Hasil untuk "Canals and inland navigation. Waterways"

Yue Hu, Avery Xi, Qixin Xiao et al.

This paper develops LongNav-R1, an end-to-end multi-turn reinforcement learning (RL) framework designed to optimize Visual-Language-Action (VLA) models for long-horizon navigation. Unlike existing single-turn paradigm, LongNav-R1 reformulates the navigation decision process as a continuous multi-turn conversation between the VLA policy and the embodied environment. This multi-turn RL framework offers two distinct advantages: i) it enables the agent to reason about the causal effects of historical interactions and sequential future outcomes; and ii) it allows the model to learn directly from online interactions, fostering diverse trajectory generation and avoiding the behavioral rigidity often imposed by human demonstrations. Furthermore, we introduce Horizon-Adaptive Policy Optimization. This mechanism explicitly accounts for varying horizon lengths during advantage estimation, facilitating accurate temporal credit assignment over extended sequences. Consequently, the agent develops diverse navigation behaviors and resists collapse during long-horizon tasks. Experiments on object navigation benchmarks validate the framework's efficacy: With 4,000 rollout trajectories, LongNav-R1 boosts the Qwen3-VL-2B success rate from 64.3% to 73.0%. These results demonstrate superior sample efficiency and significantly outperform state-of-the-art methods. The model's generalizability and robustness are further validated by its zero-shot performance in long-horizon real-world navigation settings. All source code will be open-sourced upon publication.

Jason H. Rife, Samer Khanafseh, Boris Pervan et al.

As a step toward founding the new field of lidar integrity, this paper compiles a list of lidar faults, threats, anomalies, and challenges – which we collectively label adversities. Engineers will eventually need to characterize and mitigate these adversities for rigorous quantification of lidar integrity. Lidar adversities manifest at the intersection of environment, hardware, and algorithms. By extension, the specific design approach or architecture of a lidar system, as well as its application, must be specified to define a complete set of adversities and resulting measurement-error distributions, including operationally hazardous errors. To this end, we focus on the application of absolute positioning for high-integrity roadway operations and identify three promising lidar architectures for that application. In comparing and contrasting these architectures, we review the broader literature to identify associated lidar adversities, and we provide a perspective on how those adversities might be mitigated in the future.

Seunghwan Kim, Nicolas Gault, Yongrae Jo et al.

Modern global navigation satellite system L5/E5a code families offer improved correlation properties, with lower auto-correlation sidelobes and cross-correlations, compared with legacy Global Positioning System L1 coarse/acquisition (C/A) codes. However, these codes encounter unique L5/E5a interference environments, particularly those including interference due to pulses from distance-measuring equipment and tactical air navigation systems. In civil aviation, temporal blanking is the assumed countermeasure. In temporal blanking, incoming samples are set to zero when the peak envelope power exceeds a threshold, blanking the codes within the sampled signals and affecting their correlation with non-blanked replicas. Through extensive simulations, this study analyzes L5/E5a code properties under blanking duty cycle (bdc) values of 0%–75% over a 1-ms integration time. Results indicate reduced auto-correlation and cross-correlation protections, although these effects remain superior to those of L1 C/A codes until bdc reaches approximately 60%. Further increases in bdc to 75%, likely due to increasing air traffic, diminish these advantages. Additionally, simulations show that Doppler residuals have a minimal impact on L5/E5a correlation properties.

Hengwei Zhang, Yiping Jiang, Zhipeng Wang

In the BDS-3 constellation, only the B3I signal is used to compute the broadcast clock offset. However, because advanced receiver autonomous integrity monitoring (ARAIM) uses dual-frequency measurements, the time group delay (TGD) must be considered in BDS-3-based ARAIM applications. The existing BDS-3 error model is therefore not sufficient to describe the actual TGD error encountered by aviation users. Specifically, the estimated signal-in-space error underestimates the actual error, which cannot be bounded by the estimated user range accuracy and nominal bias. This inaccuracy results in a loss of integrity. To avoid this risk, this paper develops a separated Gaussian model to bound the TGD error for BDS-3 in ARAIM. Using a one-year data set, this paper characterizes and bounds the TGD error for different signal combinations. Of the tested combinations, the B1C/B2a signal combination resulted in the smallest standard deviation of 0.78 m and a corresponding bias component of 0.71 m. We suggest that this signal combination be adopted for use in ARAIM.

