论文检索

Zirui Song, Guangxian Ouyang, Mingzhe Li, Yuheng Ji, Chenxi Wang, Zixiang Xu, Zeyu Zhang, Xiaoqing Zhang, Qian Jiang, Fengxian Ji 等

Large Vision-Language Models (LVLMs) have recently advanced robotic manipulation by leveraging vision for scene perception and language for instruction following. However, existing methods rely heavily on costly human-annotated training datasets, which limits their generalization and causes them to struggle in out-of-domain (OOD) scenarios, reducing real-world adaptability. To address these challenges, we propose ManipLVM-R1, a novel reinforcement learning framework that replaces traditional supervision with Reinforcement Learning using Verifiable Rewards (RLVR). By directly optimizing for task-aligned outcomes, our method enhances generalization and physical reasoning while removing the dependence on costly annotations. Specifically, we design two rule-based reward functions targeting key robotic manipulation subtasks: an Affordance Perception Reward to enhance localization of interaction regions, and a Trajectory Match Reward to ensure the physical plausibility of action paths. These rewards provide immediate feedback and impose spatial-logical constraints, encouraging the model to go beyond shallow pattern matching and instead learn deeper, more systematic reasoning about physical interactions. Experimental results show that ManipLVM-R1 achieves substantial performance gains across multiple manipulation tasks, using only 50% of the training data while achieving strong generalization to OOD scenarios. We further analyze the benefits of our reward design and its impact on task success and efficiency.

Wenxuan Song, Ziyang Zhou, Han Zhao, Jiayi Chen, Pengxiang Ding, Haodong Yan, Yuxin Huang, Feilong Tang, Donglin Wang, Haoang Li

Recent advances in Vision-Language-Action (VLA) models have enabled robotic agents to integrate multimodal understanding with action execution. However, our empirical analysis reveals that current VLAs struggle to allocate visual attention to target regions. Instead, visual attention is always dispersed. To guide the visual attention grounding on the correct target, we propose ReconVLA, a reconstructive VLA model with an implicit grounding paradigm. Conditioned on the model's visual outputs, a diffusion transformer aims to reconstruct the gaze region of the image, which corresponds to the target manipulated objects. This process prompts the VLA model to learn fine-grained representations and accurately allocate visual attention, thus effectively leveraging task-specific visual information and conducting precise manipulation. Moreover, we curate a large-scale pretraining dataset comprising over 100k trajectories and 2 million data samples from open-source robotic datasets, further boosting the model’s generalization in visual reconstruction. Extensive experiments in simulation and the real world demonstrate the superiority of our implicit grounding method, showcasing its capabilities of precise manipulation and generalization.

Abhudaya Shrivastava, Shelly Gupta, Zoran Obradovic

Autonomous aerial robots must operate in cluttered, wind-disturbed environments where turbulence and gusts generated by wind-object and terrain interactions introduce significant aerodynamic risks, including orientation instability, sensor degradation, control drift, and increased power consumption, often leading to mission failure or crash. We present Graphlets-based Zero-Shot Planning Framework (GZS), a novel, non-parametric, fast computation, memory-efficient, zero-shot training-free onboard inference framework for real-time 3D spatial-aware aerodynamic risk perception that operates without prior scene knowledge. GZS dynamically classifies point clouds to extract local topology, incorporates physics-informed modeling of wind interactions, and applies attention-guided segment matching to generate onboard 3D representations of wind-induced aerodynamic risk. It transforms unstructured scene segments into structured graphlets topologies encoding aerodynamic risk-aware features, enabling UAVs to identify and navigate through regions of minimal aerodynamic hazard in real time and without prior training in any environment. Unlike computational fluid dynamics(CFD)-based, deep learning, or map-dependent approaches, GZS performs zero-shot aerodynamic risk estimation in previously unseen and dynamic conditions. Extensive experiments demonstrate 90-95% accurate aerodynamic risk zone identification compared to conventional methods of CFDs and wind tunnels, while substantially reducing computational and memory overhead, and a 100% success rate in creating onboard 3d spatial-aware risk perceptions. Our results establish GZS as a framework for a zero-shot, non-parametric, robust, aerodynamic risk perception for autonomous real-time trajectory planning in wind-affected aerial environments.

