Searcharxiv⌕ Search

arXiv subjects

Kaiyu Hang

Publications and source records attributed to Kaiyu Hang.

At least 19 recordsLinked to original sources

TMA: Sim-to-Real Forceful Humanoid Manipulation via Tactile-Driven Motor Adaptation

Recent humanoid loco-manipulation in articulated environments has largely focused on geometry-dominant interactions, where success is primarily determined by geometric alignment and motion execution. In contrast, forceful multi-finger manipulation requires the robot to adapt to real-world uncertainties in contact and interaction dynamics. We present Tactile-Driven Motor Adaptation (TMA) and an integrated whole-body system for zero-shot sim-to-real forceful humanoid manipulation, and study round-doorknob opening as a challenging benchmark requiring stable multi-finger frictional grasping, sufficient torque generation without slip, force-regulated pushing, and whole-body stability. TMA structures policy learning around interactions observable through tactile feedback, uses cone geometry as an inductive bias for multi-finger contact representation, and adapts motor behavior online from tactile history. An upper-body manipulation policy is trained alongside a pretrained general locomotion controller to coordinate dexterous interaction and whole-body stabilization. Trained entirely in simulation, TMA transfers zero-shot to a Unitree G1 humanoid with BrainCo Revo2 multi-fingered hands and substantially outperforms standard Rapid Motor Adaptation (RMA) and reactive tactile policy baselines across four commercial round doorknobs in the real world.

cs.RO↗

Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success

Robot foundation models are typically evaluated through costly closed-loop rollouts, motivating low-cost offline proxies for model capability. The Platonic Representation Hypothesis (PRH) suggests that as representations improve, modalities such as vision and language converge toward a shared statistical model of reality. We ask whether motion trajectories form another such modality: as embodied models become more capable, should their sensory representations converge toward the structure of physical motion? To test this, we propose Sensorimotor Alignment ($S^2$), a training-free offline metric that measures how well a model's sensory representation aligns with the geometry of physical motion. We find that $S^2$ correlates positively with downstream robot task success across model families, making it a low-cost offline proxy for prioritizing models before closed-loop evaluation. $S^2$ can also identify promising vision-language model (VLM) backbones before costly fine-tuning into vision-language-action models (VLAs). Beyond this correlation, $S^2$ offers representation-level explanations for phenomena observed in VLAs and world action models (WAMs). With $S^2$, we extend PRH to robotics and make sensorimotor alignment measurable, offering a low-cost, representation-level view of robot foundation models that closed-loop success rates alone cannot reveal.

cs.CV↗

What Matters in Quality-Aware VLA Pretraining: A Benchmark and Empirical Study

How should demonstration quality be used during vision-language-action (VLA) pretraining to improve performance after target-task fine-tuning? We compare weighting, filtering, and conditioning across reward definitions and label granularities using 5,000 naturally suboptimal human demonstrations and 24 target tasks. Within each VLA, we match demonstrations and training budgets. Additional comparisons examine pretraining data size and the roles of quality tags during fine-tuning and inference. Across three VLAs, we find that approach-aware episode conditioning improves mean success over plain behavioral cloning; conditioning and filtering favor episode and chunk labels, respectively, on average, with model-dependent reversals; and constant-tag fine-tuning improves mean success after conditioned pretraining with either tagged or untagged inference. We introduce AXIS-Bench to support these controlled comparisons. Built on crowdsourced simulation demonstrations, it provides recorded object and contact states for recomputing quality labels on shared trajectories. Replayable trajectories support workspace-aligned rendering and user-defined real-world target tasks. In our real-world experiment, simulation pretraining raises success from 9.6\% to 31.7\%. Project page: https://axis-bench.github.io/.

cs.RO↗

RoboTok: A Scalable Data Engine for Internet Demonstration Video Retrieval and Dexterous Manipulation Learning

Robot learning increasingly depends on broad and diverse demonstrations, yet collecting robot data remains expensive and difficult to scale across the wide range of real-world tasks. To address this bottleneck, we introduce RoboTok, a scalable data engine that uses a query human manipulation video to retrieve manipulation-relevant internet demonstrations for training dexterous robot policies. Specifically, we learn a latent motion space from 3D hand trajectories expressed in estimated actor-centered reference frames. This representation enables manipulation behaviors to be compared across variations in camera viewpoint, scene appearance, and actor occlusions, while remaining compact enough for efficient indexing and retrieval over internet video collections. We evaluate RoboTok against existing robot-data retrieval approaches using retrieval metrics and downstream robot policy performance, showing that RoboTok retrieves more manipulation-relevant demonstrations and improves downstream task success. In real-world robot experiments, RoboTok-guided policies achieve a mean success improvement of 42.2 percentage points over the strongest baseline for each task, establishing hand-pose trajectory-aware retrieval as a scalable way to leverage continuously growing web video for robot learning.

