arXiv subjects

Lifeng Zhou

Publications and source records attributed to Lifeng Zhou.

At least 19 recordsLinked to original sources

arXiv2026

GlanceWAM: Sparse Test-Time Imagination for World-Action Models

Video generative models provide rich physical priors for robot learning, yet existing world-action models (WAMs) face a fundamental trade-off: synchronous video generation at control rate is latency-prohibitive, while abandoning test-time visual imagination sacrifices task success. We show that visual imagination achieves both real-time inference and superior success rates when generated asynchronously off the critical path and consumed directly in latent space. We introduce GlanceWAM, which decouples imagination from control within a single video DiT: an asynchronous proposer glances ahead on a slow clock to imagine a single lookahead frame seconds into the future in the background, while an action head decodes action chunks at control rate (48 ms) purely in latent space without blocking. Enabled by a non-interfering attention mask that isolates video representations and staleness-robust horizon training that accommodates asynchronous lookahead aging, GlanceWAM breaks the speed-success dilemma. Trained purely on demonstrations, it attains 72.2% on the 24-task RoboCasa kitchen benchmark (surpassing synchronous Cosmos Policy at 67.1% and imagination-free co-training at 64.4%) and 99.0% on LIBERO, executing at 48 ms per chunk on an NVIDIA A100 GPU (24x faster than synchronous baselines). Code is available at https://github.com/linhanwang/GlanceWAM.

cs.CV↗

arXiv2026

Latent World Models with Monotone Planning Costs for Image-Goal Navigation

Image-goal navigation with latent world models requires not only accurate future prediction, but also a planning cost that reliably ranks candidate action sequences. We define the cost as the cosine distance between the predicted future embedding and the goal embedding, and show that poor cost ordering can mislead sampling-based planners such as Cross-Entropy Method (CEM). To address this, we propose a latent world model built on a frozen DINO-family encoder and train it with two complementary objectives. An autoregressive rollout loss reduces the gap between training and multi-step planning rollouts, while a Monotone Cost Ranking (MCR) loss directly encourages increasingly perturbed action sequences to receive higher planning costs. We also study InfoNCE-based action-contrastive training and find that temporal permutation negatives distort the latent geometry and degrade planning performance. On the GNM navigation dataset, our method outperforms Navigation World Models (NWM), DINO-WM, OmniVLA, and NoMaD, achieving state-of-the-art image-goal navigation performance while reducing orientation error by $2.7\times$ over the same-encoder DINO WM baseline. We also deploy the model zero-shot on a physical robot, where it follows goal-directed paths in unseen indoor and outdoor environments.

cs.RO↗

arXiv2026

TransGraspNet: Physically and Geometrically Consistent Manipulation of Transparent Labware

Manipulating transparent laboratory glassware that contains liquid is inherently safety-critical: even small geometric errors can cause unstable grasps and hazardous spillage. Although recent progress has been made in transparent object perception and robotic grasping, most existing systems optimize detection, depth reconstruction, and grasp planning independently, which leads to cross-stage inconsistency imperfect boundaries induce depth bleeding, distorted surfaces corrupt normal estimation, and task agnostic grasp scoring yields tilted or off-center grasps that fail under dynamic motion. In this paper, we propose TransGraspNet, a geometry physics consistent framework that explicitly enforces consistency from perception to execution through three coupled principles: boundary consistency to produce structurally reliable object contours as downstream priors, surface consistency to preserve geometric fidelity and surface normal accuracy during depth reconstruction, and physics consistency to refine grasp selection with centroid alignment and wrench-space stability for upright and dynamically robust manipulation. We evaluate TransGraspNet on public benchmarks, a dedicated transparent glassware dataset, and a real robotic platform. The results show improved boundary quality and surface normal fidelity, and demonstrate strong task-level performance in cluttered transparent scenes. Most importantly, the proposed system achieves reliable real-world operation, including high grasp success rates in clutter and zero spillage during high speed liquid transport, highlighting the effectiveness of our method.

cs.RO↗

arXiv2026

What's Hidden Matters: Identifying Planning-Critical Occluded Agents using Vision-Language Models