Juyi Sheng, Ziyi Wang, Peiming Li, Mengyuan Liu

In robot manipulation, robot learning has become a prevailing approach. However, generative models within this field face a fundamental trade-off between the slow, iterative sampling of diffusion models and the architectural constraints of faster Flow-based methods, which often rely on explicit consistency losses. To address these limitations, we introduce MP1, which pairs 3D point-cloud inputs with the MeanFlow paradigm to generate action trajectories in one network function evaluation (1-NFE). By directly learning the interval-averaged velocity via the "MeanFlow Identity", our policy avoids any additional consistency constraints. This formulation eliminates numerical ODE-solver errors during inference, yielding more precise trajectories. MP1 further incorporates CFG for improved trajectory controllability while retaining 1-NFE inference without reintroducing structural constraints. Because subtle scene-context variations are critical for robot learning, especially in few-shot learning, we introduce a lightweight Dispersive Loss that repels state embeddings during training, boosting generalization without slowing inference. We validate our method on the Adroit and Meta-World benchmarks, as well as in real-world scenarios. Experimental results show MP1 achieves superior average task success rates, outperforming DP3 by 10.2% and FlowPolicy by 7.3%. Its average inference time is only 6.8 ms—19 times faster than DP3 and nearly 2 times faster than FlowPolicy.

Buqing Nie, Yang Zhang, Rongjun Jin, Zhanxiang Cao, Huangxuan Lin, Xiaokang Yang, Yue Gao

The human nervous system exhibits bilateral symmetry, enabling coordinated and balanced movements. However, existing Deep Reinforcement Learning (DRL) methods for humanoid robots neglect morphological symmetry of the robot, leading to uncoordinated and suboptimal behaviors. Inspired by human motor control, we propose Symmetry Equivariant Policy (SE-Policy), a new DRL framework that embeds strict symmetry equivariance in the actor and symmetry invariance in the critic without additional hyperparameters. SE-Policy enforces consistent behaviors across symmetric observations, producing temporally and spatially coordinated motions with higher task performance. Extensive experiments on velocity tracking tasks, conducted in both simulation and real-world deployment with the Unitree G1 humanoid robot, demonstrate that SE-Policy improves tracking accuracy by up to 40% compared to state-of-the-art baselines, while achieving superior spatial-temporal coordination. These results demonstrate the effectiveness of SE-Policy and its broad applicability to humanoid robots.

Asen Nachkov, Jan-Nico Zaech, Danda Pani Paudel, Xi Wang, Luc Van Gool

Planning allows an agent to safely refine its actions before executing them in the real world. In autonomous driving, this is crucial to avoid collisions and navigate in complex, dense traffic scenarios. One way to plan is to search for the best action sequence. However, this is challenging when all necessary components – policy, next-state predictor, and critic – have to be learned. Here we propose Differentiable Simulation for Search (DSS), a framework that leverages the differentiable simulator Waymax as both a next state predictor and a critic. It relies on the simulator’s hardcoded dynamics, making state predictions highly accurate, while utilizing the simulator’s differentiability to effectively search across action sequences. Our DSS agent optimizes its actions using gradient descent over imagined future trajectories. We show experimentally that DSS – the combination of planning gradients and stochastic search – significantly improves tracking and path planning accuracy compared to sequence prediction, imitation learning, model-free RL, and other planning methods.

Yanghong Mei, Yirong Yang, Longteng Guo, Qunbo Wang, Ming-Ming Yu, Xingjian He, Wenjun Wu, Jing Liu

Navigating complex urban environments using natural language instructions poses significant challenges for embodied agents, including noisy language instructions, ambiguous spatial references, diverse landmarks, and dynamic street scenes. Current visual navigation methods are typically limited to simulated or off-street environments, and often rely on precise goal formats, such as specific coordinates or images. This limits their effectiveness for autonomous agents like last-mile delivery robots navigating unfamiliar cities. To address these limitations, we introduce UrbanNav, a scalable framework that trains embodied agents to follow free-form language instructions in diverse urban settings. Leveraging web-scale city walking videos, we develop an scalable annotation pipeline that aligns human navigation trajectories with language instructions grounded in real-world landmarks. UrbanNav encompasses over 1,500 hours of navigation data and 3 million instruction-trajectory-landmark triplets, capturing a wide range of urban scenarios. Our model learns robust navigation policies to tackle complex urban scenarios, demonstrating superior spatial reasoning, robustness to noisy instructions, and generalization to unseen urban settings. Experimental results show that UrbanNav significantly outperforms existing methods, highlighting the potential of large-scale web video data to enable language-guided, real-world urban navigation for embodied agents.

