Long-Horizon Robotic Manipulation

Ask about this topic

Overview

Long-horizon robotic manipulation concerns tasks that require many dependent actions, such as assembling furniture, preparing food, or moving objects through changing environments. Common approaches combine hierarchical planning and reusable skills with vision-language-action policies, world models, symbolic task representations, and memory of past actions or object states. Researchers train these systems with demonstrations, reinforcement learning, simulated experience, and human corrections, and evaluate them in multi-stage benchmarks and real-robot settings. A central challenge is that strong performance on individual skills does not guarantee reliable task completion: errors can accumulate at skill transitions, while memory, recovery, and safety remain difficult to evaluate and generalize.

Latest papers

CardsList

435 papers88 papers in the last four weeks, up 49% on the four weeks before. 0.5% of all new papers.

Apr 6, 2026

ROSClaw: A Hierarchical Semantic-Physical Framework for Heterogeneous Multi-Agent Collaboration

The integration of large language models (LLMs) with embodied agents has improved high-level reasoning capabilities; however, a critical gap remains between semantic understanding and physical execution. While vision-language-action (VLA) and vision-language-navigation (VLN) systems enable robots to perform manipulation and navigation tasks from natural language instructions, they still struggle with long-horizon sequential and temporally structured tasks. Existing frameworks typically adopt modular pipelines for data collection, skill training, and policy deployment, resulting in high costs in experimental validation and policy optimization. To address these limitations, we propose ROSClaw, an agent framework for heterogeneous robots that integrates policy learning and task execution within a unified vision-language model (VLM) controller. The framework leverages e-URDF representations of heterogeneous robots as physical constraints to construct a sim-to-real topological mapping, enabling real-time access to the physical states of both simulated and real-world agents. We further incorporate a data collection and state accumulation mechanism that stores robot states, multimodal observations, and execution trajectories during real-world execution, enabling subsequent iterative policy optimization. During deployment, a unified agent maintains semantic continuity between reasoning and execution, and dynamically assigns task-specific control to different agents, thereby improving robustness in multi-policy execution. By establishing an autonomous closed-loop framework, ROSClaw minimizes the reliance on robot-specific development workflows. The framework supports hardware-level validation, automated generation of SDK-level control programs, and tool-based execution, enabling rapid cross-platform transfer and continual improvement of robotic skills. Ours project page: https://www.rosclaw.io/.

Rongfeng Zhao, Xuanhao Zhang, Zhaochen Guo +4

Shanghai Research Institute for Intelligent Autonomous Systems, Shanghai 201210, China · National Key Laboratory of Autonomous Intelligent Unmanned Systems (Tongji University), Shanghai 201210, China · Frontiers Science Center for Intelligent Autonomous Systems, Shanghai 201210, China +1

VLMs for RoboticsCross-Embodiment Robot LearningMulti-Robot CoordinationLong-Horizon Robotic ManipulationContinual Robot Learning
AskPDF
Apr 3, 2026

Hierarchical Planning with Latent World Models

World models are a promising path to zero-shot embodied control through planning. However, existing world model planners struggle on long-horizon, multi-stage tasks: prediction errors compound and naive search is exponential in the planning horizon. Hierarchy mitigates both by decomposing tasks into shorter, tractable subproblems; yet prior hierarchical approaches either amortize control into task-specific policies (hierarchical RL) or assume low-dimensional states and known dynamics (classical hierarchical MPC). We present Hierarchical Planning with Latent World Models (HWM), an architecture and planning paradigm for hierarchical model predictive control directly on visual world models trained solely via next-latent prediction. HWM learns world models at multiple temporal scales within a shared latent space, so predictions from the long horizon model serve as subgoals for the short horizon model via latent matching, without task-specific rewards or hierarchical policies. To keep long-horizon search tractable, HWM learns an action encoder that compresses primitive action chunks into latent macro-actions. On real-world Franka manipulation, HWM solves pick-and-place from a single goal image at 70% success vs. 0% for single-level planning. Across simulated push manipulation and maze navigation, HWM consistently improves performance on long-horizon tasks while requiring up to 3x less planning compute.

Wancong Zhang, Basile Terver, Artem Zholus +7

FAIR at Meta · New York University · Mila - Québec AI Institute +1

Hierarchical PlanningHierarchical Robot ControlHierarchical World ModelsLong-Horizon Robotic ManipulationModel Predictive ControlLatent World Models
AskPDF
Apr 3, 2026

SpatialVAM:Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot Policy

Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing policies neglect one or both aspects. They often rely on 2D visual observations or backbones pretrained on static image--text pairs, which leads to high data requirements and limited comprehension of environment dynamics. To address this, we introduce SpatialVAM, the first 3D Video Action Model that simultaneously predict spatial-aware multi-view heatmap videos and RGB videos. Our key insight is that this design naturally injects 3D information into video foundation models while aligning the representation format between video pretraining and action finetuning. Extensive experiments demonstrate that SpatialVAM enables data-efficient, robust, generalizable, and interpretable manipulation. With only ten demonstration trajectories and no additional pretraining, SpatialVAM handles challenging long-horizon and contact-rich tasks, generalizes to out-of-distribution settings, and predicts realistic future videos. Evaluations on Meta-World (22%↑\uparrow), RoboCasa (15%↑\uparrow) and real-world robotic platforms (16%↑\uparrow) show that SpatialVAM consistently outperforms other video action models, vision language action models and 3D-based policies, establishing a new state-of-the-art in data-efficient multi-task manipulation.

Peiyan Li, Yixiang Chen, Yuan Xu +13

New Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · Tsinghua University +4

Multi-Task Robotic ManipulationData-Efficient Robot LearningLong-Horizon Robotic ManipulationMulti-View Video Generation
AskPDF
Apr 3, 2026

ARM: Advantage Reward Modeling for Long-Horizon Manipulation

Long-horizon robotic manipulation remains challenging for reinforcement learning (RL) because sparse rewards provide limited guidance for credit assignment. Practical policy improvement thus relies on richer intermediate supervision, such as dense progress rewards, which are costly to obtain and ill-suited to non-monotonic behaviors such as backtracking and recovery. To address this, we propose Advantage Reward Modeling (ARM), a framework that shifts from hard-to-quantify absolute progress to estimating relative advantage. We introduce a cost-effective tri-state labeling strategy -- Progressive, Regressive, and Stagnant -- that reduces human cognitive overhead while ensuring high cross-annotator consistency. By training on these intuitive signals, ARM enables automated progress annotation for both complete demonstrations and fragmented DAgger-style data. Integrating ARM into an offline RL pipeline allows for adaptive action-reward reweighting, effectively filtering suboptimal samples. Our approach achieves a 99.4% success rate on a challenging long-horizon towel-folding task, demonstrating improved stability and data efficiency over current VLA baselines with near-zero human intervention during policy training.