cs.CV↗

EgoInfinity: A Web-Scale 4D Hand-Object Interaction Data Engine for Any-View Robot Retargeting and Video-to-Action Robot Learning

Internet videos constitute the largest reservoir of embodied human manipulation knowledge, yet converting arbitrary RGB footage into actionable robot training data remains a major bottleneck. Existing lab- or factory-collected datasets are narrow in scale and diversity, limiting open-world robot learning. Instead of proposing a static dataset, we introduce EgoInfinity, a universal 4D hand-object interaction data engine that enables web-scale data generation for robot retargeting and learning. EgoInfinity is a modular engine integrating perception, segmentation, reconstruction, interaction-aware refinement, and retargeting to automate this traditionally unscalable video-to-action problem without human-in-the-loop annotation. Its modular design lets the engine continuously benefit from advances in any incorporated component. With EgoInfinity, in-the-wild human manipulation videos are lifted into agent-agnostic, metric 4D hand-object representations, including hand trajectories, 6-DoF object poses, and contact-relevant states. Rather than naively connecting standalone components, EgoInfinity combines cross-module metric calibration with interaction-aware refinement to improve physical reliability, reducing drift and contact inconsistencies common in pure visual reconstruction. We further propose a novel motion retargeter that compiles the recovered 3D hand motions into executable joint trajectories for diverse robot morphologies, enabling video-to-action retargeting on any robot from arbitrary viewpoints and shot sizes (e.g., the human body is only partially visible). We validate EgoInfinity across perception fidelity, kinematic feasibility, contact consistency, cross-embodiment generalization, and real-robot skill acquisition (e.g., grasping, cutting, wiping, and pouring), demonstrating a scalable bridge from internet videos to executable robot behavior for open-world robot learning.

cs.RO↗

Zero-Shot Sim-to-Real Robot Learning: A Dexterous Manipulation Study on Reactive Catching

Dexterous manipulation is physics-intensive and highly sensitive to modeling errors and perception noise, making sim-to-real transfer prohibitively challenging. Domain randomization (DR) is commonly used to improve the robustness of learned policies for such tasks, but conventional DR randomizes one instance per episode, offering very limited exposure to the variability of real-world dynamics. To this end, we propose Domain-Randomized Instance Set (DRIS), which represents and propagates a set of randomized instances simultaneously, providing richer approximation of uncertain dynamics and enabling policies to learn actions that account for multiple possible outcomes. Supported by theoretical analysis, we show that DRIS yields more robust policies and alleviates the need for real-world fine-tuning, even with a modest number of instances (e.g., 10). We demonstrate this on a challenging reactive catching task. Unlike traditional catching setups that use end-effectors designed to mechanically stabilize the object (e.g., curved or enclosing surfaces), our system uses a flat plate that offers no passive stabilization, making the task highly sensitive to noise and requiring rapid reactive motions. The learned policies exhibit strong robustness to uncertainties and achieve reliable zero-shot sim-to-real transfer.

cs.RO↗

ManiDreams: An Open-Source Library for Robust Object Manipulation via Uncertainty-aware Task-specific Intuitive Physics

Dynamics models, whether simulators or learned world models, have long been central to robotic manipulation, but most focus on minimizing prediction error rather than confronting a more fundamental challenge: real-world manipulation is inherently uncertain. We argue that robust manipulation under uncertainty is fundamentally an integration problem: uncertainties must be represented, propagated, and constrained within the planning loop, not merely suppressed during training. We present and open-source ManiDreams, a modular framework for uncertainty-aware manipulation planning over intuitive physics models. It realizes this integration through composable abstractions for distributional state representation, backend-agnostic dynamics prediction, and declarative constraint specification for action optimization. The framework explicitly addresses three sources of uncertainty: perceptual, parametric, and structural. It wraps any base policy with a sample-predict-constrain loop that evaluates candidate actions against distributional outcomes, adding robustness without retraining. Experiments on ManiSkill tasks show that ManiDreams maintains robust performance under various perturbations where the RL baseline degrades significantly. Runnable examples on pushing, picking, catching, and real-world deployment demonstrate flexibility across different policies, optimizers, physics backends, and executors. The framework is publicly available at https://github.com/Rice-RobotPI-Lab/ManiDreams

