Yuki Uranishi

Eduardo Iglesius, Masato Kobayashi, Yuki Uranishi

Recent advancements have made robot navigation more intuitive by transitioning from traditional 2D displays to spatially aware Mixed Reality (MR) systems. However, current MR interfaces often rely on manual "air tap" gestures for goal placement, which can be repetitive and physically demanding, especially for beginners. This paper proposes the Mixed Reality-Based Robot Navigation Interface using Spatial Pointing and Speech (MRPoS). This novel framework replaces complex hand gestures with a natural, multimodal interface combining spatial pointing with Large Language Model (LLM)-based speech interaction. By leveraging both information, the system translates verbal intent into navigation goals visualized by MR technology. Comprehensive experiments comparing MRPoS against conventional gesture-based systems demonstrate that our approach significantly reduces task completion time and workload, providing a more accessible and efficient interface. For additional material, please check: https://mertcookimg.github.io/mrpos

Thanpimon Buamanee, Masato Kobayashi, Yuki Uranishi

Long-horizon contact-rich robotic manipulation remains challenging due to partial observability and unstable subtask transitions under contact uncertainty. While hierarchical architectures improve temporal reasoning and bilateral imitation learning enables force-aware control, existing approaches often rely on flat policies that struggle with long-horizon coordination. We propose Bi-HIL, a bilateral control-based multimodal hierarchical imitation learning framework for long-horizon manipulation. Bi-HIL stabilizes hierarchical coordination by integrating keyframe memory with subtask-level progress rate that models phase progression within the active subtask and conditions both high- and low-level policies. We evaluate Bi-HIL on unimanual and bimanual real-robot tasks, demonstrating consistent improvements over flat and ablated variants. The results highlight the importance of explicitly modeling subtask progression together with force-aware control for robust long-horizon manipulation. For additional material, please check: https://mertcookimg.github.io/bi-hil

Xuanmeng Sha, Liyun Zhang, Tomohiro Mashita et al.

Generating holistic co-speech gestures that integrate full-body motion with facial expressions suffers from semantically incoherent coordination on body motion and spatially unstable meaningless movements due to existing part-decomposed or frame-level regression methods, We introduce 3DGesPolicy, a novel action-based framework that reformulates holistic gesture generation as a continuous trajectory control problem through diffusion policy from robotics. By modeling frame-to-frame variations as unified holistic actions, our method effectively learns inter-frame holistic gesture motion patterns and ensures both spatially and semantically coherent movement trajectories that adhere to realistic motion manifolds. To further bridge the gap in expressive alignment, we propose a Gesture-Audio-Phoneme (GAP) fusion module that can deeply integrate and refine multi-modal signals, ensuring structured and fine-grained alignment between speech semantics, body motion, and facial expressions. Extensive quantitative and qualitative experiments on the BEAT2 dataset demonstrate the effectiveness of our 3DGesPolicy across other state-of-the-art methods in generating natural, expressive, and highly speech-aligned holistic gestures.

Xuanmeng Sha, Liyun Zhang, Tomohiro Mashita et al.

Audio-driven 3D facial animation has achieved significant progress in both research and applications. While recent baselines struggle to generate natural and continuous facial movements due to their frame-by-frame vertex generation approach, we propose 3DFacePolicy, a pioneer work that introduces a novel definition of vertex trajectory changes across consecutive frames through the concept of "action". By predicting action sequences for each vertex that encode frame-to-frame movements, we reformulate vertex generation approach into an action-based control paradigm. Specifically, we leverage a robotic control mechanism, diffusion policy, to predict action sequences conditioned on both audio and vertex states. Extensive experiments on VOCASET and BIWI datasets demonstrate that our approach significantly outperforms state-of-the-art methods and is particularly expert in dynamic, expressive and naturally smooth facial animations.

Takumi Kobayashi, Masato Kobayashi, Thanpimon Buamanee et al.

