arXiv subjects

Masayoshi Tomizuka

Publications and source records attributed to Masayoshi Tomizuka.

At least 73 records · Page 4Linked to original sources

arXiv2025

Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL

Maximum entropy has become a mainstream off-policy reinforcement learning (RL) framework for balancing exploitation and exploration. However, two bottlenecks still limit further performance improvement: (1) non-stationary Q-value estimation caused by jointly injecting entropy and updating its weighting parameter, i.e., temperature; and (2) short-sighted local entropy tuning that adjusts temperature only according to the current single-step entropy, without considering the effect of cumulative entropy over time. In this paper, we extends maximum entropy framework by proposing a trajectory entropy-constrained reinforcement learning (TECRL) framework to address these two challenges. Within this framework, we first separately learn two Q-functions, one associated with reward and the other with entropy, ensuring clean and stable value targets unaffected by temperature updates. Then, the dedicated entropy Q-function, explicitly quantifying the expected cumulative entropy, enables us to enforce a trajectory entropy constraint and consequently control the policy long-term stochasticity. Building on this TECRL framework, we develop a practical off-policy algorithm, DSAC-E, by extending the state-of-the-art distributional soft actor-critic with three refinements (DSAC-T). Empirical results on the OpenAI Gym benchmark demonstrate that our DSAC-E can achieve higher returns and better stability.

cs.LG↗

arXiv2025

MEReQ: Max-Ent Residual-Q Inverse RL for Sample-Efficient Alignment from Intervention

Aligning robot behavior with human preferences is crucial for deploying embodied AI agents in human-centered environments. A promising solution is interactive imitation learning from human intervention, where a human expert observes the policy's execution and provides interventions as feedback. However, existing methods often fail to utilize the prior policy efficiently to facilitate learning, thus hindering sample efficiency. In this work, we introduce MEReQ (Maximum-Entropy Residual-Q Inverse Reinforcement Learning), designed for sample-efficient alignment from human intervention. Instead of inferring the complete human behavior characteristics, MEReQ infers a residual reward function that captures the discrepancy between the human expert's and the prior policy's underlying reward functions. It then employs Residual Q-Learning (RQL) to align the policy with human preferences using this residual reward function. Extensive evaluations on simulated and real-world tasks demonstrate that MEReQ achieves sample-efficient policy alignment from human intervention.

cs.RO↗

arXiv2025

LANGTRAJ: Diffusion Model and Dataset for Language-Conditioned Trajectory Simulation

Evaluating autonomous vehicles with controllability enables scalable testing in counterfactual or structured settings, enhancing both efficiency and safety. We introduce LangTraj, a language-conditioned scene-diffusion model that simulates the joint behavior of all agents in traffic scenarios. By conditioning on natural language inputs, LangTraj provides flexible and intuitive control over interactive behaviors, generating nuanced and realistic scenarios. Unlike prior approaches that depend on domain-specific guidance functions, LangTraj incorporates language conditioning during training, facilitating more intuitive traffic simulation control. We propose a novel closed-loop training strategy for diffusion models, explicitly tailored to enhance stability and realism during closed-loop simulation. To support language-conditioned simulation, we develop Inter-Drive, a large-scale dataset with diverse and interactive labels for training language-conditioned diffusion models. Our dataset is built upon a scalable pipeline for annotating agent-agent interactions and single-agent behaviors, ensuring rich and varied supervision. Validated on the Waymo Open Motion Dataset, LangTraj demonstrates strong performance in realism, language controllability, and language-conditioned safety-critical simulation, establishing a new paradigm for flexible and scalable autonomous vehicle testing. Project Website: https://langtraj.github.io/

cs.LG↗

arXiv2025

P2 Explore: Efficient Exploration in Unknown Cluttered Environment with Floor Plan Prediction

Robot exploration aims at the reconstruction of unknown environments, and it is important to achieve it with shorter paths. Traditional methods focus on optimizing the visiting order of frontiers based on current observations, which may lead to local-minimal results. Recently, by predicting the structure of the unseen environment, the exploration efficiency can be further improved. However, in a cluttered environment, due to the randomness of obstacles, the ability to predict is weak. Moreover, this inaccuracy will lead to limited improvement in exploration. Therefore, we propose FPUNet which can be efficient in predicting the layout of noisy indoor environments. Then, we extract the segmentation of rooms and construct their topological connectivity based on the predicted map. The visiting order of these predicted rooms is optimized which can provide high-level guidance for exploration. The FPUNet is compared with other network architectures which demonstrates it is the SOTA method for this task. Extensive experiments in simulations show that our method can shorten the path length by 2.18% to 34.60% compared to the baselines.

