arXiv subjects

Zezhou Sun

Publications and source records attributed to Zezhou Sun.

15 recordsLinked to original sources

arXiv2026

Sub-Pixel Affine Registration of Space Debris Images via the Radon Point Spread Function

Inter-frame affine misalignment caused by platform jitter and attitude adjustments poses a fundamental challenge for multi-frame analysis of point targets in optical surveillance. Conventional registration methods rely on spatial intensity correlations or distinctive image features, both of which are largely absent in low-signal-to-noise-ratio point target imagery. We introduce the Radon Point Spread Function (RPSF) to characterize point targets in the Radon-transformed domain, and derive a closed-form framework that jointly estimates inter-frame translation and rotation from as few as four scalar RPSF samples per frame pair. The method requires no iterative optimization, feature extraction or interpolation, which is suitable for resource-constrained onboard processing. Simulation results confirm sub-pixel translation accuracy and a mean rotation error of 0.2556{\deg} at 1{\deg} Radon angular resolution. Validation on five real space debris datasets including both ground-based and in-orbit observations yields a mean calibration error below 0.5 pixels, substantially exceeding the precision required for reliable multi-frame processing.

cs.CV↗

arXiv2026

UNCLE-Grasp: A Task-Adapted Framework for Uncertainty-Aware Grasping of Leaf-Occluded Strawberries

Robotic strawberry harvesting remains challenging under partial occlusion, where leaves obscure fruit geometry and make grasp decisions based on a single shape estimate unreliable. A partial observation may admit multiple plausible 3D completions, so a grasp feasible on one completion may fail on another. Existing uncertainty-aware grasping methods estimate uncertainty in pose, shape, or individual candidates, but do not aggregate grasp feasibility across completion hypotheses for an object-level attempt-or-abstain decision. We present UNCLE-Grasp, a task-adapted framework integrating learned shape completion, dropout-based variability estimation, physically grounded grasp evaluation, and risk-aware target-level decisions for leaf-occluded strawberries. Monte Carlo dropout generates multiple completion samples. For each sample, retained grasp candidates are combined into a wrench space to compute a completion-level force-closure score. Variability in this score across plausible completions, rather than geometric point variability alone, quantifies target-level grasp uncertainty. A conservative lower confidence bound determines whether to grasp or abstain. We evaluate the framework in simulation and on a physical robot under increasing synthetic and real leaf occlusion. At the highest simulated occlusion, UNCLE-Grasp raises success among attempted grasps from 0.780 for the strongest completed baseline to 0.870, with similar attempt rates of 0.860 and 0.880, respectively, and raises overall success from 0.680 to 0.740. On the physical robot at approximately 87% synthetic occlusion, it achieves 0.800 success among attempted grasps versus 0.483 for the strongest completed baseline, although at a lower attempt rate. These results show that UNCLE-Grasp enables more reliable risk-aware execution through selective abstention, with a trade-off between grasp reliability and harvesting yield.

cs.RO↗

arXiv2025

Imagination at Inference: Synthesizing In-Hand Views for Robust Visuomotor Policy Inference

Visual observations from different viewpoints can significantly influence the performance of visuomotor policies in robotic manipulation. Among these, egocentric (in-hand) views often provide crucial information for precise control. However, in some applications, equipping robots with dedicated in-hand cameras may pose challenges due to hardware constraints, system complexity, and cost. In this work, we propose to endow robots with imaginative perception - enabling them to 'imagine' in-hand observations from agent views at inference time. We achieve this via novel view synthesis (NVS), leveraging a fine-tuned diffusion model conditioned on the relative pose between the agent and in-hand views cameras. Specifically, we apply LoRA-based fine-tuning to adapt a pretrained NVS model (ZeroNVS) to the robotic manipulation domain. We evaluate our approach on both simulation benchmarks (RoboMimic and MimicGen) and real-world experiments using a Unitree Z1 robotic arm for a strawberry picking task. Results show that synthesized in-hand views significantly enhance policy inference, effectively recovering the performance drop caused by the absence of real in-hand cameras. Our method offers a scalable and hardware-light solution for deploying robust visuomotor policies, highlighting the potential of imaginative visual reasoning in embodied agents.