cs.RO↗

MotionBits: Video Segmentation through Motion-Level Analysis of Rigid Bodies

Rigid bodies constitute the smallest manipulable elements in the real world, and understanding how they physically interact is fundamental to embodied reasoning and robotic manipulation. Thus, accurate detection, segmentation, and tracking of moving rigid bodies is essential for enabling reasoning modules to interpret and act in diverse environments. However, current segmentation models trained on semantic grouping are limited in their ability to provide meaningful interaction-level cues for completing embodied tasks. To address this gap, we introduce MotionBit, a novel concept that, unlike prior formulations, defines the smallest unit in motion-based segmentation through kinematic spatial twist equivalence, independent of semantics. In this paper, we contribute (1) the MotionBit concept and definition, (2) a hand-labeled benchmark, called MoRiBo, for evaluating moving rigid-body segmentation across robotic manipulation and human-in-the-wild videos, and (3) a learning-free graph-based MotionBits segmentation method that outperforms state-of-the-art embodied perception methods by 37.3\% in macro-averaged mIoU on the MoRiBo benchmark. Finally, we demonstrate the effectiveness of MotionBits segmentation for downstream embodied reasoning and manipulation tasks, highlighting its importance as a fundamental primitive for understanding physical interactions.

cs.CV↗

ManipulationNet: An Infrastructure for Benchmarking Real-World Robot Manipulation with Physical Skill Challenges and Embodied Multimodal Reasoning

Dexterous manipulation enables robots to purposefully alter the physical world, transforming them from passive observers into active agents in unstructured environments. This capability is the cornerstone of physical artificial intelligence. Despite decades of advances in hardware, perception, control, and learning, progress toward general manipulation systems remains fragmented due to the absence of widely adopted standard benchmarks. The central challenge lies in reconciling the variability of the real world with the reproducibility and authenticity required for rigorous scientific evaluation. To address this, we introduce ManipulationNet, a global infrastructure that hosts real-world benchmark tasks for robotic manipulation. ManipulationNet delivers reproducible task setups through standardized hardware kits, and enables distributed performance evaluation via a unified software client that delivers real-time task instructions and collects benchmarking results. As a persistent and scalable infrastructure, ManipulationNet organizes benchmark tasks into two complementary tracks: 1) the Physical Skills Track, which evaluates low-level physical interaction skills, and 2) the Embodied Reasoning Track, which tests high-level reasoning and multimodal grounding abilities. This design fosters the systematic growth of an interconnected network of real-world abilities and skills, paving the path toward general robotic manipulation. By enabling comparable manipulation research in the real world at scale, this infrastructure establishes a sustainable foundation for measuring long-term scientific progress and identifying capabilities ready for real-world deployment.

cs.RO↗

Efficient Multi-Robot Motion Planning for Manifold-Constrained Manipulators by Randomized Scheduling and Informed Path Generation

Multi-robot motion planning for high degree-of-freedom manipulators in shared, constrained, and narrow spaces is a complex problem and essential for many scenarios such as construction, surgery, and more. Traditional coupled methods plan directly in the composite configuration space, which scales poorly; decoupled methods, on the other hand, plan separately for each robot but lack completeness. Hybrid methods that obtain paths from individual robots together require the enumeration of many paths before they can find valid composite solutions. This paper introduces Scheduling to Avoid Collisions (StAC), a hybrid approach that more effectively composes paths from individual robots by scheduling (adding stops and coordination motion along all paths) and generates paths that are likely to be feasible by using bidirectional feedback between the scheduler and motion planner for informed sampling. StAC uses 10 to 100 times fewer paths from the low-level planner than state-of-the-art hybrid baselines on challenging problems in manipulator cases.

cs.RO↗

Object-Centric Kinodynamic Planning for Nonprehensile Robot Rearrangement Manipulation

