Overview

Robotic manipulation studies how machines use sensing and motion to change objects and environments, from picking and assembly to tool use and handling deformable materials. Approaches combine geometric planning and force or impedance control with imitation learning, reinforcement learning, diffusion policies, and vision-language-action models; world models, memory, tactile feedback, and human-video demonstrations are also used. Methods are tested in simulation and on real robots using suites such as LIBERO, RoboTwin, ManiSkill, and RLBench, across clutter, bimanual coordination, mobile manipulation, and precision contact tasks. A central challenge is turning benchmark performance into safe, reliable long-horizon behavior across new objects, cameras, robot bodies, and real-world dynamics, while limiting data collection and inference costs.

Latest papers

1,805 papers244 papers in the last four weeks, down 37% on the four weeks before. 1.7% of all new papers.

Nov 2, 2026

When Robots Outweigh Objects: How Inertia Mismatch Shapes Robot Policy Learning

Conventional robot arms can be extremely heavy compared with the everyday objects they manipulate, creating a significant inertia mismatch at contact. Even a small accidental bump from a heavy arm can knock a light object out of place. Modern learning methods have nevertheless demonstrated a wide range of successful manipulation behaviors on these platforms, suggesting that even extreme inertia mismatch can be overcome with sufficient data. However, it remains unclear whether high inertia imposes a hidden cost on learning, potentially worsening scaling with data or lowering the performance ceiling of modern robot learning methods. We investigate this question through controlled simulation experiments that vary robot and object masses. We find that reinforcement learning succeeds across a broad range of mass combinations, while behavior cloning learns more reliable policies when a lighter robot manipulates a heavier object. Heavier robots require more demonstrations to attain the same performance as lighter robots. Finally, because new hardware is rarely an option, we explore ways to lower an existing arm's inertia at contact with existing hardware, either by choosing a lower-inertia workspace before collecting data or by steering the demonstrator toward lower-inertia configurations during the task. In both cases, the lower-inertia demonstrations are imitated more reliably. Project website: https://younghyopark.me/inertia-mismatch/
Nov 2, 2026

Exploring Proximity and Tactile Sensing for Robotic Manipulation

Pre-touch sensing, or sensing information about an object before contact, is an attractive modality for robot hands as it can allow a robot to anticipate and respond to a contact before it happens. In this work, we introduce ToFTouch, a multimodal tactile sensor combining three multizone (4×\times4 resolution) time-of-flight sensors with an optics-based pressure sensing array. We mount this sensor on a parallel jaw gripper and demonstrate its utility on three distinct tasks: (i) pre-grasp adjustment, (ii) item extraction from clutter, and (iii) item insertion into tight spaces. For pre-grasp adjustment, ToF feedback reduced cycle time by 7.4%\% by enabling anticipatory gripper closure during approach. For extraction, ToF sensing enabled successful retrieval across all tested depth offsets (±\pm2 cm) deviating from the nominal pick point, including conditions where baseline approaches failed, with standard deviations below 0.4 cm. For insertion into dense clutter, we explore the proximity and tactile information provided from ToFTouch during an insertion trajectory. The results demonstrate the utility of multizone ToF sensing in a manipulation environment.
Nov 2, 2026

VerifLM: Physically Verified Image-Edit-Guided Goal Pose Generation for Robotic Manipulation

Many manipulation goals are easier to visualize than to specify numerically through explicit geometric constraints. We present VerifLM, a framework that converts image-edited goal configurations into physically verified 6-DoF object poses for planning. Using an edited image, VerifLM recovers an initial relative pose between an active object and a passive object, then prompts a vision-language model to generate axis-wise sampling constraints and a task-specific validation program. Candidate poses are evaluated in a physics simulator, and the VLM selects the most task-consistent retained candidate. To operate without predefined object meshes or physical parameters, VerifLM reconstructs metric object geometry from RGB-D observations and constructs multiple hypothetical simulations with varying physics and geometry. Parallel-world validation evaluates candidates across geometry--physics variations and ranks them by the number of worlds in which they satisfy the validation program. We evaluate VerifLM on nine manipulation tasks. VerifLM achieves the highest task success on eight of nine tasks, with the largest performance gain on goals requiring precise orientation and contact relationships.
Nov 2, 2026

