Browse Topic: Navigation and guidance systems

Items (1,090)
This research, path planning optimization of the deep Q-network (DQN) algorithm is enhanced through integration with the enhanced deep Q-network (EDQN) for mobile robot (MR) navigation in specific scenarios. This approach involves multiple objectives, such as minimizing path distance, energy consumption, and obstacle avoidance. The proposed algorithm has been adapted to operate MRs in both 10 × 10 and 15 × 15 grid-mapped environments, accommodating both static and dynamic settings. The main objective of the algorithm is to determine the most efficient, optimized path to the target destination. A learning-based MR was utilized to experimentally validate the EDQN methodology, confirming its effectiveness. For robot trajectory tasks, this research demonstrates that the EDQN approach enables collision avoidance, optimizes path efficiency, and achieves practical applicability. Training episodes were implemented over 3000 iterations. In comparison to traditional algorithms such as A*, GA
Arumugam, VengatesanAlagumalai, VasudevanRajendran, Sundarakannan
The exponential growth of the agribusiness market in Brazil combined with the high receptivity among farmers of new technological solutions has driven the study and implementation of high technology in the field. This work aimed to apply servo-assisted driving technology to enable autonomous mobility in an off-road sugarcane truck responsible for harvesting sugarcane. The technology consists of a conventional hydraulic steering with a motor, ECU and torque and angle sensors responsible for reading input data converted from GPS signals and previously recorded tracking lines. The motor responsible for replacing 100% of the physical force generated by the driver acts in accordance with the required torque demand, and the sensors combined with the ECU correct the course to meet the follow-up line through external communication ports. The accuracy of the system depends exclusively on the accuracy of the GPS signal, in this case reaching 2,5 cm, which is considered extremely high accuracy
Oliveira Santos Neto, AntídioLara, VanderleiSilva, EvertonDestro, DanielMoura, MárcioBorges, FelipeHaegele, Timo
The objective of this document is to provide a classification of AI techniques that may be used in AI-based systems for aeronautical products. Aeronautical products include products in Airborne and Air Traffic Management (ATM) and Air Navigation Systems (ANS) domains for crewed and uncrewed aircraft. This document is: Intended to provide an understanding of the AI space, which will improve over time Not intended to provide guidance, objectives, or safety considerations A scenario builder for AI technologies, in particular supervised learning The publication of a taxonomy document for the aviation domain is an opportunity to support other AI standardization initiatives that will also publish taxonomy documents. Disclaimer: This document provides content to support other products of the SAE G-34/EUROCAE WG-114 Committee
G-34 Artificial Intelligence in Aviation
LIDAR-based autonomous mobile robots (AMRs) are gradually being used for gas detection in industries. They detect tiny changes in the composition of the environment in indoor areas that is too risky for humans, making it ideal for the detection of gases. This current work focusses on the basic aspect of gas detection and avoiding unwanted accidents in industrial sectors by using an AMR with LIDAR sensor capable of autonomous navigation and MQ2 a gas detection sensor for identifying the leakages including toxic and explosive gases, and can alert the necessary personnel in real-time by using simultaneous localization and mapping (SLAM) algorithm and gas distribution mapping (GDM). GDM in accordance with SLAM algorithm directs the robot towards the leakage point immediately thereby avoiding accidents. Raspberry Pi 4 is used for efficient data processing and hardware part accomplished with PGM45775 DC motor for movements with 2D LIDAR allowing 360° mapping. The adoption of LIDAR-based AMRs
Feroz Ali, L.Madhankumar, S.Hariush, V.C.Jahath Pranav, R.Jayadeep, J.Jeffrey, S.
