15 citations · 40 across the 25 of their papers we have counts for
29 papers
YUBI-Real2Sim: 3DGS Scene Verification for Reliable Policy Evaluation
Hiroki Nishizawa, Takehiko Ohkawa, Nicola Scianca +3
Evaluating VLA policies on real robots is costly, time-consuming, and difficult to reproduce, making real-to-sim simulation essential for scalable evaluation. While 3D Gaussian Spl…
YUBI-STAG: Contact and Semantic-Rich Alignment for VLAs via Automated Video-Language Grounding
Masatoshi Tateno, Takehiko Ohkawa, Yueh-Hua Wu +4
Vision-Language-Action (VLA) models acquire broad manipulation capabilities via large-scale pretraining, yet eliciting them through language requires fine-grained alignment between…
RoboPace: Contact-Aware Time-Optimal Retiming for Action-Chunk Policies
Mimo Shirasaka, Takehiko Ohkawa, Takuya Okubo +3
Robot manipulation data collection has been shifting from teleoperation toward robot-free demonstrations, through interfaces such as the Universal Manipulation Interface (UMI) or d…
CounterAlign: Counterfactual Supervision for Vision-Language-Action Models
Haru Kondoh, Kei Ota, Asako Kanezaki +1
Vision-Language-Action (VLA) models are typically trained with behavior cloning (BC) on expert demonstrations. However, BC provides only positive supervision for expert actions, wi…
Auditing Instruction-Trajectory Mismatches in Multimodal Robot Demonstrations
Simon Holk, Ryosuke Takanami, Tatsuya Matsushima +4
Robot demonstration datasets used to train vision-language-action policies can contain a subtle but harmful failure mode: trajectories that are behaviorally correct but paired with…
YUBI: Yielding Universal Bidigital Interface for Bimanual Dexterous Manipulation at Scale
Takehiko Ohkawa, Jumpei Arima, Yuki Noguchi +16
We introduce Yielding Universal Bidigital Interface (YUBI), a finger-aligned gripper designed to enable intuitive, ergonomic, and scalable data collection for bimanual dexterous ma…
See Less, Specify More: Visual Evidence Budgets for Generalizable VLAs
Yueh-Hua Wu, Tatsuya Matsushima, Kei Ota
Generalization remains a central bottleneck for vision-language-action (VLA) models: under distractors, appearance shifts, and semantically similar tasks, the policy must often inf…
Continuous Reasoning for Vision-Language-Action
Yueh-Hua Wu, Tatsuya Matsushima, Kei Ota
Natural language is a powerful reasoning medium for language and vision-language models, but it is mismatched to the granularity of continuous control. Text and explicit subgoals o…
Touch2Insert: Zero-Shot Peg Insertion by Touching Intersections of Peg and Hole
Masaru Yajima, Yuma Shin, Rei Kawakami +2
Reliable insertion of industrial connectors remains a central challenge in robotics, requiring sub-millimeter precision under uncertainty and often without full visual access. Visi…
Simultaneous Extrinsic Contact and In-Hand Pose Estimation via Distributed Tactile Sensing
Mark Van der Merwe, Kei Ota, Dmitry Berenson +2
Prehensile autonomous manipulation, such as peg insertion, tool use, or assembly, require precise in-hand understanding of the object pose and the extrinsic contacts made during in…
Analytic Conditions for Differentiable Collision Detection in Trajectory Optimization
Akshay Jaitly, Devesh K. Jha, Kei Ota +1
Optimization-based methods are widely used for computing fast, diverse solutions for complex tasks such as collision-free movement or planning in the presence of contacts. However,…
Learning Pivoting Manipulation with Force and Vision Feedback Using Optimization-based Demonstrations
Yuki Shirai, Kei Ota, Devesh K. Jha +1
Non-prehensile manipulation is challenging due to complex contact interactions between objects, the environment, and robots. Model-based approaches can efficiently generate complex…
Modality Selection and Skill Segmentation via Cross-Modality Attention
Jiawei Jiang, Kei Ota, Devesh K. Jha +1
Incorporating additional sensory modalities such as tactile and audio into foundational robotic models poses significant challenges due to the curse of dimensionality. This work ad…
FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models
Kuanting Wu, Kei Ota, Asako Kanezaki
Video Diffusion Models (VDMs) can generate high-quality videos, but often struggle with producing temporally coherent motion. Optical flow supervision is a promising approach to ad…
Zero-Shot Peg Insertion: Identifying Mating Holes and Estimating SE(2) Poses with Vision-Language Models
Masaru Yajima, Kei Ota, Asako Kanezaki +1
Achieving zero-shot peg insertion, where inserting an arbitrary peg into an unseen hole without task-specific training, remains a fundamental challenge in robotics. This task deman…
Autonomous Robotic Assembly: From Part Singulation to Precise Assembly
Kei Ota, Devesh K. Jha, Siddarth Jain +5
Imagine a robot that can assemble a functional product from the individual parts presented in any configuration to the robot. Designing such a robotic system is a complex problem w…
Robust In-Hand Manipulation with Extrinsic Contacts
Boyuan Liang, Kei Ota, Masayoshi Tomizuka +1
We present in-hand manipulation tasks where a robot moves an object in grasp, maintains its external contact mode with the environment, and adjusts its in-hand pose simultaneously.…
Tactile Estimation of Extrinsic Contact Patch for Stable Placement
Kei Ota, Devesh K. Jha, Krishna Murthy Jatavallabhula +2
Precise perception of contact interactions is essential for fine-grained manipulation skills for robots. In this paper, we present the design of feedback skills for robots that mus…
Style-transfer based Speech and Audio-visual Scene Understanding for Robot Action Sequence Acquisition from Videos
Chiori Hori, Puyuan Peng, David Harwath +7
To realize human-robot collaboration, robots need to execute actions for new tasks according to human instructions given finite prior knowledge. Human experts can share their knowl…
Tactile-Filter: Interactive Tactile Perception for Part Mating
Kei Ota, Devesh K. Jha, Hsiao-Yu Tung +1
Humans rely on touch and tactile sensing for a lot of dexterous manipulation tasks. Our tactile sensing provides us with a lot of information regarding contact formations as well a…
H-SAUR: Hypothesize, Simulate, Act, Update, and Repeat for Understanding Object Articulations from Interactions
Kei Ota, Hsiao-Yu Tung, Kevin A. Smith +5
The world is filled with articulated objects that are difficult to determine how to use from vision alone, e.g., a door might open inwards or outwards. Humans handle these objects…
Object Memory Transformer for Object Goal Navigation
Rui Fukushima, Kei Ota, Asako Kanezaki +2
This paper presents a reinforcement learning method for object goal navigation (ObjNav) where an agent navigates in 3D indoor environments to reach a target object based on long-te…
OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching
Hana Hoshino, Kei Ota, Asako Kanezaki +1
Inverse Reinforcement Learning (IRL) is attractive in scenarios where reward engineering can be tedious. However, prior IRL algorithms use on-policy transitions, which require inte…
Training Larger Networks for Deep Reinforcement Learning
Kei Ota, Devesh K. Jha, Asako Kanezaki
The success of deep learning in the computer vision and natural language processing communities can be attributed to training of very deep neural networks with millions or billions…