collaborators

11 papers

cs.RO2026

VFILC: Accurate Frequency Extrapolations in Imitation Learning via Sampling Frequency ILC

Nozomu Masuya, Toshiaki Tsuji, Sho Sakaino

Conventional neural network (NN)-based imitation learning methods for variable-speed motion either restricted their scope to interpolated speeds, or generated unpredictable motions…

cs.RO2026

Design and Experimental Validation of Sensorless 4-Channel Bilateral Teleoperation for Low-Cost Manipulators

Koki Yamane, Yunhan Li, Masashi Konosu +4

Teleoperation of low-cost manipulators is attracting increasing attention as a practical means of collecting demonstration data for imitation learning. However, most existing low-c…

cs.RO2026

A Reproducible and Physically Feasible Dynamic Parameter Identification Framework for a Low-Cost Robot Arm

Junji Oaki, Koki Yamane, Koki Inami +1

This paper presents a reproducible and physically feasible dynamic parameter identification framework for CRANE-X7, a low-cost robot arm driven by modular smart actuators. To impro…

cs.RO2026

Refinement of Accelerated Demonstrations via Incremental Iterative Reference Learning Control for Fast Contact-Rich Imitation Learning

Koki Yamane, Cristian C. Beltran-Hernandez, Steven Oh +2

Fast execution of contact-rich manipulation is critical for practical deployment, yet providing fast demonstrations for imitation learning (IL) remains challenging: humans cannot d…

cs.RO2026

Force Generative Imitation Learning: Bridging Position Trajectory and Force Commands through Control Technique

Hiroshi Sato, Sho Sakaino, Toshiaki Tsuji

In contact-rich tasks, while position trajectories are often easy to obtain, appropriate force commands are typically unknown. Although it is conceivable to generate force commands…

cs.RO2026

Hierarchical Proportion Models for Motion Generation via Integration of Motion Primitives

Yu-Han Shu, Toshiaki Tsuji, Sho Sakaino

Imitation learning (IL) enables robots to acquire human-like motion skills from demonstrations, but it still requires extensive high-quality data and retraining to handle complex o…