Autonomous vehicles must safely navigate complex environments where planning-critical agents may be hidden from view. Current approaches often treat all occlusions with uniform conservatism, yielding needlessly defensive driving, or they infer hidden spaces without estimating the impact on the planner. This work bridges the critical gap between perception and planning by enabling Vision-Language Models (VLMs) to identify and reason about the specific hidden agents that are most critical to the ego-vehicle's trajectory. We introduce a novel framework that uses Planning KL-divergence (PKL), an information-theoretic metric, to systematically identify and rank occluded agents based on their impact on the ego vehicle's plan. Using this planning-aware ranking, we employ an expert VLM (GPT-5) to generate rich, structured annotations that capture the visual evidence and reasoning required for this task. We apply this framework to the nuScenes dataset to create a new benchmark focused on high-impact scenarios. We conduct comprehensive experiments on a wide range of general-purpose and domain-adapted VLMs, demonstrating that fine-tuning on our PKL-guided data yields dramatic performance improvements across all models. Notably, our results show that smaller, fine-tuned models significantly outperform their much larger zero-shot counterparts, and that our PKL-guided data selection strategy improves performance by approximately 30\% over random sampling. Our work presents the first systematic approach for training VLMs to focus on planning-critical occlusions, enabling more semantically grounded and efficient risk assessment in autonomous driving.

cs.RO↗

arXiv2026

Threading Optimization for Vision-Language-Action Model Inference in Low-Cost Smart Agricultural Manipulation

Vision-Language Action (VLA) models continue to face challenges such as slow inference speed and difficulty performing fine-grained motion adjustments, limiting their widespread adoption in industry. While the Real-Time Action Chunking (RTAC) algorithm has been proposed to address these bottlenecks, bridging the gap between the algorithm provided in pseudocode to a stable, real-world deployment on a low-cost robotic arm remains a challenge. In this work, we present a complete system-level implementation of RTAC tailored for a low-cost robotic manipulation system. We advance beyond the original high-level pseudocode by optimizing the threading implementation for the policy inference and control pipeline, reducing end-to-end latency and improving responsiveness without modifying the underlying policy. We evaluate this system on tasks involving the manipulation of agricultural produce, specifically garlic bulbs and walnuts. Experimental results demonstrate that our custom threading implementation significantly improves control stability and speed compared to the base implementation of RTAC.

cs.RO↗

arXiv2026

ROG-Grasp: Root-Oriented Geometry for Robotic Grasping and Placement

Orientation-aware manipulation is essential in post-harvest agricultural processing, where produce must be grasped and placed in consistent configurations. This paper presents ROG-Grasp, a geometry-based robotic grasping and placement framework that estimates the produce orientation from root surface geometry using RGB-D perception. A YOLO-based root detector and point cloud plane fitting are used to infer the root normal, enabling stable grasp pose generation and orientation-constrained Cartesian motion planning. Experiments on tomatoes and onions demonstrate high success rates and stable execution time in both isolated and cluttered scenarios. Compared with vision-language-action (VLA) policies, the proposed method achieves more reliable and accurate grasp completion with faster execution. These results highlight the effectiveness of geometry-driven perception for practical orientation-controlled manipulation tasks. A video of our paper is available online https://youtu.be/Ir2UtGODdMo.

cs.RO↗

arXiv2026

GA3T: A Ground-Aerial Terrain Traversability Dataset for Heterogeneous Robot Teams in Unstructured Environments

Heterogeneous air-ground robot teams combine complementary sensing modalities, mobility characteristics, and spatial viewpoints that can significantly enhance perception in complex outdoor environments. However, progress in multi-robot collaborative perception has been constrained by the lack of real-world datasets featuring overlapping multi-modal observations from platforms operating in unstructured terrain. We present GA3T (Ground-Aerial Team for Terrain Traversal), a real-world multi-robot collaborative perception dataset collected using a Clearpath Husky UGV and an Autel EVO~II UAV across diverse unstructured environments, including forest trails, rocky paths, muddy terrain, snow piles, and grass-covered fields. The ground platform provides 3D LiDAR, stereo camera, IMU, and GPS data, while the aerial platform contributes RGB imagery, thermal/infrared observations, and GPS from a complementary overhead viewpoint, allowing for rich cross-modal and cross-view perception. The dataset is collected in 4 unique environments, with over 13,000 synchronized frames across approximately 29 minutes of operation, and includes both SAM~3-based zero-shot segmentation and over 8,000 manually labeled images. A unique aspect of the dataset is its early-spring collection period, during which sparse tree canopies allow the aerial robot to partially observe the ground robot and terrain through the trees, allowing for occlusion-aware collaborative perception. Unlike prior multi-robot datasets that focus on SLAM or simulated cooperative driving, GA3T is specifically designed to support research on cross-view perception, air-ground viewpoint fusion, traversability estimation, and collaborative scene understanding in real off-road environments.

cs.RO↗

arXiv2026

VILAS: A VLA-Integrated Low-cost Architecture with Soft Grasping for Robotic Manipulation