FineCraft: Enhancing VLA Models for Fine-Grained Manipulation

Fine-grained manipulation couples instruction grounding, local visual precision, and sustained execution. We present FineCraft, a framework that adapts pretrained models for fine-grained manipulation in the MetaFine Challenge. A task-routed mixture of policies selects independently adapted DINOv2-DiT or pretrained π0.5π_{0.5} policies through a common observation-action interface. Local visual features help identify the instructed object parts, demonstrations and expert continuations teach the required actions, and new observations guide replanning during execution. FineCraft ranks fourth with an overall score of 0.8780.878, exceeding the published reference on all five tasks. Official results and local diagnostics characterize performance across visual perturbations, instruction changes, and multi-stage manipulation. Code is available at https://github.com/eqcy/FineCraft
Nov 2, 2026

BeyondContact: A Reinforcement Learning Framework for Airflow-Based Non-Contact Manipulation

Contact-based robotic manipulation is constrained by end-effector reachability and the mechanical properties of objects. Airflow can exert forces without direct robot-object contact, enabling manipulation of objects beyond the reach or when direct contact is undesirable. However, the lack of suitable simulation has hindered the application of reinforcement learning to airflow-based manipulation, limiting the broader adoption of this mechanism compared with contact-based methods. To address this gap, we developed a robot- and task-agnostic airflow extension for Isaac Lab that supports massively parallel training. The extension uses experimentally identified airflow models to compute the forces and torques exerted on objects. Based on this extension, we train a hybrid push-blow (HPB) policy that combines contact-based pushing with airflow manipulation and a rectangular reorientation (RR) policy that controls a cuboid's heading using airflow alone. To enable physical execution, we design a lightweight, high-speed blower that coexists with a gripper. In zero-shot real-world deployment, HPB achieves an 80% success rate over 20 trials, while RR achieves a mean absolute heading error of 2.6 degrees across four target headings. The project materials are available at https://github.com/iit-DLSLab/BeyondContact.
Nov 2, 2026

PointPilot: Unified Robotic Manipulation via Object-Centric 3D Point Flow Prediction

Generalization remains a central challenge in robotics, calling for policies that address domain variations from multiple dimensions such as diverse embodiments, camera poses, and/or scene layouts. In order to approach this problem, we introduce PointPilot, a task-focused and 3D aligned manipulation framework built on a 3D space point-flow prediction. Rather than modeling the global scene, PointPilot only represents task-focused objects (robot grippers treated as objects), avoiding the prediction of potentially redundant scene parts unrelated to the manipulation tasks. Moreover, PointPilot aligns 3D spatial representation in one unified coordinate and supports closed-loop and fully automatic action execution across different manipulation modes from object point flow without a separately trained action expert, while existing works typically need an extra action head or are (semi-)automatic and single-arm mode specific. Given sensor observations and language instructions, our model jointly learns subtask planning, task-relevant object grounding, and 3D point flow prediction in an end-to-end way. By processing heterogeneous data in a shared 3D point flow space, PointPilot is able to absorb demonstrations from different embodiments. Extensive simulative and real world experiments validate our method. Notably, we demonstrate zero-shot embodiment generalization with PointPilot. A single trained policy can be deployed on previously unseen embodiments and successfully complete manipulation tasks without any additional fine-tuning.
Nov 2, 2026

ReGATE: Recurrent Gated Visual Fusion for Reactive Humanoid-Object Interaction

Humanoid loco-manipulation requires coordinating object acquisition, transport, and release from onboard sensing while responding to user commands and incomplete visual observations. We present ReGATE, a whole-body controller that combines egocentric depth, proprioception, and online locomotion and contact commands. Built on a teacher-student framework, ReGATE integrates interaction-state estimation through a recurrent adapter that predicts object geometry and physical contact without an external object-pose estimator. Head-wise and global gates regulate visual updates to a proprioceptive pathway. A visual-grounding and corruption curriculum trains the adapter, while phase-aware initialization increases coverage of brief contact transitions. In simulation, ReGATE achieves 85.2% success across 330 static-object acquisition trials, compared with 48.5% for VisualMimic under the same protocol, and 85.9% across 440 moving-object acquisition trials. Deployment on a Unitree G1 demonstrates commanded grasp-transport-release sequences and acquisition of laterally displaced boxes. A qualitative hardware experiment further demonstrates successful box acquisition when the camera is occluded after an initial observation and before the contact command. To the best of our knowledge, this is the first work to extend recurrent gated fusion of onboard depth and proprioception from perceptive locomotion to humanoid loco-manipulation under interrupted visual sensing.
Nov 2, 2026

Beyond Policy Patches: Distilling RL Specialists into Vision-Language-Action Policies