cs.RO↗

arXiv2025

Interleave-VLA: Enhancing Robot Manipulation with Interleaved Image-Text Instructions

The rise of foundation models paves the way for generalist robot policies in the physical world. Existing methods relying on text-only instructions often struggle to generalize to unseen scenarios. We argue that interleaved image-text inputs offer richer and less biased context and enable robots to better handle unseen tasks with more versatile human-robot interaction. Building on this insight, Interleave-VLA, the first robot learning paradigm capable of comprehending interleaved image-text instructions and directly generating continuous action sequences in the physical world, is introduced. It offers a natural, flexible, and model-agnostic paradigm that extends state-of-the-art vision-language-action (VLA) models with minimal modifications while achieving strong zero-shot generalization. Interleave-VLA also includes an automatic pipeline that converts text instructions from Open X-Embodiment into interleaved image-text instructions, resulting in a large-scale real-world interleaved embodied dataset with 210k episodes. Comprehensive evaluation in simulation and the real world shows that Interleave-VLA offers two major benefits: (1) improves out-of-domain generalization to unseen objects by 2x compared to text input baselines, (2) supports flexible task interfaces and diverse instructions in a zero-shot manner, such as hand-drawn sketches. We attribute Interleave-VLA's strong zero-shot capability to the use of instruction images, which effectively mitigate hallucinations, and the inclusion of heterogeneous multimodal datasets, enriched with Internet-sourced images, offering potential for scalability. More information is available at https://interleave-vla.github.io/Interleave-VLA-Anonymous/

cs.RO↗

arXiv2025

Everything-Grasping (EG) Gripper: A Universal Gripper with Synergistic Suction-Grasping Capabilities for Cross-Scale and Cross-State Manipulation

Grasping objects across vastly different sizes and physical states-including both solids and liquids-with a single robotic gripper remains a fundamental challenge in soft robotics. We present the Everything-Grasping (EG) Gripper, a soft end-effector that synergistically integrates distributed surface suction with internal granular jamming, enabling cross-scale and cross-state manipulation without requiring airtight sealing at the contact interface with target objects. The EG Gripper can handle objects with surface areas ranging from sub-millimeter scale 0.2 mm2 (glass bead) to over 62,000 mm2 (A4 sized paper and woven bag), enabling manipulation of objects nearly 3,500X smaller and 88X larger than its own contact area (approximated at 707 mm2 for a 30 mm-diameter base). We further introduce a tactile sensing framework that combines liquid detection and pressure-based suction feedback, enabling real-time differentiation between solid and liquid targets. Guided by the actile-Inferred Grasping Mode Selection (TIGMS) algorithm, the gripper autonomously selects grasping modes based on distributed pressure and voltage signals. Experiments across diverse tasks-including underwater grasping, fragile object handling, and liquid capture-demonstrate robust and repeatable performance. To our knowledge, this is the first soft gripper to reliably grasp both solid and liquid objects across scales using a unified compliant architecture.

cs.RO↗

arXiv2025

Global-Local Interface for On-Demand Teleoperation

Teleoperation is a critical method for human-robot interface, holds significant potential for enabling robotic applications in industrial and unstructured environments. Existing teleoperation methods have distinct strengths and limitations in flexibility, range of workspace and precision. To fuse these advantages, we introduce the Global-Local (G-L) Teleoperation Interface. This interface decouples robotic teleoperation into global behavior, which ensures the robot motion range and intuitiveness, and local behavior, which enhances human operator's dexterity and capability for performing fine tasks. The G-L interface enables efficient teleoperation not only for conventional tasks like pick-and-place, but also for challenging fine manipulation and large-scale movements. Based on the G-L interface, we constructed a single-arm and a dual-arm teleoperation system with different remote control devices, then demonstrated tasks requiring large motion range, precise manipulation or dexterous end-effector control. Extensive experiments validated the user-friendliness, accuracy, and generalizability of the proposed interface.

cs.RO↗

arXiv2025

Programmable Locking Cells (PLC) for Modular Robots with High Stiffness Tunability and Morphological Adaptability