There are certain situations when landing an Advanced Air Mobility (AAM) aircraft is required to be performed without assistance from GPS data. For example, AAM aircraft flying in an urban environment with tall buildings and narrow canyons may affect the ability of the AAM aircraft to effectively use GPS to access a landing area. Incorporating a vision-based navigation method, NASA Ames has developed a novel Alternative Position, Navigation, and Timing (APNT) solution for AAM aircraft in environments where GPS is not available
ABSTRACT Determining the required power for the tractive elements of off-road vehicles has always been a critical aspect of the design process for military vehicles. In recent years, military vehicles have been equipped with hybrid, diesel-electric drives to improve stealth capabilities. The electric motors that power the wheel or tracks require an accurate estimation of the power and duty cycle for a vehicle during certain operating conditions. To meet this demand, a GPS-based mobility power model was developed to predict the duty cycle and energy requirements of off-road vehicles. The dynamic vehicle parameters needed to estimate the forces developed during locomotion are determined from the GPS data, and these forces include the following: the gravitational, acceleration, motion resistance, aerodynamic drag, and drawbar forces. Initial application of the mobility power concept began when three U.S. military’s Stryker vehicles were equipped with GPS receivers while conducting a
Ayers, PaulBozdech, George
ABSTRACT In this paper, we present CLICS, a program that optimizes convoy vehicle tracks by intelligently combining sensor updates of all vehicles in the convoy in a distributed, cooperative localization system. Currently, follower vehicles in the convoy rely either on GPS breadcrumbs from the lead vehicle, or rely on sensing the location of its predecessor and following its path. However, GPS availability and accuracy oftentimes cause the former solution to fail, and accumulated errors in tracking and control in long convoys can cause the latter solution to fail. Robotic Research’s CLICS system attempts to overcome these problems by (1) integrating multiple heterogeneous sensor outputs from multiple vehicles (2) developing a distributed, real-time non-linear estimation of inter-vehicle pose using spring network providing coordinated localization for members of a vehicle convoy, and (3) real-time robust synchronization of information amongst the convoy, and local convoy and mission
Wilhelm, RayBalas, CristianSchneider, AnneKlarquist, WilliamLacaze, AlbertoMurphy, Karl
ABSTRACT We present the results of an exploratory investigation of applying a hybrid quantum-classical architecture to an off-road vehicle mobility problem, namely the generation of go/no-go maps posed as a machine learning problem. The premise of this work rests on two observations. First, quantum computing allows in principle for algorithms that provide a speedup over the best known classical counterparts. However, as it is to be expected of such novel and complex tools (both hardware and algorithmic) at this early developmental stage, current quantum algorithms do not always perform well on real-world problems. Second, complex physics-based vehicle and terramechanics models and simulations, currently advocated for high-fidelity high-accuracy ground vehicle–terrain interaction analyses, pose significant computational burden, especially when applied to mobility studies which may require numerous simulation runs. We describe the Quantum-Assisted Helmholtz Machine formulation, suitable
Serban, RaduWilson, MaxBenedetti, MarcelloRealpe-Gómez, JohnPerdomo-Ortiz, AlejandroPetukhov, AndreJayakumar, Paramsothy
ABSTRACT The NAUS ATO (2004-2009) was a follow-on program to the Robotic Follower ATO (2000- 2004) and built on the concept of semi-autonomous leader follower technology to achieve dynamic robotic movement in tactical formations. The NAUS ATO also developed and tested an Unmanned Ground Vehicle (UGV) Self-Security system capable of detecting, tracking, and predicting the intent of human beings in the vicinity of the vehicle. The ATO concluded its Engineering and Evaluation Testing (EET) with a capstone demonstration in October 2008. This paper will detail the technology developed and utilized under the program as well as report on the EET results to the robotic community
Frederick, PhilipKania, RobertBantz, WadeHagner, DonArfa, JoeLacaze, Alberto
ABSTRACT In the field of ground robotics, the problems of global path planning and local obstacle avoidance are often treated separately but both are assessed in terms of a cost related to navigating through a given environment. Traversal cost is typically defined in terms of the required fuel [1], required travel time [2], and imparted mechanical wear [3] to guide route selection. Prior work [4] has shown that obstacle field complexity and navigation cost can be abstracted into quantitative dimensionless parameters. But determining the cost parameters and their relationship to field complexity requires running repeated path planning simulations [4]. This work presents a method for estimating navigation cost solely from geometric obstacle field complexity measures, namely the statistical properties of an obstacle’s shape and the density of obstacles within an environment, eliminating the requirement to run a path planner in a simulation environment. Citation: S. J. Harnett, S. Brennan
Harnett, Stephen J.Brennan, SeanReichard, KarlPentzer, JesseTau, SethGorsich, David