Vision-language-action (VLA) policies can handle noncritical stages of long-horizon manipulation yet fail during short precision-critical phases. Lightweight reinforcement learning (RL) specialists can address these failures without directly applying RL to the full VLA, but retain auxiliary controllers and switching mechanisms at deployment. We study how to transfer their capabilities into a single flow-matching VLA. Direct imitation of specialist rollouts can reproduce action jitter and leave the VLA unprepared for states encountered during its own execution. We introduce REPAIR, a value-guided distillation framework that combines offline initialization with on-policy refinement. At each critical-phase observation, REPAIR queries the corresponding specialist for multiple action candidates and weights them using its critic to construct a supervision distribution. A shared weighted flow-matching objective trains the VLA first on observations from specialist-assisted rollouts, then on observations collected through its own execution. Specialists provide supervision without taking control during on-policy collection and are removed at deployment. Across six real-robot tasks with 30 evaluation trials per task, REPAIR achieves 100% success on all six tasks, with lower mean end-effector jerk than specialist-assisted execution on every task.
Nov 2, 2026

Visuo-tactile Diffusion Policy for Robotic Manipulation with Auxiliary Tactile Dynamics Prediction

Long-horizon robotic assembly requires reliable perception and action across grasping, alignment, and insertion. Vision captures global object pose and scene context, where as fingertip touch provides local contact cues that are especially useful as contact states change. We present a visuotactile diffusion policy that combines four-step histories from two camera views and two fingertip tactile images to condition action-sequence generation. A recurrent temporal representation integrates recent observations from both modalities. To encourage it to capture how contact evolves under action, an auxiliary objective predicts fingertip-image changes two steps ahead from the temporal representation and demonstrated actions. This objective is used only during training and adds no inference-time computation. Across three independent training seeds in MuJoCo assembly experiments, the full model achieves an average success rate of 59.0%±2.6%59.0\% \pm 2.6\%, improving on the visual-only baseline (42.7%±1.5%42.7\% \pm 1.5\%) by 16.3 percentage points.
Nov 2, 2026

DexArena: A Unified Benchmark for Long-Horizon Dexterous Manipulation

Long-horizon dexterous manipulation remains a fundamental challenge for robot learning, requiring the composition of multiple skills, precise bimanual coordination, generalizable visual understanding, and robust skill transitions. Yet existing manipulation benchmarks largely emphasize isolated skills or support only a limited range of end-effectors, making these capabilities difficult to evaluate systematically. We introduce DexArena, a benchmark designed to evaluate learning and generalization in long-horizon bimanual dexterous manipulation. DexArena features 10 long-horizon tasks and 30 stage-level tasks spanning diverse household and industrial scenarios. Each long-horizon task is composed of explicitly defined stages with physically grounded success conditions, enabling reliable evaluation of both intermediate progress and end-to-end task completion. A unified benchmark interface and verified human-teleoperated demonstrations enable testing different policy learning algorithms, with standardized simulation configurations, scene randomization, trajectory replay, and task-level evaluation. Through extensive baseline experiments, we identify substantial challenges in precise manipulation, generalization to scene variation, and skill composition. DexArena establishes a challenging and reproducible benchmark for developing robot learning methods that move toward generalizable long-horizon dexterous behavior.
Nov 2, 2026

W2A: Distilling World Priors into Action Models for Real-Time Robotic Control

World Action Models (WAMs) have recently shown great promise in robotic control, benefiting from the future imagination capability of large-scale pretrained video models. However, most existing WAMs require explicitly imagining future states at test time, incurring substantial computational overhead and latency that make them unsuitable for real-time robotic control. In this paper, we propose W2A, a two-stage distillation framework for real-time robotic manipulation that distills intermediate denoising representations from a video diffusion model into an action model during training, while entirely discarding the video model at test time. We hypothesize that although video latent representations are high-dimensional, a compressed low-dimensional subspace is sufficient to provide effective supervision for action generation. This makes it possible to transfer such information effectively into an action model. Extensive experiments in both simulation and real-world settings demonstrate competitive success rates while significantly improving inference efficiency. On LIBERO, W2A achieves a 95.9% average success rate. More importantly, W2A achieves about 21x faster inference than the representative WAM baseline.
Nov 2, 2026

Gnomon4D: Learning Where and When to Focus for Geometric Motion-Grounded World-Action Modeling