cs.RO↗

arXiv2025

GeoAware-VLA: Implicit Geometry Aware Vision-Language-Action Model

Vision-Language-Action (VLA) models often fail to generalize to unseen camera viewpoints, a limitation stemming from their difficulty in inferring robust 3D geometry from 2D images. We introduce GeoAware-VLA, a simple yet effective approach that enhances viewpoint invariance by integrating strong geometric priors into the vision backbone. Instead of training a visual encoder or relying on explicit 3D data, we leverage a frozen, pretrained geometric vision model as a feature extractor. A lightweight, trainable projection layer then adapts these geometrically-rich features for the policy decoder, relieving it of the burden of learning 3D consistency from scratch. Through extensive evaluations on the LIBERO and CALVIN benchmarks, we show that GeoAware-VLA preserves and even improves in-distribution performance while achieving substantial gains in zero-shot generalization to unseen camera poses, improving unseen-view success rates by an average of 35 percentage points on LIBERO and over 11 percentage points on CALVIN compared to their respective baselines. Crucially, these gains transfer to the physical world, where our model shows significant improvement on a real robotic platform. Our approach proves effective across both continuous and discrete action spaces, highlighting that robust geometric grounding is a key ingredient for building more generalizable robotic agents.

cs.RO↗

arXiv2025

A Hybrid Hinge-Beam Continuum Robot with Passive Safety Capping for Real-Time Fatigue Awareness

Cable-driven continuum robots offer high flexibility and lightweight design, making them well-suited for tasks in constrained and unstructured environments. However, prolonged use can induce mechanical fatigue from plastic deformation and material degradation, compromising performance and risking structural failure. In the state of the art, fatigue estimation of continuum robots remains underexplored, limiting long-term operation. To address this, we propose a fatigue-aware continuum robot with three key innovations: (1) a Hybrid Hinge-Beam structure where TwistBeam and BendBeam decouple torsion and bending: passive revolute joints in the BendBeam mitigate stress concentration, while TwistBeam's limited torsional deformation reduces BendBeam stress magnitude, enhancing durability; (2) a Passive Stopper that safely constrains motion via mechanical constraints and employs motor torque sensing to detect corresponding limit torque, ensuring safety and enabling data collection; and (3) a real-time fatigue-awareness method that estimates stiffness from motor torque at the limit pose, enabling online fatigue estimation without additional sensors. Experiments show that the proposed design reduces fatigue accumulation by about 49% compared with a conventional design, while passive mechanical limiting combined with motor-side sensing allows accurate estimation of structural fatigue and damage. These results confirm the effectiveness of the proposed architecture for safe and reliable long-term operation.

cs.RO↗

arXiv2025

Accurate and Scalable Simulation of Cavity-Based Networks in Modular Quantum Architectures

Cavity-mediated interconnects are a promising platform for scaling modular quantum computers by enabling high-fidelity inter-chip quantum state transmission and entanglement generation. In this work, we first model the dynamics of deterministic inter-chip quantum state transfer using the Stimulated Raman Adiabatic Passage (STIRAP) protocol, analyzing fidelity loss mechanisms under experimentally achievable qubit-cavity coupling and decoherence parameters. We then extend the NetSquid simulator, typically used for simulating long-range quantum communication networks, to support cavity-based communication channels for mediating inter-chip state transfer and entanglement generation. We model cavities as amplitude damping channels parameterized by physical system characteristics; cavity decay rate k and qubit-cavity coupling strength g, and analyze the impact of intrinsic qubit decoherence factors dictated by T1 and T2 times. Our simulations accurately represent the system's dynamics in both strong and weak coupling regimes, and identify critical trade-offs between fidelity, latency, and noise factors. The proposed framework supports faithful modeling and scalable simulation of modular architectures, and provides insights into design optimization for practical quantum network implementations.