ABSTRACT Robotic platforms require accurate geo-spatial localization for high-level mission planning, real-time site reconnaissance, and multi-machine collaboration. Global navigation satellite system (GNSS) receivers are most commonly used to provide UGVs with accurate geolocation. However, GNSS is not reliable in contested environments because it is vulnerable to jamming, spoofing and black-outs. To address these issues, the United States Army Corps of Engineers (USACE) -Engineer Research and Development Center (ERDC) has developed the Active Terrain Localization Imagery System (ATLIS) which uses on-board perception and a priori satellite imagery to eliminate reliance on GNSS for global positioning of a ground vehicle. Using LiDAR and camera imagery, ATLIS creates a vehicle-centric, orthorectified image that is compared to an a priori satellite image using template matching. It then produces a global position estimate for the vehicle. We develop a method to estimate the uncertainty
Niles, KennethBunkley, StevenWagner, W. JacobBlankenau, IsaacNetchaev, AntonSoylemezoglu, Ahmet
ABSTRACT Many significant advances have been made in autonomous vehicle technology over the recent decades. This includes platooning of heavy trucks. As such, many institutions have created their own version of the basic platooning platform. This includes the California PATH program [1], Japan’s “Energy ITS” project [2], and Auburn University’sCACC Platform [3]. One thing these platforms have in common is a strong dependence on GPS based localization solutions. Issues arise when the platoon navigates into challenging environments, including rural areas with foliage which might block receptions, or more populated areas which might present urban canyon effects. Recent research focus has shifted to handling these situations through the use of alternative sensors, including cameras. The perception method proposed in this paper utilizes the You Only Look Once (YOLO) real-time object detection algorithm in order to bound the lead vehicle using both RGB and IR cameras. Range and bearing are
Flegel, TylerChen, HowardBevly, David
ABSTRACT This paper presents a new concept in GNSS navigation: Sequential Lock GPS (GPS-SL). The new concept and prototype provide a variety of advantages for robustness, solution maintenance, and jamming resistance. Under normal circumstances, GNSS receivers need to receive signals from four satellites simultaneously to get a fix on position and the receiver time bias. If three or less satellites are visible given the occlusions provided by the environment, or because someone/something is intentionally or unintentionally jamming the space, no benefit is provided to the navigation solution. In other words, four or more simultaneous satellites give you a fix, three or less simultaneous satellites usually do not contribute (with some caveats) at all
Lacaze, AlbertoWilhelm, RaySchneider, AnneRay, Tanner
ABSTRACT Autonomous systems are the future of the Army and Ground Vehicle Systems Center has aligned itself accordingly to support unmanned ground vehicle (UGV) development. Physically testing autonomous algorithms and vehicle systems can be expensive and time consuming, a problem addressed by the use of modeling and simulation (M&S) tools. A multitude of both Government owned and Commercial Off-the-Shelf Tools (COTS) are widely available, all claim to virtually evaluate autonomous ground vehicles operating on various environments and scenarios. Most of the COTS tools primarily focus on the commercial automotive industry where vehicles are driven in a structured environment. In this paper two M&S tools, viz., Autonomous Navigation Virtual Environment Laboratory (ANVEL) and Rover Analysis Modeling and Simulation (ROAMS) are evaluated for military applications, where the demands for navigation include both on-road and off-road, as well as both structured and unstructured environments as
Cole, MichaelLucas, CesarKulkarni, Kumar BCarruth, DanielHudson, ChristopherJayakumar, Paramsothy
ABSTRACT Self-driving or autonomous vehicles consist of software and hardware subsystems that perform tasks like sensing, perception, path-planning, vehicle control, and actuation. An error in one of these subsystems may manifest itself in any subsystem to which it is connected. Errors in sensor data propagate through the entire software pipeline from perception to path planning to vehicle control. However, while a small number of previous studies have focused on the propagation of errors in pose estimation or image processing, there has been little prior work on systematic evaluation of the propagation of errors through the entire autonomous architecture. In this work, we present a simulation study of error propagation through an autonomous system and work toward developing appropriate metrics for quantifying the error at both the subsystem and system levels. Finally, we demonstrate how the framework for analyzing error propagation can be applied to analysis of an autonomous systems
Carruth, Daniel W.Goodin, ChristopherDabbiru, LalithaScherer, NicklausJayakumar, Paramsothy
ABSTRACT Cold regions are becoming increasingly more important for off-road vehicle mobility, including autonomous navigation. Most of the time, these regions are covered by snow, and vehicles are forced to operate under active snowfall conditions. In such scenarios, realistic and effective models to predict performance of on-board sensors during snowfalls become of paramount importance. This paper describes a stochastic approach for two-dimensional numerical simulation of dynamic snow scenes that eventually will be used for driving condition visualization and vehicle sensor performance predictions. The model captures realistic snow particle size distribution, terminal near-surface particle speeds, and adequately describes interactions with wind. Citation: S. N. Vecherin, M. E. Tedesche, M. W. Parker, “Dynamic Snowfall Scene Simulations for Autonomous Vehicle Sensor Performance”, In Proceedings of the Ground Vehicle Systems Engineering and Technology Symposium (GVSETS), NDIA, Novi, MI
Vecherin, Sergey N.Tedesche, Molly E.Parker, Michael W.