World-action models (WAMs) predict scene changes to guide robot actions, yet their RGB futures entangle state changes with appearance and lack 3D geometry. Recent WAMs add geometry as a training signal or a control interface, or build native 3D models, but decide what geometry to model rather than how the action should read it. Intuitively, control-relevant cues lie at embodiment--object interactions and their transitions, yet probing existing WAMs reveals that their action attention underweights these interactions in favor of the rest of the embodiment. To focus the action on these interactions, we present Gnomon4D, a WAM that jointly generates future video, robot actions, and GeoDelta, a video-aligned 4D geometric motion field recording the image-plane displacement and depth change of embodiment and object points. With the embodiment and objects in one field, their relative motion, which marks an interaction, can be read off. Guided by this motion and the task, Interaction-Salient Attention (InSAttn) selects where the action reads, and Transition-Anchored Aggregation (TransAgg) selects when, around grasp and release. As GeoDelta encodes surface motion rather than embodiment-specific controls, it serves as a human--robot quasi-action that links action-free pretraining on EgoManip-5000H, which we curate, to robot mid-training on Robot-30H. Gnomon4D leads on RoboTwin~2.0, VLABench, and RoboDojo, and outperforms real-robot baselines, especially under visual shifts. Project page: https://droliven.github.io/Gnomon4D.
Oct 31, 2026

Shades of Success: Evaluating Manipulation Quality from Object-Centric Constraints

As learned manipulation policies become increasingly capable of solving practical manipulation tasks, assessing how well a task is performed becomes a fundamental challenge. While binary labels confirm task success, they cannot distinguish successful executions with different levels of geometric precision. To address this, we introduce SPECTRA, an object-centric framework for quantifying execution quality in manipulation of rigid objects. From a small set of oracle demonstrations generated in simulation, SPECTRA represents object interactions through progress-aligned relative poses. SPECTRA identifies which relative-pose directions are constrained and their admissible variations from demonstrations. These constraints establish a reference for evaluating robotic manipulation tasks. To score an unseen execution, deviations beyond the admissible variation are summarized by a Task Quality Index Q in [0,1]. Across seven simulated tasks, SPECTRA recovers constraints with 94% accuracy using 30 demonstrations per task. On rollouts from three learned policies, its scores achieve pooled Spearman correlations with human judgments of p=0.81 over all rollouts and p=0.61 among successful rollouts, exceeding all baselines in both subsets. Using the task reference learned in simulation, we use SPECTRA to select the highest-scoring demonstrations for training a diffusion policy on hardware. Exploratory results show higher success rate than training on randomly selected demonstrations.
Oct 31, 2026

ClothDojo: Learned Data Generation and Benchmarking for Bimanual Garment Flattening and Folding

Garment flattening and folding require robots to identify garment structure during manipulation and adapt their actions as the cloth deforms. We present ClothDojo, a simulation platform that generates adaptive manipulation trajectories at scale across diverse garments and initial states and evaluates policies in closed loop. ClothDojo encodes each garment's canonical mesh coordinates as an NOCS texture, providing canonical surface-position cues through the visual interface of a pretrained vision-language-action model. We fine-tune the model on human demonstrations and corrections to obtain a data-generation policy. The policy autonomously generates simulated manipulation trajectories, and we retain rollouts that satisfy task-specific success criteria. Each retained trajectory is re-rendered under a randomly sampled appearance to provide RGB observations for downstream policies that do not receive NOCS. Across both tasks, the policy produces nearly 8,000 successful trajectories over hundreds of garments. RGB policies trained on these generated trajectories outperform those trained directly on the original human demonstrations and corrections across all evaluated garment splits and appearance settings. Evaluations across multiple policy models show that overall performance and appearance robustness vary across models and tasks, while generalization to unseen garments remains a common challenge.
Oct 31, 2026

Task-Specialized Language-Conditioned Models for Fine-Grained Robotic Manipulation

Fine-grained robotic manipulation requires instruction grounding, robust perception, and precise contact control. We describe our submission to the MetaFine Open Competition at CoRL 2026. Five independently trained models use a common architecture with frozen DINOv2 and CLIP encoders, trainable language-conditioned feature modulation, and task-specific action heads. We improve demonstrations through contact-aware grasp filtering, instruction-matched data, and expert correction of insertion failures. At inference, task-dependent strategies include photometric test-time augmentation, stochastic action averaging, and uncertainty-triggered replanning. Our submission achieves an official overall score of 0.914 and ranks third among 15 teams. We analyze the models and their task-specific behavior.
Oct 31, 2026

Trading Transparency for Stability: Friction-Cone-Constrained Bilateral Teleoperation for Opening Doors of Unsecured Furniture