Kailin Lyu, Long Xiao, Jianing Zeng, Junhao Dong, Xuexin Liu, Zhuojun Zou, Haoyue Yang, Lin Shu, Jie Hao

Traditional vision-based material perception methods often experience substantial performance degradation under visually impaired conditions, thereby motivating the shift toward non-visual multimodal material perception. Despite this, existing approaches frequently perform naive fusion of multimodal inputs, overlooking key challenges such as modality-specific noise, missing modalities common in real-world scenarios, and the dynamically varying importance of each modality depending on the task. These limitations lead to suboptimal performance across several benchmark tasks. In this paper, we propose a robust multimodal fusion framework, TouchFormer. Specifically, we employ a Modality-Adaptive Gating (MAG) mechanism and intra- and inter-modality attention mechanisms to adaptively integrate cross-modal features, enhancing model robustness. Additionally, we introduce a Cross-Instance Embedding Regularization(CER) strategy, which significantly improves classification accuracy in fine-grained subcategory material recognition tasks. Experimental results demonstrate that, compared to existing non-visual methods, the proposed TouchFormer framework achieves classification accuracy improvements of 2.48% and 6.83% on SSMC and USMC tasks, respectively. Furthermore, real-world robotic experiments validate TouchFormer's effectiveness in enabling robots to better perceive and interpret their environment, paving the way for its deployment in safety-critical applications such as emergency response and industrial automation.

Shouyi Lu, Huanyu Zhou, Guirong Zhuo, Xiao Tang

A novel learning-optimization-combined 4D radar odometry model, named DNOI-4DRO, is proposed in this paper. The proposed model seamlessly integrates traditional geometric optimization with end-to-end neural network training, leveraging an innovative differentiable neural-optimization iteration operator. In this framework, point-wise motion flow is first estimated using a neural network, followed by the construction of a cost function based on the relationship between point motion and pose in 3D space. The radar pose is then refined using Gauss-Newton updates. Additionally, we design a dual-stream 4D radar backbone that integrates multi-scale geometric features and clustering-based class-aware features to enhance the representation of sparse 4D radar point clouds. Extensive experiments on the VoD and Snail-Radar datasets demonstrate the superior performance of our model, which outperforms recent classical and learning-based approaches. Notably, our method even achieves results comparable to A-LOAM with mapping optimization using LiDAR point clouds as input.

Yuyan Liu, Li Zhang, Di Wu, Yan Zhang, Anran Huang, Zhi Wang, Liu Liu, Dan Guo

Articulated object modeling, which represents interconnected rigid bodies with their geometry, part segmentation, articulation tree, and physical properties, is crucial for robotic perception and manipulation. Recently existing methods like SAGCI leverage Interactive Perception (IP) to refine models through robot interaction. However, SAGCI suffers from prior-dependency (requiring initialization), neglects kinematic/dynamic constraints, and generates non-watertight meshes. To overcome these limitations, we propose SIAM, a novel framework for efficient and generalizable Single-Interaction Articulated Modeling. Given an initial point cloud, SIAM first enables minimal robot interaction to trigger object motion. It then precisely segments parts by analyzing point cloud differences pre- and post-interaction. For joint parameter estimation, we introduce an optimization incorporating novel kinematic energy constraints, enhancing physical consistency. Finally, we reconstruct a high-quality, topologically watertight mesh by learning 3D Gaussian Primitives from multi-view RGB-D observations under deformation. Extensive experiments on the PartNet-Mobility benchmark demonstrate state-of-the-art articulation modeling performance. Successful real-world deployment with an xArm robot further validates the framework's practicality and transferability. SIAM achieves accurate, prior-free modeling with significantly reduced interaction cost.

