Weights for Few-Shot Imitation Learning
por: Xie, Amber, et al.
Publicado: (2025)

End-to-End Driving via Self-Supervised Imitation Learning Using Camera and LiDAR Data
por: Park, Jin Bok, et al.
Publicado: (2023)