An official website of the United States government
Enabling autonomous robots to safely and efficiently navigate, explore, and map underwater caves is of significant importance to water resource management, hydrogeology, archaeology, and marine robotics. In this work, we demonstrate the system design and algorithmic integration of a visual servoing framework for semantically guided autonomous underwater cave exploration. We present the hardware and edge-AI design considerations to deploy this framework on a novel AUV (Autonomous Underwater Vehicle) named CavePI. The guided navigation is driven by a computationally light yet robust deep visual perception module, delivering a rich semantic understanding of the environment. Subsequently, a robust control mechanism enables CavePI to track the semantic guides and navigate within complex cave structures. We evaluate the system through field experiments in natural underwater caves and spring-water sites and further validate its ROS (Robot Operating System)-based digital twin in a simulation environment. Our results highlight how these integrated design choices facilitate reliable navigation under feature-deprived, GPS-denied, and low-visibility conditions.
more »
« less
This content will become publicly available on July 20, 2027
Hyperspectral semantic mapping and A-PNT integration for autonomous navigation in GPS-denied environments
Autonomous systems encounter navigation challenges in GPS-denied environment, where GPS signals are unavailable or degraded due to obstruction, jamming, or spoofing. This paper presents a navigation framework that combines hyperspectral semantic data with an A-PNT uncertainty model to support navigation when GPS is unavailable. Principal Component Analysis (PCA) is first applied to reduce the dimensionality of the hyperspectral imagery while preserving important spectral information. The reduced data are then classified into terrain types, including roads, vegetation, water, and buildings, thereby creating a semantic map. Road extraction and skeletonization are used to identify preferred travel paths. A terrain-aware cost map is generated and updated according to the uncertainty of the A-PNT position estimate. An A* algorithm computes the route, while a replanning module adjusts the route when off-road segments are detected. A Kalman filter is applied to smooth the trajectory and improve navigation stability. The combination of 5 principal components and 6 clusters provided the best balance between classification quality and navigation performance, achieving 99% variance retention, full street coverage, and a planning time of 1.4 s. The proposed framework provides a practical solution for autonomous systems operating in GPS-denied environment.
more »
« less
- Award ID(s):
- 1920182
- PAR ID:
- 10711589
- Publisher / Repository:
- American Council on Science & Education
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Positioning, navigation, and timing (PNT) information is critical for a range of critical civil, industrial, and defense applications. PNT relies predominantly on global navigation satellite systems (GNSSs), but GNSS signals are becoming increasingly vulnerable to natural and man-made disruptions, which motivated the development of alternative PNT technologies that can complement or substitute GNSS in denied environments. These approaches fall into three categories: opportunistic, infrastructure-based, and environment-based PNT. While numerous studies have examined individual techniques, the literature remains fragmented and lacks a comprehensive review. This paper reviews and synthesizes recent advances across all three categories, highlighting application scenarios, achieved accuracy, and limitations. Opportunistic PNT, i. e., using signals of opportunity, has evolved rapidly over the past decade with the introduction of 5G cellular systems and the large-scale deployment of low Earth orbit constellations, although their accuracy remains at the meter level. Infrastructure-based methods can achieve meter- to subcentimeter-level accuracy, but with trade-offs between accuracy, coverage, and reliability. Environment-based PNT requires no external infrastructure and continues to advance through improvements in visual and lidar simultaneous localization and mapping (SLAM) algorithms, while radar-SLAM offers a more robust alternative in environments where visual- or lidar-based systems may struggle. Despite all these alternatives, GNSS remains unmatched due to decades of infrastructure investment and operational evolution. Future resilient PNT in GNSS-denied environments will rely on adaptive multi-sensor integration, combining ambient signals, dedicated infrastructure, and SLAM to meet application-specific needs.more » « less
-
Modern systems and devices, including unmanned aerial systems (UAS), autonomous vehicles, and other unmanned and autonomous systems, commonly rely on the Global Positioning System (GPS) for positioning, navigation, and timing (PNT). Cellular mobile devices rely on GPS for PNT and location-based services. Many of these systems cannot function correctly without GPS; however, GPS signals are susceptible to a wide variety of signal-related disruptions and cyberattacks. GPS threat detection and mitigation have received significant attention recently. There are many surveys and systematic reviews in the literature related to GPS security; however, many existing reviews only briefly discuss GPS security within a larger discussion of cybersecurity. Other reviews focus on niche topics related to GPS security. There are no existing comprehensive reviews of GPS security issues in the literature. This paper fills that gap by providing a comprehensive treatment of GPS security, with an emphasis on UAS applications. This paper provides an overview of the threats to GPS and the state-of-the-art techniques for attack detection and countermeasures. Detection and mitigation approaches are categorized, and the strengths and weaknesses of existing approaches are identified. This paper also provides a comprehensive overview of the state-of-the-art on alternative positioning and navigation techniques in GPS-disrupted environments, discussing the strengths and weaknesses of existing approaches. Finally, this paper identifies gaps in existing research and future research directions.more » « less
-
Accurate and up-to-date digital road maps are the foundation of many mobile applications, such as navigation and autonomous driving. A manually-created map suffers from the high cost for creation and maintenance due to constant road network updating. Recently, the ubiquity of GPS devices in vehicular systems has led to an unprecedented amount of vehicle sensing data for map inference. Unfortunately, accurate map inference based on vehicle GPS is challenging for two reasons. First, it is challenging to infer complete road structures due to the sensing deviation, sparse coverage, and low sampling rate of GPS of a fleet of vehicles with similar mobility patterns, e.g., taxis. Second, a road map requires various road properties such as road categories, which is challenging to be inferred by just GPS locations of vehicles. In this paper, we design a map inference system called coMap by considering multiple fleets of vehicles with Complementary Mobility Features. coMap has two key components: a graph-based map sketching component, a learning-based map painting component. We implement coMap with the data from four type-aware vehicular sensing systems in one city, which consists of 18 thousand taxis, 10 thousand private vehicles, 6 thousand trucks, and 14 thousand buses. We conduct a comprehensive evaluation of coMap with two state-of-the-art baselines along with ground truth based on OpenStreetMap and a commercial map provider, i.e., Baidu Maps. The results show that (i) for the map sketching, our work improves the performance by 15.9%; (ii) for the map painting, our work achieves 74.58% of average accuracy on road category classification.more » « less
-
Unlike many current navigation approaches for micro air vehicles, the relative navigation (RN) framework presented in this paper ensures that the filter state remains observable in GPS-denied environments by working with respect to a local reference frame. By subtly restructuring the problem, RN ensures that the filter uncertainty remains bounded, consistent, and normally-distributed, and insulates flight-critical estimation and control processes from large global updates. This paper thoroughly outlines the RN framework and demonstrates its practicality with several long flight tests in unknown GPS-denied and GPS-degraded environments. The relative front end is shown to produce low-drift estimates and smooth, stable control while leveraging off-the-shelf algorithms. The system runs in real time with onboard processing, fuses a variety of vision sensors, and works indoors and outdoors without requiring special tuning for particular sensors or environments. RN is shown to produce globally-consistent, metric, and localized maps by incorporating loop closures and intermittent GPS measurementsmore » « less