Yu Liu, Zhijie Liu, Xiao Ren, Youfu Li, He Kong

Predicting pedestrian motion trajectories is critical for the path planning and motion control of autonomous vehicles. Recent diffusion-based models have shown promising results in capturing the inherent stochasticity of pedestrian behavior for trajectory prediction. However, the absence of explicit semantic modelling of pedestrian intent in many diffusion-based methods may result in misinterpreted behaviors and reduced prediction accuracy. To address the above challenges, we propose a diffusion-based pedestrian trajectory prediction framework that incorporates both short-term and long-term motion intentions. Short-term intent is modelled using a residual polar representation, which decouples direction and magnitude to capture fine-grained local motion patterns. Long-term intent is estimated through a learnable, token-based endpoint predictor that generates multiple candidate goals with associated probabilities, enabling multimodal and context-aware intention modelling. Furthermore, we enhance the diffusion process by incorporating adaptive guidance and a residual noise predictor that dynamically refines denoising accuracy. The proposed framework is evaluated on the widely used ETH, UCY, NBA, and SDD benchmarks, demonstrating competitive results against state-of-the-art methods.

Litao Liu, Wentao Wang, Yifan Han, Zhuoli Xie, Pengfei Yi, Junyan Li, Wenzhao Lian

Multi-task imitation learning (MTIL) has shown significant potential in robotic manipulation by enabling agents to perform various tasks using a single policy. It simplifies the policy deployment and enhances the agent's adaptability across different scenarios. However, key challenges remain, such as maintaining action reliability (e.g., avoiding abnormal action sequences that deviate from nominal task trajectories) and generalizing to unseen tasks with a few expert demonstrations. To address these challenges, we introduce the Foresight-Augmented Manipulation (FoAM) policy, a novel MTIL policy that pioneers the use of multi-modal goal conditions as input and introduces a foresight augmentation in addition to the general action reconstruction. FoAM enables the agent to reason about its actions' visual consequences (foresight) and to be guided by these more expressive representations during task execution. Extensive experiments on over 100 tasks in simulation and real-world settings demonstrate that FoAM significantly enhances MTIL policy performance, outperforming state-of-the-art baselines by up to 41% in success rate. We released our simulation suites that include over 80 challenging tasks across more than 10 scenarios designed for manipulation policy training and evaluation.

Chenghao Liu, Jiachen Zhang, Chengxuan Li, Zhimu Zhou, Shixin Wu, Songfang Huang, Huiling Duan

Vision-Language-Action (VLA) models process visual inputs independently at each timestep, discarding valuable temporal information inherent in robotic manipulation tasks. This frame-by-frame processing makes models vulnerable to visual noise while ignoring the substantial coherence between consecutive frames in manipulation sequences. We propose Temporal Token Fusion (TTF), a training-free approach that intelligently integrates historical and current visual representations to enhance VLA inference quality. Our method employs dual-dimension detection combining efficient grayscale pixel difference analysis with attention-based semantic relevance assessment, enabling selective temporal token fusion through hard fusion strategies and keyframe anchoring to prevent error accumulation. Comprehensive experiments across LIBERO, SimplerEnv, and real robot tasks demonstrate consistent improvements: 4.0 percentage points average on LIBERO (72.4% vs 68.4% baseline), cross-environment validation on SimplerEnv (4.8% relative improvement), and 8.7% relative improvement on real robot tasks. Our approach proves model-agnostic, working across OpenVLA and VLA-Cache architectures. Notably, TTF reveals that selective Query matrix reuse in attention mechanisms enhances rather than compromises performance, suggesting promising directions for direct KQV matrix reuse strategies that achieve computational acceleration while improving task success rates.

Tzu-Jung Lin, Jia-Fong Yeh, Hung-Ting Su, Chung-Yi Lin, Yi-Ting Chen, Winston H. Hsu

In open-vocabulary mobile manipulation (OVMM), task success often hinges on the selection of an appropriate base placement for the robot. Existing approaches typically navigate to proximity-based regions without considering affordances, resulting in frequent manipulation failures. We propose Affordance-Guided Coarse-to-Fine Exploration, a zero-shot framework for base placement that integrates semantic understanding from vision-language models (VLMs) with geometric feasibility through an iterative optimization process. Our method constructs cross-modal representations, namely Affordance RGB and Obstacle Map+, to align semantics with spatial context. This enables reasoning that extends beyond the egocentric limitations of RGB perception. To ensure interaction is guided by task-relevant affordances, we leverage coarse semantic priors from VLMs to guide the search toward task-relevant regions and refine placements with geometric constraints, thereby reducing the risk of convergence to local optima. Evaluated on five diverse open-vocabulary mobile manipulation tasks, our system achieves an 85% success rate, significantly outperforming classical geometric planners and VLM-based methods. This demonstrates the promise of affordance-aware and multimodal reasoning for generalizable, instruction-conditioned planning in OVMM.