ABSTRACT The OMU (orientation measurement unit), a combination of inertial (accelerometer, gyroscope), magnetometer and GPS/GNSS sensors, can play a significant role in the stabilization, orientation, navigation and munitions guidance applications performed in ground-based military vehicles. The raw data measured by the OMU’s sensor array includes angular rate, acceleration, magnetic field strength as well as position. By blending these sensor measurements with the use of software algorithms (a.k.a. sensor fusion), the data can be transformed into orientation data (pitch, roll & yaw), commonly referred to as Euler Angles. OMUs have a wide range of price that depends on the quality of its individual device sensors, environmental packaging, standards met and the sophistication of the device firmware used to filter, correct and smooth the inertial inputs used in the computation of application output data. In the ground-based military vehicle industry, applications supported by the OMU
Wright, Ronnie L.Wilson, Chad J.Petty, Millard E.Wong, Michael C.Smith, Michael R.
ABSTRACT Localization refers to the process of estimating ones location (and often orientation) within an environment. Ground vehicle automation, which offers the potential for substantial safety and logistical benefits, requires accurate, robust localization. Current localization solutions, including GPS/INS, LIDAR, and image registration, are all inherently limited in adverse conditions. This paper presents a method of localization that is robust to most conditions that hinder existing techniques. MIT Lincoln Laboratory has developed a new class of ground penetrating radar (GPR) with a novel antenna array design that allows mapping of the subsurface domain for the purpose of localization. A vehicle driving through the mapped area uses a novel real-time correlation-based registration algorithm to estimate the location and orientation of the vehicle with respect to the subsurface map. A demonstration system has achieved localization accuracy of 2 cm. We also discuss tracking results
Stanley, ByronCornick, MatthewKoechling, Jeffrey
ABSTRACT Global Positioning System (GPS) technology has seen increased use in many different military applications worldwide, beyond navigation. The Warfighter uses GPS to enhance Situational Awareness on the battle field with systems such as Land Warrior, Blue Force Tracker, TIGR, and various electronic mission planning tools in locations where the GPS signals are normally not available. For example, this includes the inside of a HMMWV, Stryker, or MRAP. GPS retransmission, or the art of repeating a live GPS signal, has evolved into a technically advanced solution to provide GPS signals to the Warfighter mounted inside ground vehicles, protecting themselves from sniper and IED threats, while providing mobility and Situational Awareness from vehicle mounted communication & navigation systems. The objective of this technical paper is to communicate a relevant understanding of how this technology is being embraced by the Warfighter to accomplish their mission safer and more efficiently
Paul, Mr. Brian
ABSTRACT Ultra-wideband (UWB) radio ranging technology was integrated into a local positioning system (LPS) for tracking mobile robots. A practical issue was the occasional large sporadic errors in the radio range data due to multipath due to reflections and attenuation effect caused by radio penetration through mediums. In this paper, we present a filtering and system integration of the radios with vehicle sensors to produce location and orientation of a moving object being tracked. We introduced a fuzzy neighborhood filter to remove outliers from range data, a progressive trilateration filter to improve update rate and produce a fused estimate of vehicle location with a compass and wheel speed sensors. Experiments were recorded and estimated position and orientation were validated against the video recording of vehicle ground truth. The UWB LPS can be used for navigation and guidance of multiple mobile robots around a command vehicle, and employed for tracking of assets of interest
Cheok, Ka CRadovnikovich, Micho TVempaty, Pavan KHudas, Gregory ROverholt, James LFleck, Paul W
ABSTRACT The Advanced Systems Engineering Capability (ASEC) developed by TARDEC Systems Engineering & Integration (SE&I) group is an integrated Systems Engineering (SE) knowledge creation and capture framework built on a decision centric method, high quality data visualizations, intuitive navigation and systems information management that enable continuous data traceability, real time collaboration and knowledge pattern leverage to support the entire system lifecycle. The ASEC framework has evolved significantly over the past year. New tools have been added for capturing lessons learned from warfighter experiences in theater and for analyzing and validating the needs of ground domains platforms/systems. These stakeholder needs analysis tools may be used to refine the ground domain capability model (functional decomposition) and to help identify opportunities for common solutions across platforms. On-going development of ASEC will migrate all tools to a single virtual desktop to promote