Vijay Singh Bhadouria, Dhaval J. Upadhyay, Parimal J. Majithiya et al.

Satellite navigation payloads use a constant-envelope composite signal to efficiently operate their high-power amplifiers in the saturation region. This composite signal consists of multiple signals that are multiplexed at the baseband level to support various services. The complexity of the signal multiplexing technique increases with multi-level signals. Here, we propose designing new service signals for Navigation with Indian Constellation (NavIC) in the L1 frequency band. The NavIC L1-band open civilian service signal is a multi-level design. We propose multiplexing new service signals to this multi-level signal at a single frequency and multiple frequencies without interfering with existing navigation service signals while maintaining backward compatibility. We present a novel concept for preserving the power spectral density criteria in the optimization framework to meet interoperability requirements and present an optimal power-sharing and modulation scheme. Results show that the single-frequency and multi-frequency methods for multiplexing new service signals both achieve maximum multiplexing efficiency.

Jyh-Ching Juang, Yung-Fu Tsai

Although the issue of global navigation satellite system (GNSS) interference has been addressed in the community of satellite navigation, the extent of GNSS interference in the past couple of years has raised serious concerns for air and marine transportation. This paper assesses GNSS interference based on observations of the TRITON GNSS reflectometry (GNSS-R) payload. The TRITON GNSS-R payload contains a navigation unit and a science unit that are designed to receive direct line-of-sight and scattered GNSS signals, respectively. In the presence of radio-frequency interference, these two units experience different phenomena, including navigation disruptions, spoofed localization, and degradation of GNSS-R performance. This paper describes the effects of interference, analyzes the observation data, and elucidates the interference characteristics. Analyses of GNSS interference based on space data are believed to be instrumental for providing information concerning the frequency, location, and severity of interference and for developing interference-resistant techniques.

A. Sesta, D. Durante, G. Boscagli et al.

The ATLAS consortium has proposed a novel architecture to implement a lunar radio navigation system capable of providing position, navigation, and timing services to several lunar users. The system consists of a small constellation of four satellites in elliptical lunar frozen orbits, with the aposelene above the southern hemisphere. The architecture envisages a ground station network of small dish antennas to establish tracking via multiple spacecraft per aperture at the K-band using a scheme based on code division multiple access. Such a configuration implements the same-beam interferometry technique with spread-spectrum ranging and Doppler measurements. We describe the orbit determination and time synchronization of the satellite constellation, validating the concept in multiple scenarios and establishing the system performance. Numerical simulations show an orbital accuracy ranging from a few centimeters to 10 m, while the signal-in-space error degrades, reaching up to 20 m after 10 h (95th percentile) or 6 h (99th percentile).

Teresa White, Jesse Wheeler, Colton Lindstrom et al.

Unmanned aerial vehicles often rely on the Global Positioning System (GPS) for navigation. GPS signals, however, are very low in power and can be easily jammed or otherwise disrupted. This paper presents a method for estimating the navigation errors present at the beginning of a GPS-denied period using data from a synthetic aperture radar (SAR) system. These errors are estimated by comparing an online-generated SAR image with a reference image obtained a priori. The distortions relative to the reference image are exploited by a convolutional neural network to learn the initial navigation errors, which can be used to recover the true flight trajectory throughout the synthetic aperture. The proposed neural network approach is able to learn to predict the initial errors on both simulated and real SAR image data.

Maria Caamano, Jose Miguel Juan, Jaume Sanz et al.

This paper addresses the potential threats posed by large ionospheric gradients acting between ground-based augmentation system (GBAS) reference stations and aircraft during approach. Current GBAS stations rely on conservative threat models to mitigate ionospheric gradient threats, limiting system availability and continuity. To solve these issues, previous research has introduced a methodology for real-time detection and estimation of ionospheric gradients using a network of dual-frequency, multi-constellation global navigation satellite system monitoring stations. This paper proposes to expand this approach by including the derivation of an uncertainty model for the estimated gradient slope, allowing the threat model to be substituted with the near real-time estimated and overbounded gradient slope in current GBAS algorithms. Evaluations with simulated and real anomalous gradients produced by equatorial plasma bubbles demonstrate the efficacy of this methodology, indicating its potential to enhance GBASs by dynamically detecting, estimating, and overbounding the estimated anomalous gradients instead of relying solely on worst-case models, thus improving system availability and continuity.