Yiming Mao, Zixi Yu, Weixin Mao +5

LimX Dynamics · Beijing University of Posts and Telecommunications · Zhejiang University

Reward ModelingLong-Horizon Robotic ManipulationData-Efficient Robot LearningDense Reward RL
AskPDF
Mar 31, 2026

Long-Reach Robotic Cleaning for Lunar Solar Arrays

Commercial lunar activity is accelerating the need for reliable surface infrastructure and routine operations to keep it functioning. Maintenance tasks such as inspection, cleaning, dust mitigation, and minor repair are essential to preserve performance and extend system life. A specific application is the cleaning of lunar solar arrays. Solar arrays are expected to provide substantial fraction of lunar surface power and operate for months to years, supplying continuous energy to landers, habitats, and surface assets, making sustained output mission-critical. However, over time lunar dust accumulates on these large solar arrays, which can rapidly degrade panel output and reduce mission lifetime. We propose a small mobile robot equipped with a long-reach, lightweight deployable boom and interchangeable cleaning tool to perform gentle cleaning over meter-scale workspaces with minimal human involvement. Building on prior vision-guided long-reach manipulation, we add a compliant wrist with distal force sensing and a velocity-based admittance controller to regulate stable contact during surface cleaning. In preliminary benchtop experiments on a planar surface, the system maintained approximately 2 N normal force while executing a simple cleaning motion over boom lengths from 0.3 m to 1.0 m, with RMS force error of approximately 0.2 N after initial contact. These early results suggest that deployable long-reach manipulators are a promising architecture for robotic maintenance of lunar infrastructure such as solar arrays, radiators, and optical surfaces.

Stanley Wang, Velin Kojouharov, Long Yin Chung +2

All authors are with the Dept. of Mechanical Engineering, Stanford University, Stanford, CA 94305, USA.

RoboticsSpace RoboticsForce-Controlled Robotic ManipulationLong-Horizon Robotic Manipulation
AskPDF
Mar 31, 2026

Generalizable Dense Reward for Long-Horizon Robotic Tasks

Existing robotic foundation policies are trained primarily via large-scale imitation learning. While such models demonstrate strong capabilities, they often struggle with long-horizon tasks due to distribution shift and error accumulation. While reinforcement learning (RL) can finetune these models, it cannot work well across diverse tasks without manual reward engineering. We propose VLLR, a dense reward framework combining (1) an extrinsic reward from Large Language Models (LLMs) and Vision-Language Models (VLMs) for task progress recognition, and (2) an intrinsic reward based on policy self-certainty. VLLR uses LLMs to decompose tasks into verifiable subtasks and then VLMs to estimate progress to initialize the value function for a brief warm-up phase, avoiding prohibitive inference cost during full training; and self-certainty provides per-step intrinsic guidance throughout PPO finetuning. Ablation studies reveal complementary benefits: VLM-based value initialization primarily improves task completion efficiency, while self-certainty primarily enhances success rates, particularly on out-of-distribution tasks. On the CHORES benchmark covering mobile manipulation and navigation, VLLR achieves up to 56% absolute success rate gains over the pretrained policy, up to 5% gains over state-of-the-art RL finetuning methods on in-distribution tasks, and up to 10%10\% gains on out-of-distribution tasks, all without manual reward engineering. Additional visualizations can be found in https://silongyong.github.io/vllr_project_page/

Silong Yong, Stephen Sheng, Carl Qi +6

Carnegie Mellon University · Amazon Robotics · UT Austin

Reinforcement LearningLong-Horizon Robotic ManipulationRobot Skill LearningDense Reward RLIntrinsic MotivationLLM-Guided RL+3
AskPDF
Mar 29, 2026

Spectral Decomposition of Inverse Dynamics for Fast Exploration in Model-Based Manipulation

Planning long duration robotic manipulation sequences is challenging because of the complexity of exploring feasible trajectories through nonlinear contact dynamics and many contact modes. Moreover, this complexity grows with the problem's horizon length. We propose a search tree method that generates trajectories using the spectral decomposition of the inverse dynamics equation. This equation maps actuator displacement to object displacement, and its spectrum is efficient for exploration because its components are orthogonal and they approximate the reachable set of the object while remaining dynamically feasible. These trajectories can be combined with any search based method, such as Rapidly-Exploring Random Trees (RRT), for long-horizon planning. Our method performs similarly to recent work in model-based planning for short-horizon tasks, and differentiates itself with its ability to solve long-horizon tasks: whereas existing methods fail, ours can generate 45 second duration, 10+ contact mode plans using 15 seconds of computation, demonstrating real-time capability in highly complex domains.

Solvin Sigurdson, Benjamin Riviere, Joel Burdick

Department of Control and Dynamical Systems, California Institute of Technology, Pasadena, CA 91125, USA · Department of Mechanical and Aerospace Engineering and the Department of Computer Science, New York University, New York City, NY 10012, USA

Long-Horizon Robotic ManipulationMotion PlanningModel-Based PlanningContact-Rich Manipulation
AskPDF
Mar 29, 2026

ProgressVLA: Progress-Guided Diffusion Policy for Vision-Language Robotic Manipulation

Most existing vision-language-action (VLA) models for robotic manipulation lack progress awareness, typically relying on hand-crafted heuristics for task termination. This limitation is particularly severe in long-horizon tasks involving cascaded sub-goals. In this work, we investigate the estimation and integration of task progress, proposing a novel model named {\textbf \vla}. Our technical contributions are twofold: (1) robust progress estimation: We pre-train a progress estimator on large-scale, unsupervised video-text robotic datasets. This estimator achieves a low prediction residual (0.07 on a scale of [0,1][0, 1]) in simulation and demonstrates zero-shot generalization to unseen real-world samples, and (2) differentiable progress guidance: We introduce an inverse dynamics world model that maps predicted action tokens into future latent visual states. These latents are then processed by the progress estimator; by applying a maximal progress regularization, we establish a differentiable pipeline that provides progress-piloted guidance to refine action tokens. Extensive experiments on the CALVIN and LIBERO benchmarks, alongside real-world robot deployment, consistently demonstrate substantial improvements in success rates and generalization over strong baselines.