Nonprehensile actions such as pushing are crucial for addressing multi-object rearrangement problems. Many traditional methods generate robot-centric actions, which differ from intuitive human strategies and are typically inefficient. To this end, we adopt an object-centric planning paradigm and propose a unified framework for addressing a range of large-scale, physics-intensive nonprehensile rearrangement problems challenged by modeling inaccuracies and real-world uncertainties. By assuming each object can actively move without being driven by robot interactions, our planner first computes desired object motions, which are then realized through robot actions generated online via a closed-loop pushing strategy. Through extensive experiments and in comparison with state-of-the-art baselines in both simulation and on a physical robot, we show that our object-centric planning framework can generate more intuitive and task-effective robot actions with significantly improved efficiency. In addition, we propose a benchmarking protocol to standardize and facilitate future research in nonprehensile rearrangement.

cs.RO↗

Collision-Inclusive Manipulation Planning for Occluded Object Grasping via Compliant Robot Motions

Robotic manipulation research has investigated contact-rich problems and strategies that require robots to intentionally collide with their environment, to accomplish tasks that cannot be handled by traditional collision-free solutions. By enabling compliant robot motions, collisions between the robot and its environment become more tolerable and can thus be exploited, but more physical uncertainties are introduced. To address contact-rich problems such as occluded object grasping while handling the involved uncertainties, we propose a collision-inclusive planning framework that can transition the robot to a desired task configuration via roughly modeled collisions absorbed by Cartesian impedance control. By strategically exploiting the environmental constraints and exploring inside a manipulation funnel formed by task repetitions, our framework can effectively reduce physical and perception uncertainties. With real-world evaluations on both single-arm and dual-arm setups, we show that our framework is able to efficiently address various realistic occluded grasping problems where a feasible grasp does not initially exist.

cs.RO↗

B4P: Simultaneous Grasp and Motion Planning for Object Placement via Parallelized Bidirectional Forests and Path Repair

Robot pick and place systems have traditionally decoupled grasp, placement, and motion planning to build sequential optimization pipelines with the assumption that the individual components will be able to work together. However, this separation introduces sub-optimality, as grasp choices may limit or even prohibit feasible motions for a robot to reach the target placement pose, particularly in cluttered environments with narrow passages. To this end, we propose a forest-based planning framework to simultaneously find grasp configurations and feasible robot motions that explicitly satisfy downstream placement configurations paired with the selected grasps. Our proposed framework leverages a bidirectional sampling-based approach to build a start forest, rooted at the feasible grasp regions, and a goal forest, rooted at the feasible placement regions, to facilitate the search through randomly explored motions that connect valid pairs of grasp and placement trees. We demonstrate that the framework's inherent parallelism enables superlinear speedup, making it scalable for applications for redundant robot arms (e.g., 7 Degrees of Freedom) to work efficiently in highly cluttered environments. Extensive experiments in simulation demonstrate the robustness and efficiency of the proposed framework in comparison with multiple baselines under diverse scenarios.

cs.RO↗

Wearable Roller Rings to Augment In-Hand Manipulation through Active Surfaces

In-hand manipulation is a crucial ability for reorienting and repositioning objects within grasps. The main challenges in this are not only the complexity of the computational models, but also the risks of grasp instability caused by active finger motions, such as rolling, sliding, breaking, and remaking contacts. This paper presents the development of the Roller Ring (RR), a modular robotic attachment with active surfaces that is wearable by both robot and human hands to manipulate without lifting a finger. By installing the angled RRs on hands, such that their spatial motions are not colinear, we derive a general differential motion model for manipulating objects. Our motion model shows that complete in-hand manipulation skill sets can be provided by as few as only 2 RRs through non-holonomic object motions, while more RRs can enable enhanced manipulation dexterity with fewer motion constraints. Through extensive experiments, we test the RRs on both a robot hand and a human hand to evaluate their manipulation capabilities. We show that the RRs can be employed to manipulate arbitrary object shapes to provide dexterous in-hand manipulation.

cs.RO↗

rt-RISeg: Real-Time Model-Free Robot Interactive Segmentation for Active Instance-Level Object Understanding