Mendonza, PradeepFitch, John
ABSTRACT The VICTORY initiative has been broadly adopted across the US Defense ground vehicle community. Last year, PEO GCS generated Acquisition Decision Memorandums (ADM) guiding the Platform community to incorporate VICTORY architecture in many vehicle modernization efforts, as well as new start vehicle programs. The community can generally agree that VICTORY is driving the vehicle architecture in a positive direction, providing a much more efficient architecture to enable current, and future, technology integration. A major component of the VICTORY standards addresses the distribution of GPS-supplied information for position, heading, elevation, and timing. The vast majority of major subsystems on today’s military ground vehicles utilize GPS data in some form. These systems include fire control computers, navigation and blue force tracking equipment, ISR assets, electronic warfare devices, personal navigation equipment, laser range finders, command & control (C2) computers, UAV’s
Paul, Brian
ABSTRACT For safe navigation through an environment, autonomous ground vehicles rely on sensory inputs such as cameras, LiDAR, and radar for detection and classification of obstacles and impassable terrain. These sensors provide data representing 3D space surrounding the vehicle. Often this data is obscured by dust, precipitation, objects, or terrain, producing gaps in the sensor field of view. These gaps, or occlusions, can indicate the presence of obstacles, negative obstacles, or rough terrain. Because sensors receive no data in these occlusions, sensor data provides no explicit information about what might be found in the occluded areas. To provide the navigation system with a more complete model of the environment, information about the occlusions must be inferred from sensor data. In this paper we show a probabilistic method for mapping point cloud occlusions in real-time and how knowledge of these occlusions can be integrated into an autonomous vehicle obstacle detection and
Bybee, Taylor C.Ferrin, Jeffrey L.
ABSTRACT In this paper, we explore the usage of normalized cross-correlation to perform localization in GPS-denied environments. Spherical panoramic images from a ground vehicle are transformed to top-down viewpoints and compared with satellite imagery using normalized cross-correlation to find the vehicle’s location within the satellite image. The implementation of this system has yielded positive results when tested upon publicly available panoramic images and satellite imagery, with the identified locations being within an average of 46.95 meters from the ground truth
Cheung, CalvinBaek, Stanley
ABSTRACT This work presents the development of a high fidelity Simulation In the Loop/Hardware In the Loop simulation environment using add-ons to Autonomous Navigation Virtual Environment Laboratory (ANVEL) and a navigation unit developed by Auburn University’s GPS and Vehicle Dynamics Lab (GAVLAB) in support of the United States Army’s Autonomous Ground Resupply Science Technology Objective. The developed add-ons include a real time interface for ANVEL, Inertial Measurement Unit module, Wheel Speed Sensor module, and a GPS module that allows simulated signals or generated Radio Frequency signals. The developed add-ons allow for faster development of navigation algorithms and controllers due to a readily available, highly accurate truth from ANVEL and can be configured to introduce realistic errors from sensors, hardware, and GPS signals such that algorithm and controller robustness can be easily examined
Nelson, BrentlyBevly, DavidRatowski, JeffTheisen, Bernard
ABSTRACT Autonomous ground vehicles have the potential to reduce the risk to Soldiers in unfamiliar, unstructured environments. Unmanned operations in unstructured environments require the ability to guide the vehicles from their starting position to a target position. This paper proposes a framework to plan paths across such unstructured environments using a priori information about the environment as cost criteria into a multi-criteria, multi-agent path planner. The proposed multi-criteria, multi-agent path planner uses a penalty-based A* algorithm to plan multiple paths across the unstructured environment and uses entropy weighting for generating weights to calculate a multi-criteria cost with distance, risk, and soil trafficability. The paths generated by the proposed framework provide a better overall performance across the cost criteria and can be used as waypoints to navigate UGVs in off-road environments. Citation: S. Khatiwada, P. Murray-Tuite, M.J. Schmid, “Multi-Criteria