Robotic systems operating in unstructured environments require the ability to switch between compliant and rigid states to perform diverse tasks such as adaptive grasping, high-force manipulation, shape holding, and navigation in constrained spaces, among others. However, many existing variable stiffness solutions rely on complex actuation schemes, continuous input power, or monolithic designs, limiting their modularity and scalability. This paper presents the Programmable Locking Cell (PLC)-a modular, tendon-driven unit that achieves discrete stiffness modulation through mechanically interlocked joints actuated by cable tension. Each unit transitions between compliant and firm states via structural engagement, and the assembled system exhibits high stiffness variation-up to 950% per unit-without susceptibility to damage under high payload in the firm state. Multiple PLC units can be assembled into reconfigurable robotic structures with spatially programmable stiffness. We validate the design through two functional prototypes: (1) a variable-stiffness gripper capable of adaptive grasping, firm holding, and in-hand manipulation; and (2) a pipe-traversing robot composed of serial PLC units that achieves shape adaptability and stiffness control in confined environments. These results demonstrate the PLC as a scalable, structure-centric mechanism for programmable stiffness and motion, enabling robotic systems with reconfigurable morphology and task-adaptive interaction.

cs.RO↗

arXiv2025

DEXOP: A Device for Robotic Transfer of Dexterous Human Manipulation

We introduce perioperation, a paradigm for robotic data collection that sensorizes and records human manipulation while maximizing the transferability of the data to real robots. We implement this paradigm in DEXOP, a passive hand exoskeleton designed to maximize human ability to collect rich sensory (vision + tactile) data for diverse dexterous manipulation tasks in natural environments. DEXOP mechanically connects human fingers to robot fingers, providing users with direct contact feedback (via proprioception) and mirrors the human hand pose to the passive robot hand to maximize the transfer of demonstrated skills to the robot. The force feedback and pose mirroring make task demonstrations more natural for humans compared to teleoperation, increasing both speed and accuracy. We evaluate DEXOP across a range of dexterous, contact-rich tasks, demonstrating its ability to collect high-quality demonstration data at scale. Policies learned with DEXOP data significantly improve task performance per unit time of data collection compared to teleoperation, making DEXOP a powerful tool for advancing robot dexterity. Our project page is at https://dex-op.github.io.

cs.RO↗

arXiv2025

Algebraic Control: Complete Stable Inversion with Necessary and Sufficient Conditions

In this paper, we establish necessary and sufficient conditions for stable inversion, addressing challenges in non-minimum phase, non-square, and singular systems. An H-Infinity based algebraic approximation is introduced for near-perfect tracking without preview. Additionally, we propose a novel robust control strategy combining the nominal model with dual feedforward control to form a feedback structure. Numerical comparison demonstrates the approach's effectiveness.

math.OC↗

arXiv2025

Language-Driven Policy Distillation for Cooperative Driving in Multi-Agent Reinforcement Learning

The cooperative driving technology of Connected and Autonomous Vehicles (CAVs) is crucial for improving the efficiency and safety of transportation systems. Learning-based methods, such as Multi-Agent Reinforcement Learning (MARL), have demonstrated strong capabilities in cooperative decision-making tasks. However, existing MARL approaches still face challenges in terms of learning efficiency and performance. In recent years, Large Language Models (LLMs) have rapidly advanced and shown remarkable abilities in various sequential decision-making tasks. To enhance the learning capabilities of cooperative agents while ensuring decision-making efficiency and cost-effectiveness, we propose LDPD, a language-driven policy distillation method for guiding MARL exploration. In this framework, a teacher agent based on LLM trains smaller student agents to achieve cooperative decision-making through its own decision-making demonstrations. The teacher agent enhances the observation information of CAVs and utilizes LLMs to perform complex cooperative decision-making reasoning, which also leverages carefully designed decision-making tools to achieve expert-level decisions, providing high-quality teaching experiences. The student agent then refines the teacher's prior knowledge into its own model through gradient policy updates. The experiments demonstrate that the students can rapidly improve their capabilities with minimal guidance from the teacher and eventually surpass the teacher's performance. Extensive experiments show that our approach demonstrates better performance and learning efficiency compared to baseline methods.

