7 papers
TOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action Models
Keisuke Shirai, Tomohiro Motoda, Hanbit Oh +5
Autoregressive Vision-Language-Action models often represent continuous robot actions as discrete token sequences, enabling action prediction with standard next-token objectives. F…
Self-Supervised Anchoring of Fingertip Sensing to Proprioception and Proactive Actions for Robot Imitation Learning
Tomohiro Motoda, Masaki Murooka, Keisuke Shirai +6
Robotic imitation learning often relies on external cameras, yet local interaction cues such as object proximity, contact onset, and grasp state are difficult to observe near the f…
The Embodiment Gap in Robot Foundation Models
Yukiyasu Domae, Keisuke Shirai, Hanbit Oh +7
Robot foundation models (RFMs), including vision-language-action (VLA) policies, are often discussed through a scaling view: more data, larger models, and broader benchmarks should…
GuidedAttention: Interpretable and Correctable Visual Attention for OOD-Robust Robot Manipulation via Imitation Learning
Masaki Murooka, Ryoichi Nakajo, Keisuke Shirai +4
End-to-end visuomotor policies provide little opportunity for humans to understand or correct the policy's visual attention. We propose GuidedAttention, a visuomotor imitation lear…
RoboManipBaselines: A Unified Framework for Imitation Learning in Robotic Manipulation across Real and Simulation Environments
Masaki Murooka, Tomohiro Motoda, Ryoichi Nakajo +5
We present RoboManipBaselines, an open-source software framework for imitation learning research in robotic manipulation. The framework supports the entire imitation learning pipel…
Grounded Vision-Language Interpreter for Long-Horizon Bimanual Task and Motion Planning
Jeremy Siburian, Keisuke Shirai, Cristian C. Beltran-Hernandez +3
While recent advances in vision-language models have accelerated language-guided robot planning, their black-box nature lacks the safety guarantees and interpretability crucial for…
KeyMPs: One-Shot Vision-Language Guided Motion Generation by Sequencing DMPs for Occlusion-Rich Tasks
Edgar Anarossi, Yuhwan Kwon, Hirotaka Tahara +6
Dynamic Movement Primitives (DMPs) provide a flexible framework wherein smooth robotic motions are encoded into modular parameters. However, they face challenges in integrating mul…