Hongyu Yan, Qiwei Li, Jiaolong Yang +1

Peking University · Microsoft Research Asia (MSRA)

Robotic ManipulationVision-Language-Action ModelsRobot Task Progress EstimationLong-Horizon Robotic ManipulationDiffusion Policy
AskPDF
Mar 26, 2026

Emergent Neural Automaton Policies: Learning Symbolic Structure from Visuomotor Trajectories

Scaling robot learning to long-horizon tasks remains a formidable challenge. While end-to-end policies often lack the structural priors needed for effective long-term reasoning, traditional neuro-symbolic methods rely heavily on hand-crafted symbolic priors. We introduce ENAP (Emergent Neural Automaton Policy), a neuro-symbolic imitation learning framework in which a bi-level policy adaptively emerges from visuomotor demonstrations. Specifically, we employ adaptive clustering and an extension of the L* algorithm to learn the task structure from demonstrations as a Mealy state machine, which serves as an interpretable high-level planner capturing latent task modes. This discrete structure then guides a low-level reactive residual network to learn precise continuous control via behavior cloning (BC). By explicitly modeling discrete transitions and continuous residuals, ENAP achieves sample efficiency and interpretability without task-specific labels. Experiments on complex manipulation and long-horizon tasks show that ENAP outperforms state-of-the-art end-to-end vision-language-action (VLA) policies by up to 27% in low-data regimes. ENAP can also distill task structure from the latent space of a pre-trained VLA, surpassing it on CALVIN benchmark with 39% fewer parameters (Fig. 1).

Yiyuan Pan, Xusheng Luo, Hanjiang Hu +2

Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA

Automata LearningVisuomotor Policy LearningNeurosymbolic LearningLong-Horizon Robotic ManipulationRobot Imitation Learning
AskPDF
Mar 26, 2026

System Design for Maintaining Internal State Consistency in Long-Horizon Robotic Tabletop Games

Long-horizon tabletop games pose a distinct systems challenge for robotics: small perceptual or execution errors can invalidate accumulated task state, propagate across decision-making modules, and ultimately derail interaction. This paper studies how to maintain internal state consistency in turn-based, multi-human robotic tabletop games through deliberate system design rather than isolated component improvement. Using Mahjong as a representative long-horizon setting, we present an integrated architecture that explicitly maintains perceptual, execution, and interaction state, partitions high-level semantic reasoning from time-critical perception and control, and incorporates verified action primitives with tactile-triggered recovery to prevent premature state corruption. We further introduce interaction-level monitoring mechanisms to detect turn violations and hidden-information breaches that threaten execution assumptions. Beyond demonstrating complete-game operation, we provide an empirical characterization of failure modes, recovery effectiveness, cross-module error propagation, and hardware-algorithm trade-offs observed during deployment. Our results show that explicit partitioning, monitored state transitions, and recovery mechanisms are critical for sustaining executable consistency over extended play, whereas monolithic or unverified pipelines lead to measurable degradation in end-to-end reliability. The proposed system serves as an empirical platform for studying system-level design principles in long-horizon, turn-based interaction.

Guangyu Zhao, Ceyao Zhang, Chengdong Ma +16

Peking University · PKU-PsiBot Joint Lab · Nanyang Technological University +1

RoboticsHuman-Robot InteractionLong-Horizon Robotic Manipulation
AskPDF
Mar 25, 2026

Chameleon: Control-Indexed Prospective Memory for Visuomotor Manipulation

Robots often observe information that determines a future action long before that action is executed. In a shell game, for example, a robot first sees which cup hides the ball, watches the cups move, and only later needs to choose the correct cup. The final observation alone is not enough for a decision: the correct action depends on an earlier event. We refer to this temporal gap as observation-action delay. It makes memory a policy-facing problem: a policy must keep similar histories distinct, retrieve the past event relevant to the current decision, and convert that recall into an action-ready state. We call these requirements separability, addressability, and prospectiveness. We introduce Chameleon, a ~60M visuomotor policy for control-indexed prospective memory. Chameleon writes embodied event memory, preserves separable histories, retrieves control-relevant traces, and trains the resulting working state to be prospective. We also introduce Camo-Dataset, a real-robot benchmark that isolates observation-action delay by making the decision scene visually ambiguous, so the correct action must be inferred from earlier observations. Chameleon improves decision/end-to-end success on Camo-Dataset from 22.5%/21.3% to 80.8%/71.3%. On public long-horizon memory benchmarks, it achieves 87.1% +/- 0.8% on LIBERO-10, 97.3% +/- 4.5% on MemoryBench, and 75.1% +/- 1.4% on MIKASA-Robo, setting the state of the art for same-size models and exceeding multiple larger VLA baselines under the reported protocols. Probes and ablations show that Chameleon learns separable, addressable, and prospective memory, and that these properties drive its performance gains.

Xinying Guo, Chenxi Jiang, Hyun Bin Kim +4

MARS Lab, Nanyang Technological University · Institute for Infocomm Research, A*STAR · National University of Singapore

Memory-Augmented AgentsLong-Horizon Robotic ManipulationVisuomotor Policy LearningRobot Manipulation Benchmarks
AskPDF
Mar 23, 2026

DexDrummer: In-Hand, Contact-Rich, and Long-Horizon Dexterous Robot Drumming

Performing in-hand, contact-rich, and long-horizon dexterous manipulation remains an unsolved challenge in robotics. Prior hand dexterity works have considered each of these three challenges in isolation, yet do not combine these skills into a single, complex task. To further test the capabilities of dexterity, we propose drumming as a testbed for dexterous manipulation. Drumming naturally integrates all three challenges: it involves in-hand control for stabilizing and adjusting the drumstick with the fingers, contact-rich interaction through repeated striking of the drum surface, and long-horizon coordination when switching between drums and sustaining rhythmic play. We present DexDrummer, a hierarchical object-centric bimanual drumming policy trained in simulation with sim-to-real transfer. The framework reduces the exploration difficulty of pure reinforcement learning by combining trajectory planning with residual RL corrections for fast transitions between drums. A dexterous manipulation policy handles contact-rich dynamics, guided by rewards that explicitly model both finger-stick and stick-drum interactions. In simulation, we show our policy can play two styles of music: multi-drum, bimanual songs and challenging, technical exercises that require increased dexterity. Across simulated bimanual tasks, our dexterous, reactive policy outperforms a fixed grasp policy by 1.87x across easy songs and 1.22x across hard songs F1 scores. In real-world tasks, we show song performance across a multi-drum setup. DexDrummer is able to play our training song and its extended version with an F1 score of 1.0.