cs.RO↗

arXiv2025

DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes

We present DeSiRe-GS, a self-supervised gaussian splatting representation, enabling effective static-dynamic decomposition and high-fidelity surface reconstruction in complex driving scenarios. Our approach employs a two-stage optimization pipeline of dynamic street Gaussians. In the first stage, we extract 2D motion masks based on the observation that 3D Gaussian Splatting inherently can reconstruct only the static regions in dynamic environments. These extracted 2D motion priors are then mapped into the Gaussian space in a differentiable manner, leveraging an efficient formulation of dynamic Gaussians in the second stage. Combined with the introduced geometric regularizations, our method are able to address the over-fitting issues caused by data sparsity in autonomous driving, reconstructing physically plausible Gaussians that align with object surfaces rather than floating in air. Furthermore, we introduce temporal cross-view consistency to ensure coherence across time and viewpoints, resulting in high-quality surface reconstruction. Comprehensive experiments demonstrate the efficiency and effectiveness of DeSiRe-GS, surpassing prior self-supervised arts and achieving accuracy comparable to methods relying on external 3D bounding box annotations. Code is available at https://github.com/chengweialan/DeSiRe-GS

cs.CV↗

arXiv2025

A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision

We present a novel framework for training 3D image-conditioned diffusion models using only 2D supervision. Recovering 3D structure from 2D images is inherently ill-posed due to the ambiguity of possible reconstructions, making generative models a natural choice. However, most existing 3D generative models rely on full 3D supervision, which is impractical due to the scarcity of large-scale 3D datasets. To address this, we propose leveraging sparse-view supervision as a scalable alternative. While recent reconstruction models use sparse-view supervision with differentiable rendering to lift 2D images to 3D, they are predominantly deterministic, failing to capture the diverse set of plausible solutions and producing blurry predictions in uncertain regions. A key challenge in training 3D diffusion models with 2D supervision is that the standard training paradigm requires both the denoising process and supervision to be in the same modality. We address this by decoupling the noisy samples being denoised from the supervision signal, allowing the former to remain in 3D while the latter is provided in 2D. Our approach leverages suboptimal predictions from a deterministic image-to-3D model-acting as a "teacher"-to generate noisy 3D inputs, enabling effective 3D diffusion training without requiring full 3D ground truth. We validate our framework on both object-level and scene-level datasets, using two different 3D Gaussian Splat (3DGS) teachers. Our results show that our approach consistently improves upon these deterministic teachers, demonstrating its effectiveness in scalable and high-fidelity 3D generative modeling. See our project page at https://lesson-in-splats.github.io/

cs.CV↗

arXiv2025

Leveraging Extrinsic Dexterity for Occluded Grasping on Grasp Constraining Walls

This study addresses the problem of occluded grasping, where primary grasp configurations of an object are not available due to occlusion with environment. Simple parallel grippers often struggle with such tasks due to limited dexterity and actuation constraints. Prior works have explored object pose reorientation such as pivoting by utilizing extrinsic contacts between an object and an environment feature like a wall, to make the object graspable. However, such works often assume the presence of a short wall, and this assumption may not always hold in real-world scenarios. If the wall available for interaction is too large or too tall, the robot may still fail to grasp the object even after pivoting, and the robot must combine different types of actions to grasp. To address this, we propose a hierarchical reinforcement learning (RL) framework. We use Q-learning to train a high-level policy that selects the type of action expected to yield the highest reward. The selected low-level skill then samples a specific robot action in continuous space. To guide the robot to an appropriate location for executing the selected action, we adopt a Conditional Variational Autoencoder (CVAE). We condition the CVAE on the object point cloud and the skill ID, enabling it to infer a suitable location based on the object geometry and the selected skill. To promote generalization, we apply domain randomization during the training of low-level skills. The RL policy is trained entirely in simulation with a box-like object and deployed to six objects in real world. We conduct experiments to evaluate our method and demonstrate both its generalizability and robust sim-to-real transfer performance with promising success rates.