Qiwei Liang, Boyang Cai, Rongyi He, Hui Li, Tao Teng, Haihan Duan, Changxin Huang, Runhao Zeng

Quadrupedal robots with manipulators offer strong mobility and adaptability for grasping in unstructured, dynamic environments through coordinated whole-body control. However, existing research has predominantly focused on static-object grasping, neglecting the challenges posed by dynamic targets and thus limiting applicability in dynamic scenarios such as logistics sorting and human–robot collaboration. To address this, we introduce DQ-Bench, a new benchmark that systematically evaluates dynamic grasping across varying object motions, velocities, heights, object types, and terrain complexities, along with comprehensive evaluation metrics. Building upon this benchmark, we propose DQ-Net, a compact teacher–student framework designed to infer grasp configurations from limited perceptual cues. During training, the teacher network leverages privileged information to holistically model both the static geometric properties and dynamic motion characteristics of the target, and integrates a grasp fusion module to deliver robust guidance for motion planning. Concurrently, we design a lightweight student network that performs dual-viewpoint temporal modeling using only the target mask, depth map, and proprioceptive state, enabling closed-loop action outputs without reliance on privileged data. Extensive experiments on DQ-Bench demonstrate that DQ-Net achieves robust dynamic objects grasping across multiple task settings, substantially outperforming baseline methods in both success rate and responsiveness. We will release our codebase and benchmark publicly.

Jiaqi Liang, Yue Chen, Qize Yu, Yan Shen, Haipeng Zhang, Hao Dong, Ruihai Wu

Furniture assembly is a crucial yet challenging task for robots, requiring precise dual-arm coordination where one arm manipulates parts while the other provides collaborative support and stabilization. To accomplish this task more effectively, robots need to actively adapt support strategies throughout the long-horizon assembly process, while also generalizing across diverse part geometries. We propose A3D, a framework which learns adaptive affordances to identify optimal support and stabilization locations on furniture parts. The method employs dense point-level geometric representations to model part interaction patterns, enabling generalization across varied geometries. To handle evolving assembly states, we introduce an adaptive module that uses interaction feedback to dynamically adjust support strategies during assembly based on previous interactions. We establish a simulation environment featuring 50 diverse parts across 8 furniture types, designed for dual-arm collaboration evaluation. Experiments demonstrate that our framework generalizes effectively to diverse part geometries and furniture categories in both simulation and real-world settings.

Dingkang Liang, Cheng Zhang, Xiaopeng Xu, Jianzhong Ju, Zhenbo Luo, Xiang Bai

Task scheduling has become increasingly critical for embodied AI, where agents need to follow natural language instructions and execute actions efficiently in 3D physical worlds. Existing datasets for task planning in 3D environments often simplify the problem, lacking operations research knowledge for task scheduling and 3D grounding for real-world applications. In this work, we propose Operations Research Knowledge-based 3D Grounded Task Scheduling (OKS3D), a new task that requires synerization of language understanding, 3D grounding, and efficiency optimization for embodied agents. OKS3D reflects real-world demands by requiring agents to generate efficient, step-by-step schedules that are grounded in 3D space. To facilitate research on OKS3D, we construct a large-scale dataset called OKS3D-60K, comprising 60K tasks across 4K real-world scenes. Furthermore, we propose GRANT, an embodied multi-modal large language model equipped with a simple yet effective scheduling token mechanism to generate efficient task schedules and grounded actions. Extensive experiments on the OKS3D-60K dataset validate the effectiveness of GRANT across language understanding, 3D grounding, and scheduling efficiency.