Hung-Chieh Fang, Amber Xie, Jennifer Grannen +2

Stanford University

Dexterous ManipulationContact-Rich Robotic ManipulationLong-Horizon Robotic ManipulationBimanual Robotic Manipulation
AskPDF
Mar 23, 2026

BiPreManip: Learning Affordance-Based Bimanual Preparatory Manipulation through Anticipatory Collaboration

Many everyday objects are difficult to directly grasp (e.g., a flat iPad) or manipulate functionally (e.g., opening the cap of a pen lying on a desk). Such tasks require sequential, asymmetric coordination between two arms, where one arm performs preparatory manipulation that enables the other's goal-directed action - for instance, pushing the iPad to the table's edge before picking it up, or lifting the pen body to allow the other hand to remove its cap. In this work, we introduce Collaborative Preparatory Manipulation, a class of bimanual manipulation tasks that demand understanding object semantics and geometry, anticipating spatial relationships, and planning long-horizon coordinated actions between the two arms. To tackle this challenge, we propose a visual affordance-based framework that first envisions the final goal-directed action and then guides one arm to perform a sequence of preparatory manipulations that facilitate the other arm's subsequent operation. This affordance-centric representation enables anticipatory inter-arm reasoning and coordination, generalizing effectively across various objects spanning diverse categories. Extensive experiments in both simulation and the real world demonstrate that our approach substantially improves task success rates and generalization compared to competitive baselines.

Yan Shen, Feng Jiang, Zichen He +5

CFCS, School of Computer Science, Peking University

Affordance-Based Robotic ManipulationRobotic ManipulationBimanual Robotic ManipulationLong-Horizon Robotic ManipulationGeneralization in Robotic Manipulation
AskPDF
Mar 23, 2026

PRM-as-a-Judge: A Dense Evaluation Paradigm for Fine-Grained Robotic Auditing

Current robotic evaluation is still largely dominated by binary success rates, which collapse rich execution processes into a single outcome and obscure critical qualities such as progress, efficiency, and stability. To address this limitation, we propose PRM-as-a-Judge, a dense evaluation paradigm that leverages Process Reward Models (PRMs) to audit policy execution directly from trajectory videos by estimating task progress from observation sequences. Central to this paradigm is the OPD (Outcome-Process-Diagnosis) metric system, which explicitly formalizes execution quality via a task-aligned progress potential. We characterize dense robotic evaluation through two axiomatic properties: macro-consistency, which requires additive and path-consistent aggregation, and micro-resolution, which requires sensitivity to fine-grained physical evolution. Under this formulation, potential-based PRM judges provide a natural instantiation of dense evaluation, with macro-consistency following directly from the induced scalar potential. We empirically validate the micro-resolution property using RoboPulse, a diagnostic benchmark specifically designed for probing micro-scale progress discrimination, where several trajectory-trained PRM judges outperform discriminative similarity-based methods and general-purpose foundation-model judges. Finally, leveraging PRM-as-a-Judge and the OPD metric system, we conduct a structured audit of mainstream policy paradigms across long-horizon tasks, revealing behavioral signatures and failure modes that are invisible to outcome-only metrics.

Yuheng Ji, Yuyang Liu, Huajie Tan +15

State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University +4

Robotic Policy EvaluationProcess Reward ModelsRobot Manipulation BenchmarksLong-Horizon Robotic Manipulation
AskPDF
Mar 19, 2026

MemoAct: Atkinson-Shiffrin-Inspired Hierarchical Memory-Augmented Policy for Robotic Manipulation

Memory-augmented robotic policies are essential in handling memory-dependent tasks. However, existing approaches typically rely on simply extending the observation window, struggling to simultaneously achieve precise task-state tracking and robust long-horizon retention. To overcome these challenges, inspired by the Atkinson--Shiffrin memory model, we propose MemoAct, a hierarchical memory-augmented policy that leverages distinct memory tiers to tackle specific bottlenecks. Specifically, sensory memory filters immediate perceptual inputs, lossless short-term memory supports precise task-state tracking, and compressed long-term memory facilitates robust long-horizon retention. To enrich the evaluation landscape, we construct MemoryRTBench based on RoboTwin 2.0, comprising 6 manipulation tasks that systematically evaluate policy memory capabilities across three dimensions: sequential, spatial, and episodic memory. Extensive experiments across simulated and real-world scenarios demonstrate that MemoAct achieves superior performance compared to both existing Markovian baselines and history-aware policies. The project page is available at https://tlf-tlf.github.io/MemoActPage/.

Liufan Tan, Jiale Li, Gangshan Jing

Memory-Augmented AgentsRobot Policy LearningLong-Horizon Robotic ManipulationRobotic ManipulationRobot Manipulation Benchmarks
AskPDF
Mar 17, 2026

Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models

Reinforcement Learning (RL) has shown strong potential for improving robotic manipulation policies, yet its practical use remains bottlenecked by the difficulty of specifying reward functions that are both semantically meaningful and reusable across tasks. In this paper, we propose Large Reward Models (LRMs), a framework that adapts foundation VLMs into frame-level reward generators for robot policy refinement. We specialize a state-of-the-art VLM on a multi-source dataset spanning real-world robot trajectories, human-object interactions, and simulated manipulation environments. Unlike prior approaches that mainly evaluate trajectories post-hoc, LRMs expose multiple reward interfaces from visual observations: progress estimation, task completion, and temporal contrastive comparison. Starting from an imitation-learned policy, we use these VLM-derived rewards to guide PPO refinement on held-out long-horizon manipulation tasks. Our experiments show that LRM progress rewards provide the strongest non-privileged online refinement signal, improving the IL baseline and narrowing the gap to privileged environment rewards. We further deploy progress rewards for progress-weighted behavioral cloning on four real-world manipulation tasks spanning two robot platforms, improving over SFT on all four tasks. These results suggest that modality-specific specialization of foundation VLMs can provide practical visual reward signals for both simulated policy refinement and physical robot self-improvement without hand-coded task rewards.