Successful execution of dexterous robotic manipulation tasks in new environments, such as grasping, depends on the ability to proficiently segment unseen objects from the background and other objects. Previous works in unseen object instance segmentation (UOIS) train models on large-scale datasets, which often leads to overfitting on static visual features. This dependency results in poor generalization performance when confronted with out-of-distribution scenarios. To address this limitation, we rethink the task of UOIS based on the principle that vision is inherently interactive and occurs over time. We propose a novel real-time interactive perception framework, rt-RISeg, that continuously segments unseen objects by robot interactions and analysis of a designed body frame-invariant feature (BFIF). We demonstrate that the relative rotational and linear velocities of randomly sampled body frames, resulting from selected robot interactions, can be used to identify objects without any learned segmentation model. This fully self-contained segmentation pipeline generates and updates object segmentation masks throughout each robot interaction without the need to wait for an action to finish. We showcase the effectiveness of our proposed interactive perception method by achieving an average object segmentation accuracy rate 27.5% greater than state-of-the-art UOIS methods. Furthermore, although rt-RISeg is a standalone framework, we show that the autonomously generated segmentation masks can be used as prompts to vision foundation models for significantly improved performance.

cs.RO↗

Robust Peg-in-Hole Assembly under Uncertainties via Compliant and Interactive Contact-Rich Manipulation

Robust and adaptive robotic peg-in-hole assembly under tight tolerances is critical to various industrial applications. However, it remains an open challenge due to perceptual and physical uncertainties from contact-rich interactions that easily exceed the allowed clearance. In this paper, we study how to leverage contact between the peg and its matching hole to eliminate uncertainties in the assembly process under unstructured settings. By examining the role of compliance under contact constraints, we present a manipulation system that plans collision-inclusive interactions for the peg to 1) iteratively identify its task environment to localize the target hole and 2) exploit environmental contact constraints to refine insertion motions into the target hole without relying on precise perception, enabling a robust solution to peg-in-hole assembly. By conceptualizing the above process as the composition of funneling in different state spaces, we present a formal approach to constructing manipulation funnels as an uncertainty-absorbing paradigm for peg-in-hole assembly. The proposed system effectively generalizes across diverse peg-in-hole scenarios across varying scales, shapes, and materials in a learning-free manner. Extensive experiments on a NIST Assembly Task Board (ATB) and additional challenging scenarios validate its robustness in real-world applications.

cs.RO↗

Caging in Time: A Framework for Robust Object Manipulation under Uncertainties and Limited Robot Perception

Real-world object manipulation has been commonly challenged by physical uncertainties and perception limitations. Being an effective strategy, while caging configuration-based manipulation frameworks have successfully provided robust solutions, they are not broadly applicable due to their strict requirements on the availability of multiple robots, widely distributed contacts, or specific geometries of robots or objects. Building upon previous sensorless manipulation ideas and uncertainty handling approaches, this work proposes a novel framework termed Caging in Time to allow caging configurations to be formed even with one robot engaged in a task. This concept leverages the insight that while caging requires constraining the object's motion, only part of the cage actively contacts the object at any moment. As such, by strategically switching the end-effector configuration and collapsing it in time, we form a cage with its necessary portion active whenever needed. We instantiate our approach on challenging quasi-static and dynamic manipulation tasks, showing that Caging in Time can be achieved in general cage formulations including geometry-based and energy-based cages. With extensive experiments, we show robust and accurate manipulation, in an open-loop manner, without requiring detailed knowledge of the object geometry or physical properties, or real-time accurate feedback on the manipulation states. In addition to being an effective and robust open-loop manipulation solution, Caging in Time can be a supplementary strategy to other manipulation systems affected by uncertain or limited robot perception.

cs.RO↗

ARC-Calib: Autonomous Markerless Camera-to-Robot Calibration via Exploratory Robot Motions

Camera-to-robot (also known as eye-to-hand) calibration is a critical component of vision-based robot manipulation. Traditional marker-based methods often require human intervention for system setup. Furthermore, existing autonomous markerless calibration methods typically rely on pre-trained robot tracking models that impede their application on edge devices and require fine-tuning for novel robot embodiments. To address these limitations, this paper proposes a model-based markerless camera-to-robot calibration framework, ARC-Calib, that is fully autonomous and generalizable across diverse robots and scenarios without requiring extensive data collection or learning. First, exploratory robot motions are introduced to generate easily trackable trajectory-based visual patterns in the camera's image frames. Then, a geometric optimization framework is proposed to exploit the coplanarity and collinearity constraints from the observed motions to iteratively refine the estimated calibration result. Our approach eliminates the need for extra effort in either environmental marker setup or data collection and model training, rendering it highly adaptable across a wide range of real-world autonomous systems. Extensive experiments are conducted in both simulation and the real world to validate its robustness and generalizability.

cs.RO↗