Khatiwada, SachetMurray-Tuite, PamelaSchmid, Matthias J
ABSTRACT Accurate terrain mapping is of paramount importance for motion planning and safe navigation in unstructured terrain. LIDAR sensors provide a modality, in the form of a 3D point cloud, that can be used to estimate the elevation map of the surrounding environment. But, working with the 3D point cloud data turns out to be challenging. This is primarily due to the unstructured nature of the point clouds, relative sparsity of the data points, occlusions due to negative slopes and obstacles, and the high computational burden of traditional point cloud algorithms. We tackle these problems with the help of a learning-based, efficient data processing approach for vehicle-centric terrain reconstruction using a 3D LIDAR. The 3D LIDAR point cloud is projected on the ground plane, which is processed by a generative adversarial network (GAN) architecture in the form of an image to fill in the missing parts of the terrain heightmap. We train the GAN model on artificially generated datasets
Sutavani, SarangZheng, AndrewJoglekar, AjinkyaSmereka, JonathonGorsich, DavidKrovi, VenkatVaidya, Umesh
ABSTRACT Geotechnical site characterization is the process of collecting geophysical and geospatial characteristics about the surface and subsurface to create a 3-dimensional (3D) model. Current Robot Operating System (ROS) world models are designed primarily for navigation in unknown environments; however, they do not store the geotechnical characteristics requisite for environmental assessment, archaeology, construction engineering, or disaster response. The automotive industry is researching High Definition (HD) Maps, which contain more information and are currently being used by autonomous vehicles for ground truth localization, but they are static and primarily used for navigation in highly regulated infrastructure. Modern site characterization and HD mapping methods involve survey engineers working on-site followed by lengthy post processing. This research addresses the shortcomings for current world models and site characterization by introducing Site Model Geospatial System
Richards, Matthew E.Murphy, Kevin F.Toledo, Israel LopezSoylemezoglu, Ahmet
ABSTRACT New generations of ground vehicles are required to perform tasks with an increased level of autonomy. Autonomous navigation and Artificial Intelligence on the edge are growing fields that require more sensors and more computational power to perform these missions. Furthermore, new sensors in the market produce better quality data at higher rates while new processors can increase substantially the computational power. Therefore, near-future ground vehicles will be equipped with large number of sensors that will produce data at rates that has not been seen before, while at the same time, data processing power will be significantly increased. This new scenario of advanced ground vehicles applications and increase in data amount and processing power, has brought new challenges with it: low determinism, excessive power needs, data losses and large response latency. In this article, a novel approach to on-board artificial intelligence (AI) is presented that is based on state-of-the
Ghiglino, PabloHarshe, Mandar
ABSTRACT A major benefit of intelligent and autonomous vehicles is their ability to navigate through hazardous environments that pose a significant danger to humans. In such environments, eventual damage to vehicle sensors is often inevitable. To address this threat to vehicle function, we propose a more robust system in which information from alternative sensors is leveraged to restore navigation capabilities in the case of primary sensor failure. This system employs image translation methods that enable the vehicle to use images generated from an auxiliary camera to synthesize the display of the primary camera. In this work, we present a conditional Generative Adversarial Network (cGAN) based method for view translation coupled with a Residual Neural Network for imitation learning. We evaluate our approach in the CARLA simulator and demonstrate its ability to restore navigation capabilities to a real-world vehicle by generating a front-view image from a left-camera view. Citation
Zhang, DanSanders, BradleyByrd, GraysonLuo, FengKrovi, VenkatGorsich, DavidSmereka, Jonathon M.Brudnak, Mark
