arXiv subjects

Jane Shin

Publications and source records attributed to Jane Shin.

12 recordsLinked to original sources

arXiv2026

Akule: Fast and Scalable Multi-Robot Motion Planning via Sparse Interaction Diffusion

Diffusion models provide expressive trajectory priors for multi-robot motion planning (MRMP), but scaling them to large teams requires coordinating individual motions without expensive joint computation. We introduce Akule, a sparse interaction diffusion framework that augments a frozen single-robot prior with three learned modules: a reusable pairwise correction model $R_ϕ$, a contextual selector $U_ψ$ that determines which corrections to evaluate, and a composer $G_ω$ that combines their effects through context-dependent signed weights. This decomposition separates which interactions merit computation from how their effects should be combined into coordinated denoising updates. We train $R_ϕ$ using matched pairwise trajectory optimizations, then learn $G_ω$ and $U_ψ$ from physically optimized joint trajectories without requiring a prescribed ground-truth interaction graph. The resulting joint proposals are passed to a downstream search-based planner for validation and repair. Across diverse MRMP benchmarks, Akule achieves competitive planning success, complete-planner speedups of up to $25\times$, zero-shot population transfer, and successful planning with up to $256$ robots. Ablations further demonstrate that learned selection and composition reduce pre-repair conflicts and downstream repair effort relative to heuristic selection and uniform summation.

cs.RO↗

arXiv2026

SURGE: Sonar-fUsed Reconstruction and localization via image-gated Graph Estimation

Remotely operated vehicles (ROVs) are widely used to explore and inspect underwater environments such as caves, shipwrecks, and submerged infrastructure. These missions require accurate 3D understanding of the surrounding environment, which depends on both reliable vehicle localization and metric scene reconstruction. However, external positioning is often unavailable underwater, requiring small ROVs to rely primarily on onboard perception. Optic vision provides rich visual and geometric information but suffers from scale ambi- guity and trajectory drift, whereas 2D imaging sonar provides metric range but incomplete 3D geometry. Existing underwater reconstruction approaches typically address these limitations separately or assume known sensor poses, leaving localization and reconstruction disconnected. We present SURGE, a camera sonar framework that jointly estimates the ROV trajectory and target location by integrating visual and acoustic observations within a factor graph, then uses the recovered metric poses for sonar Gaussian splatting. Experiments on real underwater RGB sonar observations show that SURGE substantially improves localization consistency over conventional vision based pose estimation and produces a more compact, natively metric reconstruction than RGB Gaussian splatting baselines.

cs.RO↗

arXiv2026

SonarVoxNet: Diver Detection in 3D Bounding Box using 3D Sonar

Autonomous underwater vehicles (AUVs) assisting human divers must continuously track not only the diver's 3D position but also their full-body orientation. However, vision-based perception is unreliable underwater, and forward-looking sonar -- despite being widely used -- discards the elevation information needed for orientation estimation, posing a fundamental limitation. Recently commercialized 3D sonar preserves elevation but produces sparse, noisy returns, and existing detectors are built for dense LiDAR data and for targets that remain upright and rotate only about the yaw axis (e.g., vehicles, pedestrians), making them unable to represent a freely pitching and rolling diver. To address this gap, we present two contributions. First, SonarVoxNet adapts a voxel-based encoder and an anchor-free center-based detection head to 3D sonar data, replacing the conventional yaw-only rotation representation with a continuous 6D rotation parameterization to predict full 9-DoF oriented bounding boxes -- to our knowledge, the first 3D sonar diver detector to do so. Second, Diver3D is the first public 3D sonar dataset with full 3D orientation labels for divers in diverse, non-upright poses, collected at a natural cave-diving site. Through controlled ablations over the backbone and detection head, we show that the dominant factor behind accurate 3D sonar-based diver detection is the transition from yaw-only rotation to full-SO(3) rotation. This transition substantially improves detection accuracy and reduces orientation error. These results demonstrate that full-body diver orientation is recoverable from 3D sonar alone, laying the groundwork for future work on diver pose estimation and diver-robot interaction.

cs.RO↗

arXiv2026

Calibration and Comparative Analysis of Forward-Looking Sonar and 3D Sonar for Enhanced Underwater Object Recognition