Opening the door of unsecured furniture loads the frictional contacts at its supports; too large a pull slides or tips the object. A friction-cone constraint on the commanded wrench removes this failure mode but costs haptic transparency. We quantify the trade-off: an admissible wrench set built from contact friction cones and support-polygon tipping margins is shrunk for robustness to bounded mass and friction errors, and any command in the shrunken set provably leaves the furniture static (Prop. 1). We call this map the robust friction cone projection (RFCP). RFCP and its haptic guard admit a bounded force transmission error (Prop. 2): transparency degrades only within a band near the constraint boundary, whose width is set by one scalar, the stability factor . A working condition controller handles the door: the operator commands a scalar swing amplitude, the slave orientation follows hinge kinematics, and the grasp wrench is regulated per phase. A pre task certificate decides whether a door can be opened without moving the furniture. Experiments on three cabinets and two supports with five operators (100 trials) measure the stability transparency trade-off and ablate the guard, RFCP and the position baseline. The mechanism is not door-specific: it applies to any body reacted by frictional contacts.
Oct 31, 2026

PREM: Prediction-Regulated Memory for Robot Manipulation

A robot's next action can depend on recent motion or earlier visual evidence absent from its current observation. A recurrent visual-memory architecture can retain this history in a visual state, but its usefulness depends on what the state represents and how it is updated with new observations. We introduce Prediction-Regulated Memory (PREM), a framework that uses action-conditioned future prediction to guide both memory learning and updating in vision-language-action policies. During training, predicting future visual features provides temporal supervision for memory learning. During execution, PREM compares current visual features with the prediction made at the preceding decision and uses the spatially normalized prediction discrepancy to regulate updates to the visual state at each spatial location. The updated visual state supplies temporal context for action generation alongside current observations. Built on π0.5π_{0.5}, PREM improves average success rate from 9.63% to 20.74% on DOMINO dynamic manipulation tasks and from 14.4% to 83.8% on the RMBench M(1) memory-dependent setting. Further evaluations on LIBERO and LIBERO-Pro show improvements in general manipulation and robustness to spatial perturbations. PREM incurs a mean inference overhead of 7.7 ms on a single NVIDIA H800 GPU.
Oct 31, 2026

Learning from an Imitable Teacher: Competition Solution for the MetaFine Challenge

The MetaFine Open Competition (RoboFineMani workshop, CoRL 2026) evaluates fine-grained manipulation beyond binary success. Its five simulated tasks, from grasping a bottle by an instructed part to inserting letter-shaped pegs with 4 mm clearance, are scored on perception under lighting and camera changes, instruction understanding, and behavior. This report presents Team Friday's solution, which got second place with an overall score of 0.947, more than twice the π0π_0 baseline. Instead of fine-tuning a large vision-language-action (VLA) model, we train one 19M-parameter policy per task with a separate instruction classifier and focus on the data, all generated in the simulator by a privileged scripted teacher, including its corrections of the student's mistakes. By analyzing failed episodes, we find that a teacher that almost always succeeds can still teach a memoryless student badly: its pauses become stalls, its fixed habits become shortcuts, and it never shows the errors the student makes. Making the teacher imitable raised the official score on letter insertion, the hardest task, from 0.44 to 0.82 with 32% more data and the same architecture, and finally to 0.88. We summarize practical lessons on demonstration data and evaluation, which we hope will help in imitation learning for precise manipulation.
Oct 30, 2026

Does Validation Loss Predict Real-Robot Success? Evidence from Four Imitation-Learning Policies on a Low-Cost Arm

Held-out validation loss is the standard offline signal for choosing checkpoints and comparing models, but its relation to closed-loop success on a real robot is rarely measured. We measure it for ACT, Diffusion Policy, SmolVLA and π0.5π_{0.5} (action expert only), trained on nested subsets of 12 to 200 demonstrations of a pick-and-place task on an SO-101 arm. We score 82 checkpoints on 25 held-out demonstrations, with each policy's training loss and with the error of the actions it outputs, and compare the scores with 930 bench rollouts. We also score all 700 intermediate checkpoints of 70 training runs, and recover the ball positions of every training, held-out and bench episode from the front camera. Within each policy, hold-out action error correlates with bench success (Spearman ρρ from -0.23 to -0.88), but no more strongly than the number of training episodes alone, and not at all among seeds trained on the same data. Across policies the ranking is inverted (ρρ = +0.90 at 200 episodes): the policy with the lowest hold-out error succeeded in 3 of 110 rollouts. The most common failure, the arm never leaving its rest pose, ended 96% of rollouts for Diffusion Policy trained on untrimmed demonstrations and 47% for SmolVLA, and cannot occur in a hold-out set made of demonstrations. Among rollouts in which the arm moved, SmolVLA's hold-out action error predicts success well (ρρ = -0.81). For the diffusion and flow-matching policies, hold-out loss rises two- to five-fold during training while hold-out action error falls by up to 29%. Held-out metrics are a sound diagnostic of learning but no substitute for evaluation on the robot, and we recommend reporting initiation failure and success among started rollouts as separate bench outcomes.
Oct 30, 2026