quant-ph↗

arXiv2025

Towards Safe Imitation Learning via Potential Field-Guided Flow Matching

Deep generative models, particularly diffusion and flow matching models, have recently shown remarkable potential in learning complex policies through imitation learning. However, the safety of generated motions remains overlooked, particularly in complex environments with inherent obstacles. In this work, we address this critical gap by proposing Potential Field-Guided Flow Matching Policy (PF2MP), a novel approach that simultaneously learns task policies and extracts obstacle-related information, represented as a potential field, from the same set of successful demonstrations. During inference, PF2MP modulates the flow matching vector field via the learned potential field, enabling safe motion generation. By leveraging these complementary fields, our approach achieves improved safety without compromising task success across diverse environments, such as navigation tasks and robotic manipulation scenarios. We evaluate PF2MP in both simulation and real-world settings, demonstrating its effectiveness in task space and joint space control. Experimental results demonstrate that PF2MP enhances safety, achieving a significant reduction of collisions compared to baseline policies. This work paves the way for safer motion generation in unstructured and obstaclerich environments.

cs.RO↗

arXiv2025

Modeling Quantum Links for the Exploration of Distributed Quantum Computing Systems

Quantum computing offers the potential to solve certain complex problems, yet, scaling monolithic processors remains a major challenge. Modular and distributed architectures are proposed to build large-scale quantum systems while bringing the security advantages of quantum communication. At present, this requires accurate and computationally efficient models of quantum links across different scales to advance system design and guide experimental prototyping. In this work, we review protocols and models for estimating latency, losses, and fidelity in quantum communication primitives relying on quantum state distribution via microwave photons. We also propose a scalable simulation framework to support the design and evaluation of future distributed quantum computing systems.

quant-ph↗

arXiv2025

Can Large Vision Language Models Read Maps Like a Human?

In this paper, we introduce MapBench-the first dataset specifically designed for human-readable, pixel-based map-based outdoor navigation, curated from complex path finding scenarios. MapBench comprises over 1600 pixel space map path finding problems from 100 diverse maps. In MapBench, LVLMs generate language-based navigation instructions given a map image and a query with beginning and end landmarks. For each map, MapBench provides Map Space Scene Graph (MSSG) as an indexing data structure to convert between natural language and evaluate LVLM-generated results. We demonstrate that MapBench significantly challenges state-of-the-art LVLMs both zero-shot prompting and a Chain-of-Thought (CoT) augmented reasoning framework that decomposes map navigation into sequential cognitive processes. Our evaluation of both open-source and closed-source LVLMs underscores the substantial difficulty posed by MapBench, revealing critical limitations in their spatial reasoning and structured decision-making capabilities. We release all the code and dataset in https://github.com/taco-group/MapBench.

cs.CV↗

arXiv2024

Active Loop Closure for OSM-guided Robotic Mapping in Large-Scale Urban Environments

The autonomous mapping of large-scale urban scenes presents significant challenges for autonomous robots. To mitigate the challenges, global planning, such as utilizing prior GPS trajectories from OpenStreetMap (OSM), is often used to guide the autonomous navigation of robots for mapping. However, due to factors like complex terrain, unexpected body movement, and sensor noise, the uncertainty of the robot's pose estimates inevitably increases over time, ultimately leading to the failure of robotic mapping. To address this issue, we propose a novel active loop closure procedure, enabling the robot to actively re-plan the previously planned GPS trajectory. The method can guide the robot to re-visit the previous places where the loop-closure detection can be performed to trigger the back-end optimization, effectively reducing errors and uncertainties in pose estimation. The proposed active loop closure mechanism is implemented and embedded into a real-time OSM-guided robot mapping framework. Empirical results on several large-scale outdoor scenarios demonstrate its effectiveness and promising performance.