Yanru Wu, Weiduo Yuan, Esteban Martinez Licon +4

USC Physical Superintelligence Lab

Long-Horizon Robotic ManipulationRobot Skill LearningRobotic RLMultimodal Reward ModelingVisual RLVLMs for Robotics+1
AskPDF
Mar 16, 2026

ExpertGen: Scalable Sim-to-Real Expert Policy Learning from Imperfect Behavior Priors

Learning generalizable and robust behavior cloning policies requires large volumes of high-quality robotics data. While human demonstrations (e.g., through teleoperation) serve as the standard source for expert behaviors, acquiring such data at scale in the real world is prohibitively expensive. This paper introduces ExpertGen, a framework that automates expert policy learning in simulation to enable scalable sim-to-real transfer. ExpertGen first initializes a behavior prior using a diffusion policy trained on imperfect demonstrations, which may be synthesized by large language models or provided by humans. Reinforcement learning is then used to steer this prior toward high task success by optimizing the diffusion model's initial noise while keep original policy frozen. By keeping the pretrained diffusion policy frozen, ExpertGen regularizes exploration to remain within safe, human-like behavior manifolds, while also enabling effective learning with only sparse rewards. Empirical evaluations on challenging manipulation benchmarks demonstrate that ExpertGen reliably produces high-quality expert policies with no reward engineering. On industrial assembly tasks, ExpertGen achieves a 90.5% overall success rate, while on long-horizon manipulation tasks it attains 85% overall success, outperforming all baseline methods. The resulting policies exhibit dexterous control and remain robust across diverse initial configurations and failure states. To validate sim-to-real transfer, the learned state-based expert policies are further distilled into visuomotor policies via DAgger and successfully deployed on real robotic hardware.

Zifan Xu, Ran Gong, Maria Vittoria Minniti +10

Robotics and AI Institute · University of Texas at Austin · Sony AI

Long-Horizon Robotic ManipulationRobot Skill LearningSim-to-Real TransferRobotic RLRobot Imitation Learning
AskPDF
Mar 16, 2026

RoCo Challenge at AAAI 2026: Benchmarking Robotic Collaborative Manipulation for Assembly Towards Industrial Automation

Embodied Artificial Intelligence (EAI) is rapidly developing, gradually subverting previous autonomous systems' paradigms from isolated perception to integrated, continuous action. This transition is highly significant for industrial robotic manipulation, promising to free human workers from repetitive, dangerous daily labor. To benchmark and advance this capability, we introduce the Robotic Collaborative Assembly Assistance (RoCo) Challenge with a dataset towards simulation and real-world assembly manipulation. Set against the backdrop of human-centered manufacturing, this challenge focuses on a high-precision planetary gearbox assembly task, a demanding yet highly representative operation in modern industry. Built upon a self-developed data collection, training, and evaluation system in Isaac Sim, and utilizing a dual-arm robot for real-world deployment, the challenge operates in two phases. The Simulation Round defines fine-grained task phases for step-wise scoring to handle the long-horizon nature of the assembly. The Real-World Round mirrors this evaluation with physical gearbox components and high-quality teleoperated datasets. The core tasks require assembling an epicyclic gearbox from scratch, including mounting three planet gears, a sun gear, and a ring gear. Attracting over 60 teams and 170+ participants from more than 10 countries, the challenge yielded highly effective solutions, most notably ARC-VLA and RoboCola. Results demonstrate that a dual-model framework for long-horizon multi-task learning is highly effective, and the strategic utilization of recovery-from-failure curriculum data is a critical insight for successful deployment. This report outlines the competition setup, evaluation approach, key findings, and future directions for industrial EAI. Our dataset, CAD files, code, and evaluation results can be found at: https://rocochallenge.github.io/RoCo2026/.

Haichao Liu, Yuheng Zhou, Zhenyu Wu +14

Nanyang Technological University, Singapore · Beijing University of Posts and Telecommunications, Beijing, China · Carnegie Mellon University, Pittsburgh, USA +1

Robot Manipulation BenchmarksRobotic AssemblyIndustrial RoboticsLong-Horizon Robotic ManipulationMulti-Task Robotic Manipulation
AskPDF
Mar 14, 2026

ST-VLA: Enabling 4D-Aware Spatiotemporal Understanding for General Robot Manipulation

Robotic manipulation in open-world environments requires reasoning across semantics, geometry, and long-horizon action dynamics. Existing hierarchical Vision-Language-Action (VLA) frameworks typically use 2D representations to connect high-level reasoning with low-level control, but lack depth awareness and temporal consistency, limiting robustness in complex 3D scenes. We propose ST-VLA, a hierarchical VLA framework using a unified 3D-4D representation to bridge perception and action. ST-VLA converts 2D guidance into 3D trajectories and generates smooth spatial masks that capture 4D spatio-temporal context, providing a stable interface between semantic reasoning and continuous control. To enable effective learning of such representations, we introduce ST-Human, a large-scale human manipulation dataset with 14 tasks and 300k episodes, annotated with 2D, 3D, and 4D supervision via a semi-automated pipeline. Using ST-Human, we train ST-VLM, a spatio-temporal vision-language model that generates spatially grounded and temporally coherent 3D representations to guide policy execution. The smooth spatial masks focus on task-relevant geometry and stabilize latent representations, enabling online replanning and long-horizon reasoning. Experiments on RLBench and real-world manipulation tasks show that \method significantly outperforms state-of-the-art baselines, improving zero-shot success rates by 44.6% and 30.3%. These results demonstrate that offloading spatio-temporal reasoning to VLMs with unified 3D-4D representations substantially improves robustness and generalization for open-world robotic manipulation. Project website: https://oucx117.github.io/ST-VLA/.