OmniPiano: Diverse Dexterous Piano-Playing Challenges for Standard, Robust, Safe, and Multi-Agent RL

Dexterous robotic manipulation remains a major challenge in robotics, exemplified by piano playing, which requires coordinated control of fingers and provides a demanding testbed for reinforcement learning (RL). Although previous work established a benchmark for robotic piano playing, it is restricted to two hands and does not support unified evaluation. To address this gap, we introduce OmniPiano, a benchmark that provides one to up to five Shadow Hands and supports standard, robust, safe, and multi-agent RL within a shared piano-playing task family. OmniPiano is developed for scalable and diverse piano-playing tasks with configurable perturbations, explicit safety constraints, and decentralized cooperation settings. Particularly, to facilitate usability and extendability, OmniPiano adopts a highly modular design and provides comprehensive tasks to support RL study of task performance, robustness, safety, and cooperation in dexterous control. With at least 912 task settings and 36 baseline algorithms, OmniPiano further incorporates LLM-based agents to broaden the evaluation scope and reveal new insights. Extensive evaluations show that state-of-the-art RL algorithms and frontier LLM-based agents still struggle on challenging piano-playing tasks, even under standard RL settings, highlighting substantial room for improvement in dexterous control. The code, dataset, tutorial, and demo are available at https://sail-research-lab.github.io/omnipiano/.
Oct 30, 2026

RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory

Recent work shows that a frozen robot policy performs far better inside an agent harness, where control code decides when to query the policy, consult vision tools, or command the arm directly. Yet today these harnesses are built by hand and redesigned for each new robot or benchmark. We show that harness design can be automated, offering a strong alternative to finetuning on a novel setup. In RoboArchitect, a coding model observes a robot's rollouts, diagnoses failures, and iteratively revises the harness around the frozen policy. The harness evolves on a set of episodes for its optimization and is evaluated on held-out scenes and tasks. Without updating any model weights, RoboArchitect raises average success from 9.7% to 43.3% on unseen scenes (4.5x) and from 12.7% to 40.2% on unseen tasks (3.2x), across multiple benchmarks and policies. The gains are largest where the benchmark is far from the policy's training data: wrapping a general-purpose policy, the evolved harness yields a specialist that often outperforms even the finetuned version. Intuitive control strategies are automatically designed, such as lifting a jammed arm clear or reaching in horizontally when an obstacle blocks the way from above. The harness also evolves its own persistent memory, carrying learned experience, such as effective grasp depths, into later decisions. These results suggest that substantial headroom in robotic manipulation lies in the agent harness, and its design can be effectively automated and optimized without weight updates.
Oct 30, 2026

Suspended-Fabric Robotic Manipulation Surfaces: Modelling, Design Space, and Multimodular Extensio

Robotic Manipulation Surfaces (RMS) reposition objects by deforming the surface on which they rest. A recent class of RMS suspends a continuous fabric sheet from a sparse grid of vertical linear actuators lowering the actuator density of such surfaces but how to design such surfaces so that objects can be controlled everywhere on it, and how to extend it beyond a single module so that objects can pass between modules and achieve parallel, remain open. This paper presents a separable catenary model of the suspended sheet that is fast to compute and provides both the surface shape for given actuator heights and the actuator heights for a desired local slope. The closed form inverse lets a simple PID controller position objects on the sheet, and the model relates fabric length, module span and actuator stroke to the reachable workspace, yielding a minimum fabric length bound and design charts for these surfaces. The approach is then extended to a multimodular platform in which neighbouring modules share actuators. On a 2×22 \times 2 prototype, we demonstrate that centimetre-scale objects are transferred between modules and positioned within 0.03 m over a 1m21 m^2 workspace with only nine actuators, enabling multi-object manipulation and opening the way to parallel manipulation.
Oct 30, 2026

SketchMate: Agentic Geometric Reasoning for Zero-Shot Precision Insertion

Inserting an unseen part requires sub-millimetre precision and the correct orientation of keyed features. Current zero-shot agentic manipulation methods built on vision-language models (VLMs) produce spatial outputs that are far too coarse for this. We propose to let a VLM build a sketch model of the task, i.e., a few geometric primitives and two mate frames, which a VLM agent measures with geometric tools in multi-view depth and which a standard planner and compliant controller execute. Because a sketch describes the parts independently of their placement, the robot needs to build it only once per task. A sketch memory stores each agent run and transfers the stored sketch to later placements by point-cloud registration, so that the VLM is called only for unfamiliar parts. After grasping the part, the robot inspects both mating faces at close range and corrects the sketch by shape matching. On 69 simulated insertion episodes, our method inserts 88% of the parts at the assembled pose in a strict kinematic test, while ReKep and MOKA with the same VLM insert none. On new placements of eight tasks, reusing one stored run inserts as many parts as calling the agent in each episode, and it produces the sketch in 3.4 s instead of about 90 s.
Oct 30, 2026