Geoffery Agorku, Sarah Hernandez, Hayley Hames et al.

Accurate, real-time estimation of barge quantity on inland waterways remains a critical challenge due to the non-self-propelled nature of barges and the limitations of existing monitoring systems. This study introduces a novel method to use Automatic Identification System (AIS) vessel tracking data to predict the number of barges in tow using Machine Learning (ML). To train and test the model, barge instances were manually annotated from satellite scenes across the Lower Mississippi River. Labeled images were matched to AIS vessel tracks using a spatiotemporal matching procedure. A comprehensive set of 30 AIS-derived features capturing vessel geometry, dynamic movement, and trajectory patterns were created and evaluated using Recursive Feature Elimination (RFE) to identify the most predictive variables. Six regression models, including ensemble, kernel-based, and generalized linear approaches, were trained and evaluated. The Poisson Regressor model yielded the best performance, achieving a Mean Absolute Error (MAE) of 1.92 barges using 12 of the 30 features. The feature importance analysis revealed that metrics capturing vessel maneuverability such as course entropy, speed variability and trip length were most predictive of barge count. The proposed approach provides a scalable, readily implementable method for enhancing Maritime Domain Awareness (MDA), with strong potential applications in lock scheduling, port management, and freight planning. Future work will expand the proof of concept presented here to explore model transferability to other inland rivers with differing operational and environmental conditions.

Keidai Iiyama, Grace Gao

The establishment of a sustainable human presence on the Moon demands robust positioning, navigation, and timing (PNT) services capable of supporting both surface and orbital operations. This paper presents a comprehensive trade-off analysis of lunar frozen-orbit constellations for the Lunar Augmented Navigation Service (LANS), focusing on how the number of satellites and orbital parameters influence coverage, position dilution of precision (PDOP), orbit determination accuracy, receiver noise, and orbit insertion cost. Three Walker-constellation families based on frozen elliptical and circular orbits are examined to characterize their relative advantages across different semi-major axes and inclinations. Results show that larger semi-major axes enhance both polar and global coverage, though the optimal inclination depends on the constellation type and target service region. The south elliptical lunar frozen orbit (ELFO) Walker constellation provides superior performance for polar coverage and PDOP, whereas the circular lunar frozen orbit (CLFO) Walker configuration achieves the best global uniformity. Orbit determination errors and receiver noise both increase with larger semi-major axes and higher inclinations, reflecting weaker geometric observability and reduced received signal power at apolune for eccentric orbits. Orbit insertion analysis reveals clear trade-offs among transfer duration, characteristic energy ($C_3$) at trans-lunar injection, and insertion $ΔV$: shorter transfers require higher insertion $ΔV$, while low-energy transfers achieve smaller $ΔV$ at the cost of months-long durations and higher $C_3$. These findings provide a systematic framework for designing LANS constellations for both regional and global coverage.

Hemanth Kannamarlapudi, Sowmya Chintalapudi

Navigation is a very crucial aspect of autonomous vehicle ecosystem which heavily relies on collecting and processing large amounts of data in various states and taking a confident and safe decision to define the next vehicle maneuver. In this paper, we propose a novel architecture based on Quantum Artificial Intelligence by enabling quantum and AI at various levels of navigation decision making and communication process in Autonomous vehicles : Quantum Neural Networks for multimodal sensor fusion, Nav-Q for Quantum reinforcement learning for navigation policy optimization and finally post-quantum cryptographic protocols for secure communication. Quantum neural networks uses quantum amplitude encoding to fuse data from various sensors like LiDAR, radar, camera, GPS and weather etc., This approach gives a unified quantum state representation between heterogeneous sensor modalities. Nav-Q module processes the fused quantum states through variational quantum circuits to learn optimal navigation policies under swift dynamic and complex conditions. Finally, post quantum cryptographic protocols are used to secure communication channels for both within vehicle communication and V2X (Vehicle to Everything) communications and thus secures the autonomous vehicle communication from both classical and quantum security threats. Thus, the proposed framework addresses fundamental challenges in autonomous vehicles navigation by providing quantum performance and future proof security. Index Terms Quantum Computing, Autonomous Vehicles, Sensor Fusion

Brent Renfro, Jason Drotar, Austin Finn et al.