We present VILAS, a fully low-cost, modular robotic manipulation platform designed to support end-to-end vision-language-action (VLA) policy learning and deployment on accessible hardware. The system integrates a Fairino FR5 collaborative arm, a Jodell RG52-50 electric gripper, and a dual-camera perception module, unified through a ZMQ-based communication architecture that seamlessly coordinates teleoperation, data collection, and policy deployment within a single framework. To enable safe manipulation of fragile objects without relying on explicit force sensing, we design a kirigami-based soft compliant gripper extension that induces predictable deformation under compressive loading, providing gentle and repeatable contact with delicate targets. We deploy and evaluate three state-of-the-art VLA models on the VILAS platform: pi_0, pi_0.5, and GR00T N1.6. All models are fine-tuned from publicly released pretrained checkpoints using an identical demonstration dataset collected via our teleoperation pipeline. Experiments on a grape grasping task validate the effectiveness of the proposed system, confirming that capable manipulation policies can be successfully trained and deployed on low-cost modular hardware. Our results further provide practical insights into the deployment characteristics of current VLA models in real-world settings.

cs.RO↗

arXiv2026

LLM-Foraging: Large Language Models for Decentralized Swarm Robot Foraging

Swarm foraging algorithms, such as the central-place foraging algorithm (CPFA), typically rely on offline parameter optimization using genetic algorithms (GA) or reinforcement learning, yielding policies tightly coupled to a specific combination of team size, arena size, and resource distribution. When deployment conditions change, performance degrades, and retraining is computationally expensive. We propose LLM-Foraging, a decentralized swarm controller that augments the CPFA state machine with a large language model (LLM) tactical decision-maker at three structured decision points, namely post-deposit, central-zone arrival, and search starvation. Each robot runs its own LLM client and queries it using only locally observable state, while the existing CPFA motion and sensing stack executes the selected action. Because the LLM serves as a general decision policy rather than parameters fitted to a single configuration, the controller is training-free at deployment and transfers across configurations without re-optimization. We evaluate LLM-Foraging in Gazebo with TurtleBot3 robots across 36 configurations spanning team sizes of 4 to 10 robots, arena sizes from 6x6 to 10x10 meters, and three resource distributions (clustered, powerlaw, random). LLM-Foraging collects more resources than the GA-tuned CPFA baseline across the evaluated configurations and is more consistent, a property that the GA's single-configuration tuning does not transfer.

cs.RO↗

arXiv2026

Fuzzy Encoding-Decoding to Improve Spiking Q-Learning Performance in Autonomous Driving

This paper develops an end-to-end fuzzy encoder-decoder architecture for enhancing vision-based multi-modal deep spiking Q-networks in autonomous driving. The method addresses two core limitations of spiking reinforcement learning: information loss stemming from the conversion of dense visual inputs into sparse spike trains, and the limited representational capacity of spike-based value functions, which often yields weakly discriminative Q-value estimates. The encoder introduces trainable fuzzy membership functions to generate expressive, population-based spike representations, and the decoder uses a lightweight neural decoder to reconstruct continuous Q-values from spiking outputs. Experiments on the HighwayEnv benchmark show that the proposed architecture substantially improves decision-making accuracy and closes the performance gap between spiking and non-spiking multi-modal Q-networks. The results highlight the potential of this framework for efficient and real-time autonomous driving with spiking neural networks.

cs.NE↗

arXiv2026

Policy-Guided World Model Planning for Language-Conditioned Visual Navigation

Navigating to a visually specified goal given natural language instructions remains a fundamental challenge in embodied AI. Existing approaches either rely on reactive policies that struggle with long-horizon planning, or employ world models that suffer from poor action initialization in high-dimensional spaces. We present PiJEPA, a two-stage framework that combines the strengths of learned navigation policies with latent world model planning for instruction-conditioned visual navigation. In the first stage, we finetune an Octo-based generalist policy, augmented with a frozen pretrained vision encoder (DINOv2 or V-JEPA-2), on the CAST navigation dataset to produce an informed action distribution conditioned on the current observation and language instruction. In the second stage, we use this policy-derived distribution to warm-start Model Predictive Path Integral (MPPI) planning over a separately trained JEPA world model, which predicts future latent states in the embedding space of the same frozen encoder. By initializing the MPPI sampling distribution from the policy prior rather than from an uninformed Gaussian, our planner converges faster to high-quality action sequences that reach the goal. We systematically study the effect of the vision encoder backbone, comparing DINOv2 and V-JEPA-2, across both the policy and world model components. Experiments on real-world navigation tasks demonstrate that PiJEPA significantly outperforms both standalone policy execution and uninformed world model planning, achieving improved goal-reaching accuracy and instruction-following fidelity.