Flexibility-Aware Robotic Manipulation: Deformation Estimation, Kinematics, and Control via Distributed Inertial Measurement

Flexible robot links challenge the rigid-body assumption, making joint measurements alone insufficient for accurate manipulation. This paper introduces a flexibility-aware manipulation framework that connects structural dynamics directly to sensing, kinematics, and control. Instead of prescribing a dense inertial measurement unit (IMU) network, the dominant vibration modes of each flexible link are first identified from response-convergence and excitation-bandwidth criteria. Under a full-rank modal observability condition, mm retained modes require only mm independent slope measurements and one reference IMU, defining the minimum observable IMU configuration. The resulting measurements are used to reconstruct the continuous link deformation, which is then incorporated into flexibility-aware forward kinematics and a deformation-informed partial differential equation-based controller. Experiments on hydraulic single- and double-link manipulators evaluate the framework. On the long-reach double-link platform, the proposed kinematics achieves end-effector root mean square errors of 0.01070.0107~m, 0.01940.0194~m, and 0.01020.0102~rad while using fewer sensors than the piecewise-rigid method. Closed-loop reaching experiments further demonstrate real-time integration of IMU-estimated joint states and reconstructed deformation into the proposed controller. The results show that dominant modal information can determine sensing requirements and enable real-time flexibility-aware robotic manipulation.
Oct 30, 2026

RTPolicy: Real-Time (32.9 Hz) Multi-View Visuomotor Policy for Robotic Manipulation on Edge Devices

Low inference latency is critical for closed-loop robotic manipulation, especially under asynchronous inference, where action chunks must be updated promptly to correct accumulated deviations. However, existing visuomotor policies rely on computationally expensive visual backbones, resulting in high inference latency and deployment overhead. In this paper, we propose RTPolicy, a multi-view visuomotor policy that attains accurate manipulation with high inference efficiency. Its core design combines view-aware feature fusion with visual compression to aggregate complementary information across camera views into a compact token representation. The representation conditions a flow-matching action generator with the robot state and flow time, reducing the cost of action generation. Extensive experiments demonstrate that this design reduces the computational cost of visual representation and action generation while preserving visual information required for manipulation. On the RoboTwin~2.0 single-task clean evaluation across 50 tasks, RTPolicy attains a mean success rate of 52.26%, outperforming the strongest leaderboard baseline π0π_0 (46.4%). We further evaluate RTPolicy under asynchronous streaming inference on a real bimanual platform, where RTPolicy attains a mean success rate of 72.0% and sustains real-time inference at 30.35 ms (32.9 Hz) on the RDK S600 and 149.72 ms (6.7 Hz) on the RDK S100, both in INT16. Project Page: https://d-robotics-ai-lab.github.io/RTPolicy.project.
Oct 30, 2026

MolmoSpaces-CommonSense: Evaluating Commonsense in Robotic Manipulation Policies

Real-world robotic manipulation requires reasoning about cluttered scenes, partially observable or hidden objects, and semantically appropriate actions, in addition to low-level execution within those scenes. However, existing simulation benchmarks primarily test the latter and remain dominated by comparatively clean environments with limited clutter and narrowly scoped task structure, leaving many forms of commonsense reasoning untested. We address this by introducing a taxonomy of reasoning processes for robotic manipulation grounded in developmental cognitive science. We operationalize this taxonomy through a new benchmark of robot tasks, MolmoSpaces-CommonSense, that requires reasoning about occlusion, containment, support relations, semantically correct grasp points, spatial affordances, and hidden objects. These evaluations require policies not only to recognize relevant scene structure but also to execute correct actions in them. We evaluate several zero-shot generalist manipulation policies. Across model types and architectures, we observe consistent failures in commonsense reasoning: success rates in cluttered scenes drop by over 50% as distractors increase, policies act on incorrect objects in cluttered settings 30% of the time, and affordance-sensitive grasping remains unreliable even with highly specific language prompts, with correct object part selection happening only about 50% of the time. Further, VLM-based success estimation struggles to reliably evaluate rollouts in these settings, suggesting that the challenge extends beyond control to the broader perception-reasoning-action stack. Our results suggest that existing benchmarks may substantially overestimate zero-shot real-world readiness. Code and policy leaderboard link at https://github.com/allenai/molmospaces.
Oct 30, 2026