cs.RO↗

arXiv2025

StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation

We introduce StreamDiffusion, a real-time diffusion pipeline designed for interactive image generation. Existing diffusion models are adept at creating images from text or image prompts, yet they often fall short in real-time interaction. This limitation becomes particularly evident in scenarios involving continuous input, such as Metaverse, live video streaming, and broadcasting, where high throughput is imperative. To address this, we present a novel approach that transforms the original sequential denoising into the batching denoising process. Stream Batch eliminates the conventional wait-and-interact approach and enables fluid and high throughput streams. To handle the frequency disparity between data input and model throughput, we design a novel input-output queue for parallelizing the streaming process. Moreover, the existing diffusion pipeline uses classifier-free guidance(CFG), which requires additional U-Net computation. To mitigate the redundant computations, we propose a novel residual classifier-free guidance (RCFG) algorithm that reduces the number of negative conditional denoising steps to only one or even zero. Besides, we introduce a stochastic similarity filter(SSF) to optimize power consumption. Our Stream Batch achieves around 1.5x speedup compared to the sequential denoising method at different denoising levels. The proposed RCFG leads to speeds up to 2.05x higher than the conventional CFG. Combining the proposed strategies and existing mature acceleration tools makes the image-to-image generation achieve up-to 91.07fps on one RTX4090, improving the throughputs of AutoPipline developed by Diffusers over 59.56x. Furthermore, our proposed StreamDiffusion also significantly reduces the energy consumption by 2.39x on one RTX3060 and 1.99x on one RTX4090, respectively.

cs.CV↗

arXiv2025

NeRFs in Robotics: A Survey

Detailed and realistic 3D environment representations have been a long-standing goal in the fields of computer vision and robotics. The recent emergence of neural implicit representations has introduced significant advances to these domains, enabling numerous novel capabilities. Among these, Neural Radiance Fields (NeRFs) have gained considerable attention because of their considerable representational advantages, such as simplified mathematical models, low memory footprint, and continuous scene representations. In addition to computer vision, NeRFs have demonstrated significant potential in robotics. Thus, we present this survey to provide a comprehensive understanding of NeRFs in the field of robotics. By exploring the advantages and limitations of NeRF as well as its current applications and future potential, we aim to provide an overview of this promising area of research. Our survey is divided into two main sections: \textit{Applications of NeRFs in Robotics} and \textit{Advances for NeRFs in Robotics}, from the perspective of how NeRF enters the field of robotics. In the first section, we introduce and analyze some works that have been or could be used in robotics for perception and interaction tasks. In the second section, we show some works related to improving NeRF's own properties, which are essential for deploying NeRFs in robotics. In the discussion section of the review, we summarize the existing challenges and provide valuable future research directions.

cs.RO↗

arXiv2025

Unified Manipulability and Compliance Analysis of Modular Soft-Rigid Hybrid Fingers

This paper presents a unified framework to analyze the manipulability and compliance of modular soft-rigid hybrid robotic fingers. The approach applies to both hydraulic and pneumatic actuation systems. A Jacobian-based formulation maps actuator inputs to joint and task-space responses. Hydraulic actuators are modeled under incompressible assumptions, while pneumatic actuators are described using nonlinear pressure-volume relations. The framework enables consistent evaluation of manipulability ellipsoids and compliance matrices across actuation modes. We validate the analysis using two representative hands: DexCo (hydraulic) and Edgy-2 (pneumatic). Results highlight actuation-dependent trade-offs in dexterity and passive stiffness. These findings provide insights for structure-aware design and actuator selection in soft-rigid robotic fingers.

cs.RO↗

arXiv2025

Reimagination with Test-time Observation Interventions: Distractor-Robust World Model Predictions for Visual Model Predictive Control

World models enable robots to "imagine" future observations given current observations and planned actions, and have been increasingly adopted as generalized dynamics models to facilitate robot learning. Despite their promise, these models remain brittle when encountering novel visual distractors such as objects and background elements rarely seen during training. Specifically, novel distractors can corrupt action outcome predictions, causing downstream failures when robots rely on the world model imaginations for planning or action verification. In this work, we propose Reimagination with Observation Intervention (ReOI), a simple yet effective test-time strategy that enables world models to predict more reliable action outcomes in open-world scenarios where novel and unanticipated visual distractors are inevitable. Given the current robot observation, ReOI first detects visual distractors by identifying which elements of the scene degrade in physically implausible ways during world model prediction. Then, it modifies the current observation to remove these distractors and bring the observation closer to the training distribution. Finally, ReOI "reimagines" future outcomes with the modified observation and reintroduces the distractors post-hoc to preserve visual consistency for downstream planning and verification. We validate our approach on a suite of robotic manipulation tasks in the context of action verification, where the verifier needs to select desired action plans based on predictions from a world model. Our results show that ReOI is robust to both in-distribution and out-of-distribution visual distractors. Notably, it improves task success rates by up to 3x in the presence of novel distractors, significantly outperforming action verification that relies on world model predictions without imagination interventions.

cs.RO↗