Sonars generate a significant amount of noise. With the advent of new technology capable of producing full 3D point clouds, the noise is amplified in sparse point clouds, making it challenging to recognize features for navigation, recognition, or reconstruction. To address this challenge, we propose using two different sonar modalities: one that produces a 2D intensity image and another that generates a 3D point cloud. By implementing auto-calibration, we can filter out noisy features between the modalities to enhance feature extraction. Experiments demonstrate that auto-calibration improves performance over manual calibration by 5% and that filtering enhances feature extraction by more than 40% relative to the raw point cloud. Code and datasets are given at https://theaprilab.org/fls-3d-calibrator

cs.CV↗

arXiv2026

uScenes: A Multimodal RGB and 3D Sonar Dataset for Underwater Robot Perception

Robust perception is essential for the deployment of autonomous underwater robots. However, optical cameras become unreliable under poor illumination and backscatter. Forward looking (2D) acoustic sensors remain effective under these conditions, but they measure range and bearing while leaving elevation unresolved, creating an ambiguity that prevents individual sonar returns from being localized in three dimensional (3D) space. This complicates the sensor use for 3D scene understanding and precise object detection. We introduce \textbf{uScenes}, a multimodal underwater dataset containing synchronized 3D multibeam sonar point clouds and RGB imagery. The dataset contains 110 scenes and 95,834 synchronized observation, representing 277.6 minutes of data collected across multiple field sessions. uScenes establishes a foundation for underwater sensor fusion, cross modal representation learning and 3D scene understanding. Code and datasets are given at https://github.com/era-research-lab/uScenes.

cs.CV↗

arXiv2026

A Hybrid Model-Based and Model-Free Framework for Active Multi-View Viewpoint Optimization in Sonar Target Recognition

This paper presents a hybrid model-based and model-free framework for active multi-view target recognition using forward-looking sonar. A convolutional neural network (CNN) provides data-driven observation likelihoods, while Radon-based orientation estimation enables viewpoint-aware sensing without requiring angle annotations. During training, an information-gain-based reward guides a Proximal Policy Optimization (PPO) agent to learn a belief-aware viewpoint selection policy offline. At deployment, the learned policy performs real-time viewpoint selection using only CNN-based belief updates, eliminating the need for computationally expensive online POMDP tree search. Experiments on a marine-debris forward-looking sonar dataset demonstrate that the proposed approach achieves competitive recognition accuracy while reducing sensing steps and motion cost compared to model-based baselines.

cs.RO↗

arXiv2025

Belief-Conditioned One-Step Diffusion: Real-Time Trajectory Planning with Just-Enough Sensing

Robots equipped with rich sensor suites can localize reliably in partially-observable environments, but powering every sensor continuously is wasteful and often infeasible. Belief-space planners address this by propagating pose-belief covariance through analytic models and switching sensors heuristically--a brittle, runtime-expensive approach. Data-driven approaches--including diffusion models--learn multi-modal trajectories from demonstrations, but presuppose an accurate, always-on state estimate. We address the largely open problem: for a given task in a mapped environment, which \textit{minimal sensor subset} must be active at each location to maintain state uncertainty \textit{just low enough} to complete the task? Our key insight is that when a diffusion planner is explicitly conditioned on a pose-belief raster and a sensor mask, the spread of its denoising trajectories yields a calibrated, differentiable proxy for the expected localisation error. Building on this insight, we present Belief-Conditioned One-Step Diffusion (B-COD), the first planner that, in a 10 ms forward pass, returns a short-horizon trajectory, per-waypoint aleatoric variances, and a proxy for localisation error--eliminating external covariance rollouts. We show that this single proxy suffices for a soft-actor-critic to choose sensors online, optimising energy while bounding pose-covariance growth. We deploy B-COD in real-time marine trials on an unmanned surface vehicle and show that it reduces sensing energy consumption while matching the goal-reach performance of an always-on baseline.

cs.RO↗

arXiv2025

Uncertainty-Aware Guidance for Target Tracking subject to Intermittent Measurements using Motion Model Learning

This paper presents a novel guidance law for target tracking applications where the target motion model is unknown and sensor measurements are intermittent due to unknown environmental conditions and low measurement update rate. In this work, the target motion model is represented by a transformer neural network and trained by previous target position measurements. This transformer motion model serves as the prediction step in a particle filter for target state estimation and uncertainty quantification. The particle filter estimation uncertainty is utilized in the information-driven guidance law to compute a path for the mobile agent to travel to a position with maximum expected entropy reduction (EER). The computation of EER is performed in real-time by approximating the information gain from the predicted particle distributions relative to the current distribution. Simulation and hardware experiments are performed with a quadcopter agent and TurtleBot target to demonstrate that the presented guidance law outperforms two other baseline guidance methods.