The concept of the signal-in-space (SIS) root-mean-square (RMS) user range error (URE) is used to evaluate the performance of multiple global navigation satellite systems (GNSSs); however, a complete analytical derivation has not been published. This article describes the instantaneous SIS URE and the instantaneous SIS RMS URE, explains the role of the instantaneous SIS RMS URE in evaluating the statistical accuracy of GNSS signals, and provides an analytical derivation of the instantaneous SIS RMS URE. This derivation is then compared to the equations found in various papers and performance standards to illustrate how the equations, although appearing different, actually measure the same quantity with differing constraints.

Dhaval J. Upadhyay, Vijay S. Bhadouria, Parimal J. Majithiya et al.

This paper presents a constant-envelope modulation scheme, based on a synthesized binary offset carrier (SBOC), for a global navigation satellite system (GNSS) that combines three signals in a nonlinear fashion with unequal amplitudes. The proposed SBOC modulation meets the power spectral density criteria of multiplexed binary offset carrier (MBOC) modulation used in the L1 frequency band (1575.42 MHz) open civilian service interoperable signals for GNSS. This SBOC modulation also allows for the selection of an arbitrary power-sharing ratio between the data and pilot signals. This approach provides better performance than various MBOC(6, 1, 1/11) modulations for narrowband receivers.

Rezy Pradipta, Charles S. Carrano, Keith M. Groves et al.

We argue the merits of having a simplified method to simulate equatorial plasma bubble (EPB) plume structures for practical usage. The capability to realistically model EPB plume structures in simulations would be advantageous when assessing the severity of ionospheric threats. Such advantages would arise because a realistic model of EPB plume structures could allow nonstationary scintillation signals to be simulated. Although EPB plume structures can be modeled via first-principle physics-based models, these models tend to be computationally demanding. High-performance computing facilities might be able to offer some remedy, but serious handicaps would remain for those without access to such advanced facilities. We investigated multiple options that utilize the diffusion-limited aggregation (DLA) fractal process to generate bifurcating structures that resemble typical EPB plume structures. We combined the DLA algorithm with the International Reference Ionosphere model to simulate EPBs in three dimensions. Initial tests of this modeling approach indicate promising results.

Jianhao Tang, Zhenni Li, Kexian Hou et al.

High-precision global navigation satellite system (GNSS) positioning for automatic driving in urban environments remains an unsolved problem because of the impact of multipath interference and non-line-of-sight reception. Recently, methods based on data-driven deep reinforcement learning (DRL), which are adaptable to nonstationary urban environments, have been used to learn positioning-correction policies without strict assumptions about model parameters. However, the performance of DRL relies heavily on the amount of training data, and high-quality, available GNSS data collected in urban environments are insufficient because of issues such as signal attenuation and large stochastic noise, resulting in poor performance and low training efficiency for DRL. In this paper, we propose a DRL-based positioning correction method with an adaptive reward augmentation method (ARAM) to improve the GNSS positioning accuracy in nonstationary urban environments. To address the problem of insufficient training data in the target domain environment, we leverage sufficient data collected in source domain environments to compensate for insufficient training data, where the source domain environments can be in different locations than the target environment. We then employ ARAM to achieve domain adaptation that adaptively modifies data matching between the source domain and target domain by a simple modification to the reward function, thus improving the performance and training efficiency of DRL. Hence, our novel DRL model can achieve an adaptive dynamic-positioning correction policy for nonstationary urban environments. Moreover, the proposed positioning-correction algorithm can be flexibly combined with different model-based positioning approaches. The proposed method was evaluated using the Google smartphone decimeter challenge data set and the Guangzhou GNSS measurement data set, with results demonstrating that our method can obtain an improvement of approximately 10% in positioning performance over existing model-based methods and 8% over learning-based approaches.

