10 papers · 1 filter
ConCent: Contact-Centric Real-to-Sim-to-Real Learning from One Demonstration
Heecheol Kim, Namiko Saito, Katsushi Ikeuchi +1
Sim-to-real policy transfer -- deploying policies trained in simulation in the real world -- is a promising paradigm for scaling robot manipulation without large-scale real-world d…
Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement
Kinam Kim, Namiko Saito, Heecheol Kim +3
Vision-Language-Action (VLA) models can generalize across diverse manipulation tasks, but their imitation-learning-based policies remain brittle in precise physical interactions du…
IK Seed Generator for Dual-Arm Human-like Physicality Robot with Mobile Base
Jun Takamatsu, Atsushi Kanehira, Kazuhiro Sasabuchi +2
Robots are strongly expected as a means of replacing human tasks. If a robot has a human-like physicality, the possibility of replacing human tasks increases. In the case of househ…
RL-Driven Data Generation for Robust Vision-Based Dexterous Grasping
Atsushi Kanehira, Naoki Wake, Kazuhiro Sasabuchi +2
This work presents reinforcement learning (RL)-driven data augmentation to improve the generalization of vision-action (VA) models for dexterous grasping. While real-to-sim-to-real…
A Taxonomy of Self-Handover
Naoki Wake, Atsushi Kanehira, Kazuhiro Sasabuchi +2
Self-handover, transferring an object between one's own hands, is a common but understudied bimanual action. While it facilitates seamless transitions in complex tasks, the strateg…
Plan-and-Act using Large Language Models for Interactive Agreement
Kazuhiro Sasabuchi, Naoki Wake, Atsushi Kanehira +2
Recent large language models (LLMs) are capable of planning robot actions. In this paper, we explore how LLMs can be used for planning actions with tasks involving situational huma…