You Wu, Zixuan Chen, Cunxu Ou +9

School of Computer Science, Nanjing University · School of Intelligence Science and Technology, Nanjing University · School of Electronic Science and Engineering, Nanjing University +2

Robotic ManipulationVLMs for RoboticsLong-Horizon Robotic Manipulation3D VLMsZero-Shot Robotic Manipulation
AskPDF
Mar 14, 2026

REFINE-DP: Diffusion Policy Fine-tuning for Humanoid Loco-manipulation via Reinforcement Learning

Humanoid loco-manipulation requires coordinated task-space motion planning with stable loco-manipulation command tracking under complex robot-environment dynamics and long-horizon tasks. While diffusion policies (DPs) show promise for learning from demonstrations, deploying them on humanoids poses critical challenges: the motion planner trained offline is decoupled from the loco-manipulation controller, leading to poor command tracking, compounding distribution shift, and task failures. The common approach of scaling demonstration data is prohibitively expensive for high-dimensional humanoid systems. To address this challenge, we present REFINE-DP (REinforcement learning FINE-tuning of Diffusion Policy), a hierarchical framework that jointly optimizes a DP motion planner and an RL-based loco-manipulation controller. The DP is fine-tuned via a PPO-based diffusion policy gradient to improve task success rate, while the controller is simultaneously updated to accurately track the planner's evolving command distribution, reducing the distributional mismatch that degrades motion quality. We validate REFINE-DP on a humanoid robot performing loco-manipulation tasks, including door traversal and long-horizon object transport. REFINE-DP achieves an over 90% success rate in simulation, even in out-of-distribution cases not seen in the pre-training data, and enables real-world execution without privileged state information. Our proposed method substantially outperforms pre-trained DP baselines and demonstrates that RL fine-tuning is key to reliable humanoid loco-manipulation. https://refine-dp.github.io/REFINE-DP/

Zhaoyuan Gu, Yipu Chen, Zimeng Chai +11

Institute for Robotics and Intelligent Machines, Georgia Institute of Technology, Atlanta, GA 30332 USA

Humanoid Loco-ManipulationDiffusion PolicyLong-Horizon Robotic ManipulationRobot Policy GeneralizationRL for Diffusion Models
AskPDF
Mar 13, 2026

RoboStream: Weaving Spatio-Temporal Reasoning with Memory in Vision-Language Models for Robotics

Enabling reliable long-horizon robotic manipulation is a crucial step toward open-world embodied intelligence. However, VLM-based planners treat each step as an isolated observation-to-action mapping, forcing them to reinfer scene geometry from raw pixels at every decision point while remaining unaware of how prior actions have reshaped the environment. Despite strong short-horizon performance, these systems lack the spatio-temporal reasoning required for persistent geometric anchoring and memory of action-triggered state transitions. Without persistent state tracking, perceptual errors accumulate across the execution horizon, temporarily occluded objects are catastrophically forgotten, and these compounding failures lead to precondition violations that cascade through subsequent steps. In contrast, humans maintain a persistent mental model that continuously tracks spatial relations and action consequences across interactions rather than reconstructing them at each instant. Inspired by this human capacity for causal spatio-temporal reasoning with persistent memory, we propose RoboStream, a training-free framework that achieves geometric anchoring through Spatio-Temporal Fusion Tokens (STF-Tokens), which bind visual evidence to 3D geometric attributes for persistent object grounding, and maintains causal continuity via a Causal Spatio-Temporal Graph (CSTG) that records action-triggered state transitions across steps. This design enables the planner to trace causal chains and preserve object permanence under occlusion without additional training or fine-tuning. RoboStream achieves 90.5% on long-horizon RLBench and 44.4% on challenging real-world block-building tasks, where both SoFar and VoxPoser score 11.1%, demonstrating that spatio-temporal reasoning and causal memory are critical missing components for reliable long-horizon manipulation.

Yuzhi Huang, Jie Wu, Weijue Bu +9

Shenzhen International Graduate School, Tsinghua University · YuanxingGuangnian Robotics · China University of Mining and Technology +3

Long-Horizon Robotic ManipulationRobot Task PlanningVLMs for RoboticsSpatiotemporal ReasoningRobotic Spatial MemoryVisual Spatial Reasoning
AskPDF
Mar 13, 2026

Spatially Grounded Long-Horizon Task Planning in the Wild

Recent advances in robot manipulation increasingly leverage Vision-Language Models (VLMs) for high-level reasoning, such as decomposing task instructions into sequential action plans expressed in natural language that guide downstream low-level motor execution. However, current benchmarks do not assess whether these plans are spatially executable, particularly in specifying the exact spatial locations where the robot should interact to execute the plan, limiting evaluation of real-world manipulation capability. To bridge this gap, we define a novel task of grounded planning and introduce GroundedPlanBench, a newly curated benchmark for spatially grounded long-horizon action planning in the wild. GroundedPlanBench jointly evaluates hierarchical sub-action planning and spatial action grounding (where to act), enabling systematic assessment of whether generated sub-actions are spatially executable for robot manipulation. We further introduce Video-to-Spatially Grounded Planning (V2GP), an automated data generation framework that leverages real-world robot video demonstrations to improve spatially grounded long-horizon planning. Our evaluations reveal that spatially grounded long-horizon planning remains a major bottleneck for current VLMs. Our results demonstrate that V2GP provides a promising approach for improving both action planning and spatial grounding performance, validated on our benchmark as well as through real-world robot manipulation experiments, advancing progress toward spatially actionable planning.

Sehun Jung, HyunJee Song, Dong-Hee Kim +4

Korea University · Microsoft Research · University of Wisconsin-Madison

Robot Task PlanningLong-Horizon Robotic ManipulationSpatial Grounding for VLA ModelsRobot Manipulation BenchmarksVLMs for Robotics
AskPDF
Mar 13, 2026

Beyond Dense Futures: World Models as Structured Planners for Robotic Manipulation

Recent world-model-based Vision-Language-Action (VLA) architectures have improved robotic manipulation through predictive visual foresight. However, dense future prediction introduces visual redundancy and accumulates errors, causing long-horizon plan drift. Meanwhile, recent sparse methods typically represent visual foresight using high-level semantic subtasks or implicit latent states. These representations often lack explicit kinematic grounding, weakening the alignment between planning and low-level execution. To address this, we propose StructVLA, which reformulates a generative world model into an explicit structured planner for reliable control. Instead of dense rollouts or semantic goals, StructVLA predicts sparse, physically meaningful structured frames. Derived from intrinsic kinematic cues (e.g., gripper transitions and kinematic turning points), these frames capture spatiotemporal milestones closely aligned with task progress. We implement this approach through a two-stage training paradigm with a unified discrete token vocabulary: the world model is first trained to predict structured frames and subsequently optimized to map the structured foresight into low-level actions. This approach provides clear physical guidance and bridges visual planning and motion control. In our experiments, StructVLA achieves strong average success rates of 75.0% on SimplerEnv-WidowX and 94.8% on LIBERO. Real-world deployments further demonstrate reliable task completion and robust generalization across both basic pick-and-place and complex long-horizon tasks.