We present Bi-LAT, a novel imitation learning framework that unifies bilateral control with natural language processing to achieve precise force modulation in robotic manipulation. Bi-LAT leverages joint position, velocity, and torque data from leader-follower teleoperation while also integrating visual and linguistic cues to dynamically adjust applied force. By encoding human instructions such as "softly grasp the cup" or "strongly twist the sponge" through a multimodal Transformer-based model, Bi-LAT learns to distinguish nuanced force requirements in real-world tasks. We demonstrate Bi-LAT's performance in (1) unimanual cup-stacking scenario where the robot accurately modulates grasp force based on language commands, and (2) bimanual sponge-twisting task that requires coordinated force control. Experimental results show that Bi-LAT effectively reproduces the instructed force levels, particularly when incorporating SigLIP among tested language encoders. Our findings demonstrate the potential of integrating natural language cues into imitation learning, paving the way for more intuitive and adaptive human-robot interaction. For additional material, please visit: https://mertcookimg.github.io/bi-lat/

Takumi Taki, Masato Kobayashi, Yuki Uranishi

Autonomous mobile robots operating in human-shared indoor environments often require paths that reflect human spatial intentions, such as avoiding interference with pedestrian flow or maintaining comfortable clearance. However, conventional path planners primarily optimize geometric costs and provide limited support for explicit route specification by human operators. This paper presents MRReP, a Mixed Reality-based interface that enables users to draw a Hand-drawn Reference Path (HRP) directly on the physical floor using hand gestures. The drawn HRP is integrated into the robot navigation stack through a custom Hand-drawn Reference Path Planner, which converts the user-specified point sequence into a global path for autonomous navigation. We evaluated MRReP in a within-subject experiment against a conventional 2D baseline interface. The results demonstrated that MRReP enhanced path specification accuracy, usability, and perceived workload, while enabling more stable path specification in the physical environment. These findings suggest that direct path specification in MR is an effective approach for incorporating human spatial intention into mobile robot navigation. Additional material is available at https://mertcookimg.github.io/mrrep

Liyun Zhang, Photchara Ratsamee, Bowen Wang et al.

Despite remarkable progress in image translation, the complex scene with multiple discrepant objects remains a challenging problem. The translated images have low fidelity and tiny objects in fewer details causing unsatisfactory performance in object recognition. Without thorough object perception (i.e., bounding boxes, categories, and masks) of images as prior knowledge, the style transformation of each object will be difficult to track in translation. We propose panoptic-aware generative adversarial networks (PanopticGAN) for image-to-image translation together with a compact panoptic segmentation dataset. The panoptic perception (i.e., foreground instances and background semantics of the image scene) is extracted to achieve alignment between object content codes of the input domain and panoptic-level style codes sampled from the target style space, then refined by a proposed feature masking module for sharping object boundaries. The image-level combination between content and sampled style codes is also merged for higher fidelity image generation. Our proposed method was systematically compared with different competing methods and obtained significant improvement in both image quality and object recognition performance.

Sota Shoman, Tomohiro Mashita, Alexander Plopski et al.

Accurate camera localization is an essential part of tracking systems. However, localization results are greatly affected by illumination. Including data collected under various lighting conditions can improve the robustness of the localization algorithm to lighting variation. However, this is very tedious and time consuming. By using synthesized images it is possible to easily accumulate a large variety of views under varying illumination and weather conditions. Despite continuously improving processing power and rendering algorithms, synthesized images do not perfectly match real images of the same scene, i.e. there exists a gap between real and synthesized images that also affects the accuracy of camera localization. To reduce the impact of this gap, we introduce "REal-to-Synthetic Transform (REST)." REST is an autoencoder-like network that converts real features to their synthetic counterpart. The converted features can then be matched against the accumulated database for robust camera localization. In our experiments REST improved feature matching accuracy under variable lighting conditions by approximately 30%. Moreover, our system outperforms state of the art CNN-based camera localization methods trained with synthetic images. We believe our method could be used to initialize local tracking and to simplify data accumulation for lighting robust localization.