HandMimicX: Learning Human-Like Dexterous Manipulation via an Object-Centric Policy from Egocentric Videos

Learning dexterous manipulation from human videos remains an open challenge, particularly in the context of transferring a single demonstration into a spatially generalizable robotic skill and maintaining physically plausible human-like interactions. Unlike prior works that emphasize hand-motion imitation, we introduce an object-centric framework for acquiring dexterous skills from egocentric human RGB-D videos. Within our framework, we formulate the reinforcement learning (RL) objective in terms of object motion to decouple the underlying skill from the specific hand trajectory and impose constraints on hand-object interaction states to promote more anatomically natural hand configurations. Extensive experiments in simulation and on real robots demonstrate that our method enables efficient learning from human videos and generalizable skill transfer across novel spatial configurations.
Oct 30, 2026

Learning from Physical Experience:Context-Space Adaptation for Robotic Manipulation

Recent multimodal foundation models exhibit strong perception, reasoning, and in-context learning capabilities, but translating these capabilities into physical action remains challenging. Through real-world experiments across diverse manipulation tasks, we find that ChatGPT-6-Astra, a state-of-the-art general-purpose reasoner, can serve as a physically actionable, context-responsive manipulation policy, demonstrating effective fine manipulation and spatial reasoning. Building on these findings, we introduce LEXP, a harness for learning from physical experience through context-space adaptation. LEXP combines task-level planning with an experience module that interprets execution evidence, extracts and retains lessons with applicability conditions, and reuses relevant lessons to generate contextual feedback for subsequent actions. Model weights and the action interface remain fixed throughout. Across 12 real-world manipulation tasks, LEXP achieves 23/3623/36 successful trials (63.9%), compared with 19/3619/36 (52.8%) with memory alone and 2/362/36 (5.6%) for vanilla Astra. On three tasks, bread transfer, sort trash and toiletries, and retrieve drawer, removing planning reduces success from 7/97/9 to 4/94/9, while removing retained experience reduces it to 3/93/9. Execution traces illustrate feedback-guided corrections and cross-episode reuse of an inspection strategy. Execution analyses illustrate how task structure and experience-derived feedback guide task progression, action correction, and experience reuse. These results support context-space adaptation as a practical mechanism for turning physical interaction into reusable guidance for robotic manipulation.
Oct 30, 2026

TinyAstral: Transferring Self-Evolving Harnesses to Tiny Generalist Manipulation Agents

Robot agents built on vision-language models depend on both the planner and its harness: the tools, feedback, memory, and recovery logic around it. Can improvements to a large teacher's harness be carried into a compact agent with lower inference compute cost? We present TinyAstral, a two-stage approach. We first freeze an open-weight teacher and improve its harness through recursive self-improvement (RSI): frontier LLM agents read the teacher's trajectories and propose harness edits, and each edit is accepted only if it passes a paired statistical test. We then freeze the final harness, collect teacher trajectories with reasoning and failure recovery, and distill a small student that replaces the teacher in the same harness. On RoboTwin, harness evolution raises the teacher's success from 33.4% to 63.6%; the final 4B student reaches 62.8%. Across four harness versions, distilled 4B students score close to their corresponding teachers, and later versions yield stronger students, showing that harness evolution gains carry into compact models. The harness gains also transfer to other frozen planners without retraining. On identical episodes, the final 4B student outperforms open 4B agents, the open 27B harness-RSI model SenseNova-RoboRSI, and our own teacher model placed in three competitors' harnesses. It stays close to its teacher on all three training benchmarks, and on three benchmarks never used for RSI or training it scores close to a 552B planner running the same harness. On the measured deployment episodes, it uses about one fifth of its teacher's accelerator time. Project page: https://garfield-kh.github.io/TinyAstral/
Oct 29, 2026

Contact Imitation Interface: Transferring Dexterous Skills by Showing How Contact Unfolds

Robot-free human demonstrations offer a promising route to scaling dexterous manipulation data. The key challenge is to preserve the demonstrator's natural dexterity while producing contact-grounded observations and actions that transfer to robot hands. We present Contact Imitation Interface (CIMI), a framework with contact-grounded demonstration and learning interfaces. The demonstration interface combines shared contact geometry and fingertip RGB views with contact-alignment-first retargeting and reprojection of wider scene views. The learning interface introduces a hierarchical policy in which a contact-surface planner predicts relative contact-surface trajectories and a controller coordinates wrist and finger commands to improve contact alignment. CIMI combines contact-grounded observations, retargeting, and action representations, improving mean final-stage success by at least 50 percentage points over baseline policies across six hand-task pairs on LEAP and Wuji. Hardware designs and software are publicly available.