cs.RO↗

arXiv2026

IDSelect: A RL-Based Cost-Aware Selection Agent for Video-based Multi-Modal Person Recognition

Video-based person recognition achieves robust identification by integrating face, body, and gait. However, current systems waste computational resources by processing all modalities with fixed heavyweight ensembles regardless of input complexity. To address these limitations, we propose IDSelect, a reinforcement learning-based cost-aware selector that chooses one pre-trained model per modality per-sequence to optimize the accuracy-efficiency trade-off. Our key insight is that an input-conditioned selector can discover complementary model choices that surpass fixed ensembles while using substantially fewer resources. IDSelect trains a lightweight agent end-to-end using actor-critic reinforcement learning with budget-aware optimization. The reward balances recognition accuracy with computational cost, while entropy regularization prevents premature convergence. At inference, the policy selects the most probable model per modality and fuses modality-specific similarities for the final score. Extensive experiments on challenging video-based datasets demonstrate IDSelect's superior efficiency: on CCVID, it achieves 95.9% Rank-1 accuracy with 92.4% less computation than strong baselines while improving accuracy by 1.8%; on MEVID, it reduces computation by 41.3% while maintaining competitive performance.

cs.CV↗

arXiv2025

New Spiking Architecture for Multi-Modal Decision-Making in Autonomous Vehicles

This work proposes an end-to-end multi-modal reinforcement learning framework for high-level decision-making in autonomous vehicles. The framework integrates heterogeneous sensory input, including camera images, LiDAR point clouds, and vehicle heading information, through a cross-attention transformer-based perception module. Although transformers have become the backbone of modern multi-modal architectures, their high computational cost limits their deployment in resource-constrained edge environments. To overcome this challenge, we propose a spiking temporal-aware transformer-like architecture that uses ternary spiking neurons for computationally efficient multi-modal fusion. Comprehensive evaluations across multiple tasks in the Highway Environment demonstrate the effectiveness and efficiency of the proposed approach for real-time autonomous decision-making.

cs.LG↗

arXiv2025

Vision Language Models Cannot Plan, but Can They Formalize?

The advancement of vision language models (VLMs) has empowered embodied agents to accomplish simple multimodal planning tasks, but not long-horizon ones requiring long sequences of actions. In text-only simulations, long-horizon planning has seen significant improvement brought by repositioning the role of LLMs. Instead of directly generating action sequences, LLMs translate the planning domain and problem into a formal planning language like the Planning Domain Definition Language (PDDL), which can call a formal solver to derive the plan in a verifiable manner. In multimodal environments, research on VLM-as-formalizer remains scarce, usually involving gross simplifications such as predefined object vocabulary or overly similar few-shot examples. In this work, we present a suite of five VLM-as-formalizer pipelines that tackle one-shot, open-vocabulary, and multimodal PDDL formalization. We evaluate those on an existing benchmark while presenting another two that for the first time account for planning with authentic, multi-view, and low-quality images. We conclude that VLM-as-formalizer greatly outperforms end-to-end plan generation. We find that visual grounding of object relations remains the primary bottleneck for weaker VLMs, while stronger models have largely overcome this limitation. While generating intermediate, textual representations such as captions or scene graphs partially compensate for the performance, their inconsistent gain leaves headroom for future research directions on multimodal planning formalization.

cs.CL↗

arXiv2025

CLAW: A Vision-Language-Action Framework for Weight-Aware Robotic Grasping

Vision-language-action (VLA) models have recently emerged as a promising paradigm for robotic control, enabling end-to-end policies that ground natural language instructions into visuomotor actions. However, current VLAs often struggle to satisfy precise task constraints, such as stopping based on numeric thresholds, since their observation-to-action mappings are implicitly shaped by training data and lack explicit mechanisms for condition monitoring. In this work, we propose CLAW (CLIP-Language-Action for Weight), a framework that decouples condition evaluation from action generation. CLAW leverages a fine-tuned CLIP model as a lightweight prompt generator, which continuously monitors the digital readout of a scale and produces discrete directives based on task-specific weight thresholds. These prompts are then consumed by $\pi_0$, a flow-based VLA policy, which integrates the prompts with multi-view camera observations to produce continuous robot actions. This design enables CLAW to combine symbolic weight reasoning with high-frequency visuomotor control. We validate CLAW on three experimental setups: single-object grasping and mixed-object tasks requiring dual-arm manipulation. Across all conditions, CLAW reliably executes weight-aware behaviors and outperforms both raw-$\pi_0$ and fine-tuned $\pi_0$ models. A video of our paper is available online https://youtu.be/MuMYj2QgReI.