cs.RO↗

arXiv2022

Graph Gain: A Concave-Hull Based Volumetric Gain for Robotic Exploration

The existing volumetric gain for robotic exploration is calculated in the 3D occupancy map, while the sampling-based exploration method is extended in the reachable (free) space. The inconsistency between them makes the existing calculation of volumetric gain inappropriate for a complete exploration of the environment. To address this issue, we propose a concave-hull based volumetric gain in a sampling-based exploration framework. The concave hull is constructed based on the viewpoints generated by Rapidly-exploring Random Tree (RRT) and the nodes that fail to expand. All space outside this concave hull is considered unknown. The volumetric gain is calculated based on the viewpoints configuration rather than using the occupancy map. With the new volumetric gain, robots can avoid inefficient or even erroneous exploration behavior caused by the inappropriateness of existing volumetric gain calculation methods. Our exploration method is evaluated against the existing state-of-the-art RRT-based method in a benchmark environment. In the evaluated environment, the average running time of our method is about 38.4% of the existing state-of-the-art method and our method is more robust.

cs.RO↗

arXiv2022

Ada-Detector: Adaptive Frontier Detector for Rapid Exploration

In this paper, we propose an efficient frontier detector method based on adaptive Rapidly-exploring Random Tree (RRT) for autonomous robot exploration. Robots can achieve real-time incremental frontier detection when they are exploring unknown environments. First, our detector adaptively adjusts the sampling space of RRT by sensing the surrounding environment structure. The adaptive sampling space can greatly improve the successful sampling rate of RRT (the ratio of the number of samples successfully added to the RRT tree to the number of sampling attempts) according to the environment structure and control the expansion bias of the RRT. Second, by generating non-uniform distributed samples, our method also solves the over-sampling problem of RRT in the sliding windows, where uniform random sampling causes over-sampling in the overlap area between two adjacent sliding windows. In this way, our detector is more inclined to sample in the latest explored area, which improves the efficiency of frontier detection and achieves incremental detection. We validated our method in three simulated benchmark scenarios. The experimental comparison shows that we reduce the frontier detection runtime by about 40% compared with the SOTA method, DSV Planner.

cs.RO↗

arXiv2020

Frontier Detection and Reachability Analysis for Efficient 2D Graph-SLAM Based Active Exploration

We propose an integrated approach to active exploration by exploiting the Cartographer method as the base SLAM module for submap creation and performing efficient frontier detection in the geometrically co-aligned submaps induced by graph optimization. We also carry out analysis on the reachability of frontiers and their clusters to ensure that the detected frontier can be reached by robot. Our method is tested on a mobile robot in real indoor scene to demonstrate the effectiveness and efficiency of our approach.

cs.CV↗

arXiv2019

LiDAR Iris for Loop-Closure Detection

In this paper, a global descriptor for a LiDAR point cloud, called LiDAR Iris, is proposed for fast and accurate loop-closure detection. A binary signature image can be obtained for each point cloud after several LoG-Gabor filtering and thresholding operations on the LiDAR-Iris image representation. Given two point clouds, their similarities can be calculated as the Hamming distance of two corresponding binary signature images extracted from the two point clouds, respectively. Our LiDAR-Iris method can achieve a pose-invariant loop-closure detection at a descriptor level with the Fourier transform of the LiDAR-Iris representation if assuming a 3D (x,y,yaw) pose space, although our method can generally be applied to a 6D pose space by re-aligning point clouds with an additional IMU sensor. Experimental results on five road-scene sequences demonstrate its excellent performance in loop-closure detection.

cs.RO↗

arXiv2019

PuzzleFlex: kinematic motion of chains with loose joints

This paper presents a method of computing free motions of a planar assembly of rigid bodies connected by loose joints. Joints are modeled using local distance constraints, which are then linearized with respect to configuration space velocities, yielding a linear programming formulation that allows analysis of systems with thousands of rigid bodies. Potential applications include analysis of collections of modular robots, structural stability perturbation analysis, tolerance analysis for mechanical systems, and formation control of mobile robots.

cs.RO↗