Alan Liang, Youquan Liu, Yu Yang, Dongyue Lu, Linfeng Li, Lingdong Kong, Huaici Zhao, Wei Tsang Ooi

Generative world models have become essential data engines for autonomous driving, yet most focus on videos or occupancy grids and overlook the unique challenges of LiDAR. Extending LiDAR generation to dynamic 4D modeling requires addressing controllability, temporal coherence, and standardized evaluation. We present LiDARCrafter, a unified framework for controllable 4D LiDAR generation and editing. Free-form language instructions are converted into ego-centric scene graphs that guide a tri-branch diffusion model to generate object geometry, motion, and structural priors. An autoregressive module further produces temporally coherent and stable LiDAR sequences with improved global consistency. To enable fair comparison, we introduce a comprehensive benchmark covering scene-, object-, and sequence-level metrics for rigorous and reproducible evaluation. Experiments on nuScenes show that LiDARCrafter achieves state-of-the-art fidelity, controllability, and temporal consistency, paving the way for scalable data augmentation and realistic simulation in diverse scenarios. Code have been publicly available at https://lidarcrafter.github.io.

Wei Li, Renshan Zhang, Rui Shao, Zhijian Fang, Kaiwen Zhou, Zhuotao Tian, Liqiang Nie

Vision-Language-Action (VLA) models have advanced in robotic manipulation, yet practical deployment remains hindered by two key limitations: **1) perceptual redundancy**, where irrelevant visual inputs are processed inefficiently, and **2) superficial instruction-vision alignment**, which hampers semantic grounding of actions. In this paper, we propose **SemanticVLA**, a novel VLA framework that performs Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation. Specifically: **1)** To sparsify redundant perception while preserving semantic alignment, **Semantic-guided Dual Visual Pruner (SD-Pruner)** performs: Instruction-driven Pruner (ID-Pruner) extracts global action cues and local semantic anchors in SigLIP; Spatial-aggregation Pruner (SA-Pruner) compacts geometry-rich features into task-adaptive tokens in DINOv2. **2)** To exploit sparsified features and integrate semantics with spatial geometry, **Semantic-complementary Hierarchical Fuser (SH-Fuser)** fuses dense patches and sparse tokens across SigLIP and DINOv2 for coherent representation. **3)** To enhance the transformation from perception to action, **Semantic-conditioned Action Coupler (SA-Coupler)** replaces the conventional observation-to-DoF approach, yielding more efficient and interpretable behavior modeling for manipulation tasks. Extensive experiments on simulation and real-world tasks show that SemanticVLA sets a new SOTA in both performance and efficiency. SemanticVLA surpasses OpenVLA on LIBERO benchmark by **21.1%** in success rate, while reducing training cost and inference latency by **3.0×** and **2.7×**.

Hao Li, Shuai Yang, Yilun Chen, Xinyi Chen, Xiaoda Yang, Yang Tian, Hanqing Wang, Tai Wang, Dahua Lin, Feng Zhao 等

Recent vision-language-action (VLA) models built on pretrained vision-language models (VLMs) have demonstrated strong performance in robotic manipulation. However, these models remain constrained by the single-frame image paradigm and fail to fully leverage the temporal information offered by multi-frame histories, as directly feeding multiple frames into VLM backbones incurs substantial computational overhead and inference latency. We propose CronusVLA, a unified framework that extends single-frame VLA models to the multi-frame paradigm. CronusVLA follows a two-stage process: (1) Single-frame pretraining on large-scale embodied datasets with autoregressive prediction of action tokens, establishing an effective embodied vision-language foundation; (2) Multi-frame post-training, which adapts the prediction of the vision-language backbone from discrete tokens to learnable features, and aggregates historical information via feature chunking. CronusVLA effectively addresses the existing challenges of multi-frame modeling while enhancing performance. To evaluate the robustness under temporal and spatial disturbances, we introduce SimplerEnv-OR, a novel benchmark featuring 24 types of observational disturbances and 120 severity levels. Experiments across three embodiments in simulated and real-world environments demonstrate that CronusVLA achieves leading performance and superior robustness, with a 70.9% success rate on SimplerEnv, a 26.8% improvement over OpenVLA on LIBERO, and the highest robustness score on SimplerEnv-OR, showing the promise of efficient multi-frame adaptation for real-world VLA deployment.