cs.RO↗

arXiv2025

Failure-Aware Multi-Robot Coordination for Resilient and Adaptive Target Tracking

Multi-robot coordination is crucial for autonomous systems, yet real-world deployments often encounter various failures. These include both temporary and permanent disruptions in sensing and communication, which can significantly degrade system robustness and performance if not explicitly modeled. Despite its practical importance, failure-aware coordination remains underexplored in the literature. To bridge the gap between idealized conditions and the complexities of real-world environments, we propose a unified failure-aware coordination framework designed to enable resilient and adaptive multi-robot target tracking under both temporary and permanent failure conditions. Our approach systematically distinguishes between two classes of failures: (1) probabilistic and temporary disruptions, where robots recover from intermittent sensing or communication losses by dynamically adapting paths and avoiding inferred danger zones, and (2) permanent failures, where robots lose sensing or communication capabilities irreversibly, requiring sustained, decentralized behavioral adaptation. To handle these scenarios, the robot team is partitioned into subgroups. Robots that remain connected form a communication group and collaboratively plan using partially centralized nonlinear optimization. Robots experiencing permanent disconnection or failure continue to operate independently through decentralized or individual optimization, allowing them to contribute to the task within their local context. We extensively evaluate our method across a range of benchmark variations and conduct a comprehensive assessment under diverse real-world failure scenarios. Results show that our framework consistently achieves robust performance in realistic environments with unknown danger zones, offering a practical and generalizable solution for the multi-robot systems community.

cs.RO↗

arXiv2025

LLM-Flock: Decentralized Multi-Robot Flocking via Large Language Models and Influence-Based Consensus

Large Language Models (LLMs) have advanced rapidly in recent years, demonstrating strong capabilities in problem comprehension and reasoning. Inspired by these developments, researchers have begun exploring the use of LLMs as decentralized decision-makers for multi-robot formation control. However, prior studies reveal that directly applying LLMs to such tasks often leads to unstable and inconsistent behaviors, where robots may collapse to the centroid of their positions or diverge entirely due to hallucinated reasoning, logical inconsistencies, and limited coordination awareness. To overcome these limitations, we propose a novel framework that integrates LLMs with an influence-based plan consensus protocol. In this framework, each robot independently generates a local plan toward the desired formation using its own LLM. The robots then iteratively refine their plans through a decentralized consensus protocol that accounts for their influence on neighboring robots. This process drives the system toward a coherent and stable flocking formation in a fully decentralized manner. We evaluate our approach through comprehensive simulations involving both state-of-the-art closed-source LLMs (e.g., o3-mini, Claude 3.5) and open-source models (e.g., Llama3.1-405b, Qwen-Max, DeepSeek-R1). The results show notable improvements in stability, convergence, and adaptability over previous LLM-based methods. We further validate our framework on a physical team of Crazyflie drones, demonstrating its practical viability and effectiveness in real-world multi-robot systems.

cs.RO↗

arXiv2025

LLM-Land: Large Language Models for Context-Aware Drone Landing

Autonomous landing is essential for drones deployed in emergency deliveries, post-disaster response, and other large-scale missions. By enabling self-docking on charging platforms, it facilitates continuous operation and significantly extends mission endurance. However, traditional approaches often fall short in dynamic, unstructured environments due to limited semantic awareness and reliance on fixed, context-insensitive safety margins. To address these limitations, we propose a hybrid framework that integrates large language model (LLMs) with model predictive control (MPC). Our approach begins with a vision-language encoder (VLE) (e.g., BLIP), which transforms real-time images into concise textual scene descriptions. These descriptions are processed by a lightweight LLM (e.g., Qwen 2.5 1.5B or LLaMA 3.2 1B) equipped with retrieval-augmented generation (RAG) to classify scene elements and infer context-aware safety buffers, such as 3 meters for pedestrians and 5 meters for vehicles. The resulting semantic flags and unsafe regions are then fed into an MPC module, enabling real-time trajectory replanning that avoids collisions while maintaining high landing precision. We validate our framework in the ROS-Gazebo simulator, where it consistently outperforms conventional vision-based MPC baselines. Our results show a significant reduction in near-miss incidents with dynamic obstacles, while preserving accurate landings in cluttered environments.

cs.RO↗