Minghao Jin, Mozheng Liao, Mingfei Han +2

University of Science and Technology of China · Department of CV, MBZUAI

World Model-Based PlanningRobotic ManipulationLong-Horizon Robotic ManipulationVLMs for Robotics
AskPDF
Mar 12, 2026

Concurrent Prehensile and Nonprehensile Manipulation: A Practical Approach to Multi-Stage Dexterous Tasks

Dexterous hands enable concurrent prehensile and nonprehensile manipulation, such as holding one object while interacting with another, a capability essential for everyday tasks yet underexplored in robotics. Learning such long-horizon, contact-rich multi-stage behaviors is challenging because demonstrations are expensive to collect and end-to-end policies require substantial data to generalize across varied object geometries and placements. We present DexMulti, a sample-efficient approach for real-world dexterous multi-task manipulation that decomposes demonstrations into object-centric skills with well-defined temporal boundaries. Rather than learning monolithic policies, our method retrieves demonstrated skills based on current object geometry, aligns them to the observed object state using an uncertainty-aware estimator that tracks centroid and yaw, and executes them via a retrieve-align-execute paradigm. We evaluate on three multi-stage tasks requiring concurrent manipulation (Grasp + Pull, Grasp + Open, and Grasp + Grasp) across two dexterous hands (Allegro and LEAP) in over 1,000 real-world trials. Our approach achieves an average success rate of 66% on training objects with only 3-4 demonstrations per object, outperforming diffusion policy baselines by 2-3x while requiring far fewer demonstrations. Results demonstrate robust generalization to held-out objects and spatial variations up to +/-25 cm.

Hao Jiang, Yue Wu, Yue Wang +2

Thomas Lord Department of Computer Science at the University of Southern California, USA.

Dexterous ManipulationLong-Horizon Robotic ManipulationRobot Imitation LearningData-Efficient Robot LearningNon-Prehensile Robotic ManipulationGeneralization in Robotic Manipulation
AskPDF
Mar 12, 2026

RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks

Vision-Language-Action (VLA) systems have shown strong potential for language-driven robotic manipulation. However, scaling them to long-horizon tasks remains challenging. Existing pipelines typically separate data collection, policy learning, and deployment, resulting in heavy reliance on manual environment resets and brittle multi-policy execution. We present RoboClaw, an agentic robotics framework that unifies data collection, policy learning, and task execution under a single VLM-driven controller. At the policy level, RoboClaw introduces Entangled Action Pairs (EAP), which couple forward manipulation behaviors with inverse recovery actions to form self-resetting loops for autonomous data collection. This mechanism enables continuous on-policy data acquisition and iterative policy refinement with minimal human intervention. During deployment, the same agent performs high-level reasoning and dynamically orchestrates learned policy primitives to accomplish long-horizon tasks. By maintaining consistent contextual semantics across collection and execution, RoboClaw reduces mismatch between the two phases and improves multi-policy robustness. Experiments in real-world manipulation tasks demonstrate improved stability and scalability compared to conventional open-loop pipelines, while significantly reducing human effort throughout the robot lifecycle, achieving a 25% improvement in success rate over baseline methods on long-horizon tasks and reducing human time investment by 53.7%.

Ruiying Li, Yunlang Zhou, YuYao Zhu +15

AgiBot, China · National University of Singapore · Shanghai Jiao Tong University, Shanghai 200240, China +1

Long-Horizon Robotic ManipulationVLMs for RoboticsRobotic Data CollectionContinual Robot LearningRobustness of VLA Models
AskPDF
Mar 12, 2026

Deployment-Time Reliability of Learned Robot Policies

Recent advances in learning-based robot manipulation have produced policies with remarkable capabilities. Yet, reliability at deployment remains a fundamental barrier to real-world use, where distribution shift, compounding errors, and complex task dependencies collectively undermine system performance. This dissertation investigates how the reliability of learned robot policies can be improved at deployment time through mechanisms that operate around them. We develop three complementary classes of deployment-time mechanisms. First, we introduce runtime monitoring methods that detect impending failures by identifying inconsistencies in closed-loop policy behavior and deviations in task progress, without requiring failure data or task-specific supervision. Second, we propose a data-centric framework for policy interpretability that traces deployment-time successes and failures to influential training demonstrations using influence functions, enabling principled diagnosis and dataset curation. Third, we address reliable long-horizon task execution by formulating policy coordination as the problem of estimating and maximizing the success probability of behavior sequences, and we extend this formulation to open-ended, language-specified tasks through feasibility-aware task planning. By centering on core challenges of deployment, these contributions advance practical foundations for the reliable, real-world use of learned robot policies. Continued progress on these foundations will be essential for enabling trustworthy and scalable robot autonomy in the future.

Christopher Agia

THE DEPARTMENT OF COMPUTER SCIENCE AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY

RoboticsRobotic Policy EvaluationLong-Horizon Robotic ManipulationRobot Task Planning
AskPDF
Mar 11, 2026

Cybo-Waiter: A Physical Agentic Framework for Humanoid Whole-Body Locomotion-Manipulation

Robots are increasingly expected to execute open ended natural language requests in human environments, which demands reliable long horizon execution under partial observability. This is especially challenging for humanoids because locomotion and manipulation are tightly coupled through stance, reachability, and balance. We present a humanoid agent framework that turns VLM plans into verifiable task programs and closes the loop with multi object 3D geometric supervision. A VLM planner compiles each instruction into a typed JSON sequence of subtasks with explicit predicate based preconditions and success conditions. Using SAM3 and RGB-D, we ground all task relevant entities in 3D, estimate object centroids and extents, and evaluate predicates over stable frames to obtain condition level diagnostics. The supervisor uses these diagnostics to verify subtask completion and to provide condition-level feedback for progression and replanning. We execute each subtask by coordinating humanoid locomotion and whole-body manipulation, selecting feasible motion primitives under reachability and balance constraints. Experiments on tabletop manipulation and long horizon humanoid loco manipulation tasks show improved robustness from multi object grounding, temporal stability, and recovery driven replanning.