R. Herrmann, S. Bose, I. Filip et al.

Advancing towards high automation and autonomous operations is crucial for the future of inland waterway transport (IWT) systems. These systems necessitate robust and precise onboard sensory technologies that can perceive the environment under all weather conditions, including static features for local positioning techniques such as Simultaneous Localization and Mapping (SLAM). Traditional marine RADAR, mandatory on vessels and operating in the 9300-9500 MHz frequency band, can cover ranges from 15 to 1200 meters but are inadequate for detecting closer objects, making them unsuitable for automated docking maneuvers, lock entry, or bridge undercrossings. This necessitates the development of reliable close-range sensor technology that functions effectively in all weather conditions. In present research works on vessel automation, LiDAR sensors, operating in the nearinfrared range, are used predominantly to detect the immediate surroundings of vessels but suffer significant degradation in poor visibility. Conversely, automotive RADAR sensors, utilizing the 76-81 GHz frequency band, can detect objects from a few centimeters to up to 200 meters, even in adverse conditions. These sensors are commonly used in advanced autonomous road traffic systems and are evaluated in this study for their suitability in inland navigation and maneuvering. This paper discusses a distributed sensor network of four compact automotive frequencymodulated continuous-wave (FMCW) radars mounted on a cabin boat as a test platform. Initial field experiments demonstrate the RADAR network's ability to perceive closerange static environmental features around the boat in inland waters. The paper also provides a comparative analysis of the environmental detection capabilities of automotive RADAR and LiDAR sensors.

Kathrin Donandt, Karim Böttger, Dirk Söffker

Physics-related and model-based vessel trajectory prediction is highly accurate but requires specific knowledge of the vessel under consideration which is not always practical. Machine learning-based trajectory prediction models do not require expert knowledge, but rely on the implicit knowledge extracted from massive amounts of data. Several deep learning (DL) methods for vessel trajectory prediction have recently been suggested. The DL models developed typically only process information about the (dis)location of vessels defined with respect to a global reference system. In the context of inland navigation, this can be problematic, since without knowledge of the limited navigable space, irrealistic trajectories are likely to be determined. If spatial constraintes are introduced, e.g., by implementing an additional submodule to process map data, however, overall complexity increases. Instead of processing the vessel displacement information on the one hand and the spatial information on the other hand, the paper proposes the merging of both information. Here, fairway-related and navigation-related displacement information are used directly. In this way, the previously proposed context-sensitive Classification Transformer (CSCT) shows an improved spatial awareness. Additionally, the CSCT is adapted to assess the model uncertainty by enabling dropout during inference. This approach is trained on different inland waterways to analyze its generalizability. As the improved CSCT obtains lower prediction errors and enables to estimate the trustworthiness of each prediction, it is more suitable for safety-critical applications in inland navigation than previously developed models.

Matthew Pierson, Zia Mehrabi

Waterways shape earth system processes and human societies, and a better understanding of their distribution can assist in a range of applications from earth system modeling to human development and disaster response. Most efforts to date to map the world's waterways have required extensive modeling and contextual expert input, and are costly to repeat. Many gaps remain, particularly in geographies with lower economic development. Here we present a computer vision model that can draw waterways based on 10m Sentinel-2 satellite imagery and the 30m GLO-30 Copernicus digital elevation model, trained using high fidelity waterways data from the United States. We couple this model with a vectorization process to map waterways worldwide. For widespread utility and downstream modelling efforts, we scaffold this new data on the backbone of existing mapped basins and waterways from another dataset, TDX-Hydro. In total, we add 124 million kilometers of waterways to the 54 million kilometers already in the TDX-Hydro dataset, more than tripling the extent of waterways mapped globally.

Daniele Borio, Ciro Gioia

Global navigation satellite systems (GNSSs) provide several signals on different frequencies: Two or more components can be processed jointly as a meta-signal. Despite significant effort devoted to developing effective techniques for meta-signal processing, limited research has been conducted to characterize meta-signal measurements. In this work, the observations obtained by processing a GNSS meta-signal are characterized and fundamental relationships between GNSS meta-signal and dual-frequency measurement combinations are derived. We show that subcarrier phase observations can be estimated as the wide-lane linear combination of the carrier phases obtained from the two original sideband components. Moreover, meta-signal code measurements can be reconstructed from the pseudoranges and carrier phases of the original components. Thus, meta-signal pseudoranges are mixed code and carrier observations. The experimental results confirm the validity of the theoretical formulas that can be used to reconstruct meta-signal measurements from dual-frequency observations.