ABSTRACT Autonomous vehicles rely on path planning to guide them towards their destination. These paths are susceptible to interruption by impassable hazards detected at the local scale via on-board sensors, and malicious disruption. We define robustness as an additional parameter which can be incorporated into multi-objective optimization functions for path planning. The robustness at any point is the output of a function of the isochrone map at that point for a set travel time. The function calculates the sum of the difference in area between the isochrone map and the isochrone map with an impassable semi-circle hazard inserted in each of the four cardinal directions. We calculate and compare two different Pareto paths which use robustness as an input parameter with different weights. Citation: T. Jonsson Damgaard, M. Rittri, P. Franz, A. Halota “Robust Path Planning in the Battlefield,” In Proceedings of the Ground Vehicle Systems Engineering and Technology Symposium (GVSETS), NDIA
Damgaard, Thomas JonssonRittri, MikaelFranz, PatrickHalota, Anika
ABSTRACT This paper will document the development of the Convoy Active Safety Technology (CAST) program, which was created to design a low cost, optionally manned vehicle (OMV) solution for tactical wheeled vehicle (TWV) fleet. This paper will describe the approach taken to integrate low cost sensors for understanding the environment sufficiently to accomplish convoy missions. This paper will also discuss the approach taken to develop the low cost guidance and navigation solution used in the CAST program
Simon, DavidTheisen, Bernard
ABSTRACT This work presents the development of an algorithm to incorporate measurements from multiple antennas to improve the relative position solution between convoying vehicles provided by Global Positioning System (GPS) measurements. The technique presented, incorporates measurements from multiple antennas with a known fixed-baseline between a base antenna and auxiliary antenna on a base vehicle, and a rover antenna on a rover vehicle. The additional information provided by the fixed-baseline distance is used to provide an additional measurement with low uncertainty for improved integer ambiguity resolution between the base and auxiliary receiver, which in turn, provides additional measurements for determining the integer ambiguity difference between the base and rover receivers for the computation of a high-precision relative position vector (HPRPV
Tabb, Thomas T.Bevly, DavidMartin, ScottRatowski, Jeff
ABSTRACT As part of an Internal Research and Design effort to take existing disparate technologies and integrate them into a single autonomous vehicle to advance the state-of-the-art in unmanned ground vehicle autonomy, SwRI has developed a data representation and routing algorithm to deal with the complexities of interconnecting urban roadways and the static and dynamic hazards in such an environment. The program was designed to utilize data from a Route Network Definition File (RNDF), which contains a priori roadway network data. Using its known location and a given destination, the vehicle determines the shortest route to completion. If, during traversal of that route, the vehicle detects an obstacle in its path using its on-board sensors, it will dynamically re-route its path whether that requires changing lanes on a multiple lane road or turning around completely and finding a different route if the path is completely blocked
Mentzer, ChristopherMcWilliams, GeorgeKozak, Kristopher
ABSTRACT An approach for a perception system for autonomous vehicle navigation is presented. The approach relies on low-cost electro-optical (EO) sensors for terrain classification, 3D environment modeling, and object/obstacle recognition. Stereo vision is used to generate real-time range maps which are populated into a hybrid probabilistic environment model. Textural and spectral cues are utilized for terrain classification and spatial contextual knowledge is proposed to augment object recognition performance
Flannigan, William C.Rigney, Michael P.Alley, Kevin J.
ABSTRACT A critical and time-consuming part of commissioning an unmanned ground vehicle (UGV) is tuning and calibrating the navigation and control systems. This involves selecting and modifying parameters for these systems to obtain a desired response. Tuning these parameters often requires experience or technical expertise that may not be readily available in a time of need. Even the simple task of measuring the mounting location of the sensors introduce opportunities for user error. In addition, the tuning parameters for these systems may change significantly between UGVs. These challenges motivate the need for automated tuning and calibration algorithms to set parameters without the interaction from a user. This work presents automated tuning and calibration approaches for UGVs. Citation: N. Bunderson, D. Bevly, A. Costley, W. Bryan, G. Mifflin, C. Balas “Automated Tuning and Calibration for Unmanned Ground Vehicles”, In Proceedings of the Ground Vehicle Systems Engineering and
Bunderson, NateBevly, DavidCostley, AustinBryan, WilliamMifflin, GregoryBalas, Cristian
Items per page:
1 – 50 of 1090