Peng Ren, Haoyang Ge, Chuan Qi +5

Beihang University, Beijing, China · Zhongguancun Academy, Beijing, China · Tianjin University, Tianjin, China +3

Humanoid Loco-ManipulationLong-Horizon Robotic ManipulationWhole-Body Robotic ManipulationHumanoid Robot LocomotionVLMs for Robotics
AskPDF
Mar 10, 2026

SELF-VLA: A Skill Enhanced Agentic Vision-Language-Action Framework for Contact-Rich Disassembly

Disassembly automation has long been pursued to address the growing demand for efficient and proper recovery of valuable components from the end-of-life (EoL) electronic products. Existing approaches have demonstrated promising and regimented performance by decomposing the disassembly process into different subtasks. However, each subtask typically requires extensive data preparation, model training, and system management. Moreover, these approaches are often task- and component-specific, making them poorly suited to handle the variability and uncertainty of EoL products and limiting their generalization capabilities. All these factors restrict the practical deployment of current robotic disassembly systems and leave them highly reliant on human labor. With the recent development of foundation models in robotics, vision-language-action (VLA) models have shown impressive performance on standard robotic manipulation tasks, but their applicability to complex, contact-rich, and long-horizon industrial practices like disassembly, which requires sequential and precise manipulation, remains limited. To address this challenge, we propose SELF-VLA, an agentic VLA framework that integrates explicit disassembly skills. Experimental studies demonstrate that our framework significantly outperforms current state-of-the-art end-to-end VLA models on two contact-rich disassembly tasks. The video illustration can be found via https://zh.engr.tamu.edu/wp-content/uploads/sites/310/2026/03/IROS-VLA-Video.mp4.

Chang Liu, Sibo Tian, Xiao Liang +1

J. Mike Walker ’66 Department of Mechanical Engineering, Texas A&M University, College Station, TX 77843, USA. · Zachry Department of Civil and Environmental Engineering, Texas A&M University, College Station, TX 77843, USA.

Vision-Language-Action ModelsContact-Rich Robotic ManipulationRobotic ManipulationLong-Horizon Robotic Manipulation
AskPDF
Mar 10, 2026

Perceptive Hierarchical-Task MPC for Sequential Mobile Manipulation in Unstructured Semi-Static Environments

As compared to typical mobile manipulation tasks, sequential mobile manipulation poses a unique challenge -- as the robot operates over extended periods, successful task completion is not solely dependent on consistent motion generation but also on the robot's awareness and adaptivity to changes in the operating environment. While existing motion planners can generate whole-body trajectories to complete sequential tasks, they typically assume that the environment remains static and rely on precomputed maps. This assumption often breaks down during long-term operations, where semi-static changes such as object removal, introduction, or shifts are common. In this work, we propose a novel perceptive hierarchical-task model predictive control (HTMPC) framework for efficient sequential mobile manipulation in unstructured, changing environments. To tackle the challenge, we leverage a Bayesian inference framework to explicitly model object-level changes and thereby maintain a temporally accurate representation of the 3D environment; this up-to-date representation is embedded in a lexicographic optimization framework to enable efficient execution of sequential tasks. We validate our perceptive HTMPC approach through both simulated and real-robot experiments. In contrast to baseline methods, our approach systematically accounts for moved and phantom obstacles, successfully completing sequential tasks with higher efficiency and reactivity, without relying on prior maps or external infrastructure.

Xintong Du, Jingxing Qian, Siqi Zhou +1

University of Toronto Institute for Aerospace Studies (UTIAS) and the Vector Institute for Artificial Intelligence, Canada. · School of Computing Science, Faculty of Applied Sciences, Simon Fraser University, Burnaby, BC, Canada. · Learning Systems and Robotics lab at the Technical University of Munich and the Munich Institute for Robotics and Machine Intelligence (MIRMI), Germany.

3D Scene Change DetectionMobile ManipulationRobot Task PlanningLong-Horizon Robotic ManipulationDynamic Robotic ManipulationModel Predictive Control
AskPDF
Mar 10, 2026

Beyond Short-Horizon: VQ-Memory for Robust Long-Horizon Manipulation in Non-Markovian Simulation Benchmarks

The high cost of collecting real-robot data has made robotic simulation a scalable platform for both evaluation and data generation. Yet most existing benchmarks concentrate on simple manipulation tasks such as pick-and-place, failing to capture the non-Markovian characteristics of real-world tasks and the complexity of articulated object interactions. To address this limitation, we present RuleSafe, a new articulated manipulation benchmark built upon a scalable LLM-aided simulation framework. RuleSafe features safes with diverse unlocking mechanisms, such as key locks, password locks, and logic locks, which require different multi-stage reasoning and manipulation strategies. These LLM-generated rules produce non-Markovian and long-horizon tasks that require temporal modeling and memory-based reasoning. We further propose VQ-Memory, a compact and structured temporal representation that uses vector-quantized variational autoencoders (VQ-VAEs) to encode past proprioceptive states into discrete latent tokens. This representation filters low-level noise while preserving high-level task-phase context, providing lightweight yet robust temporal cues that are compatible with existing Vision-Language-Action models (VLA). Extensive experiments on state-of-the-art VLA models and diffusion policies show that VQ-Memory consistently improves long-horizon planning, enhances generalization to unseen configurations, and enables more efficient manipulation with reduced computational cost. Project page: vqmemory.github.io

Honghui Wang, Zhi Jing, Jicong Ao +4

Tsinghua University · Fudan University · Institute of Artificial Intelligence (TeleAI), China Telecom

Long-Horizon Robotic ManipulationRobot Manipulation BenchmarksMemory-Augmented AgentsArticulated Object ManipulationRobotics SimulationVector-Quantized Variational Autoencoder
AskPDF