eess.SY↗

arXiv2025

Point Cloud Structural Similarity-based Underwater Sonar Loop Detection

In this letter, we propose a point cloud structural similarity-based loop detection method for underwater Simultaneous Localization and Mapping using sonar sensors. Existing sonar-based loop detection approaches often rely on 2D projection and keypoint extraction, which can lead to data loss and poor performance in feature-scarce environments. Additionally, methods based on neural networks or Bag-of-Words require extensive preprocessing, such as model training or vocabulary creation, reducing adaptability to new environments. To address these challenges, our method directly utilizes 3D sonar point clouds without projection and computes point-wise structural feature maps based on geometry, normals, and curvature. By leveraging rotation-invariant similarity comparisons, the proposed approach eliminates the need for keypoint detection and ensures robust loop detection across diverse underwater terrains. We validate our method using two real-world datasets: the Antarctica dataset obtained from deep underwater and the Seaward dataset collected from rivers and lakes. Experimental results show that our method achieves the highest loop detection performance compared to existing keypointbased and learning-based approaches while requiring no additional training or preprocessing. Our code is available at https://github.com/donghwijung/point_cloud_structural_similarity_based_underwater_sonar_loop_detection.

cs.RO↗

arXiv2024

Global Uncertainty-Aware Planning for Magnetic Anomaly-Based Navigation

Navigating and localizing in partially observable, stochastic environments with magnetic anomalies presents significant challenges, especially when balancing the accuracy of state estimation and the stability of localization. Traditional approaches often struggle to maintain performance due to limited localization updates and dynamic conditions. This paper introduces a multi-objective global path planner for magnetic anomaly navigation (MagNav), which leverages entropy maps to assess spatial frequency variations in magnetic fields and identify high-information areas. The system generates paths toward these regions by employing a potential field planner, enhancing active localization. Hardware experiments demonstrate that the proposed method significantly improves localization stability and accuracy compared to existing active localization techniques. The results underscore the effectiveness of this method in reducing localization uncertainty and highlight its adaptability to various gradient-based navigation maps, including topographical and underwater depth-based environments.

cs.RO↗

arXiv2024

Real-time Uncertainty-Aware Motion Planning for Magnetic-based Navigation

Localization in GPS-denied environments is critical for autonomous systems, and traditional methods like SLAM have limitations in generalizability across diverse environments. Magnetic-based navigation (MagNav) offers a robust solution by leveraging the ubiquity and unique anomalies of external magnetic fields. This paper proposes a real-time uncertainty-aware motion planning algorithm for MagNav, using onboard magnetometers and information-driven methodologies to adjust trajectories based on real-time localization confidence. This approach balances the trade-off between finding the shortest or most energy-efficient routes and reducing localization uncertainty, enhancing navigational accuracy and reliability. The novel algorithm integrates an uncertainty-driven framework with magnetic-based localization, creating a real-time adaptive system capable of minimizing localization errors in complex environments. Extensive simulations and real-world experiments validate the method, demonstrating significant reductions in localization uncertainty and the feasibility of real-time implementation. The paper also details the mathematical modeling of uncertainty, the algorithmic foundation of the planning approach, and the practical implications of using magnetic fields for localization. Future work includes incorporating a global path planner to address the local nature of the current guidance law, further enhancing the method's suitability for long-duration operations.

cs.RO↗

arXiv2024

Modularis: Modular Underwater Robot for Rapid Development and Validation of Autonomous Systems

Autonomous underwater robots typically require higher cost and time for demonstrations compared to other domains due to the complexity of the environment. Due to the limited capacity and payload flexibility, it is challenging to find off-the-shelf underwater robots that are affordable, customizable, and subject to environmental variability. Custom-built underwater robots may be necessary for specialized applications or missions, but the process can be more costly and time-consuming than purchasing an off-the-shelf autonomous underwater vehicle (AUV). To address these challenges, we propose a modular underwater robot, Modularis, that can serve as an open-source testbed system. Our proposed system expedites the testing of perception, planning, and control algorithms.

cs.RO↗