Browse Topic: Control systems

Items (5,569)
ABSTRACT Recurrent Neural Networks have largely been explored for low-dimensional time-series tasks due to their fading memory properties, which is not needed for feed-forward methods like the Convolutional Neural Network. However, benefits of using a recurrent-based neural network (i.e. reservoir computing) for time-independent inputs includes faster training times, lower training requirements, and reduced computational burdens, along with competitive performances to standard machine learning methods. This is especially important for high-dimensional signals like complex images. In this report, a modified Echo State Network (ESN) is introduced and evaluated for its ability to perform semantic segmentation. The parallel ESN containing 16 parallel reservoirs has an image processing time of 2 seconds with an 88% classification rate of 3 classes, with no prior feature extraction or normalization, and a training time of under 2 minutes. Citation: S. Gardner, M. R. Haider, J. Smereka, P
Gardner, S.Haider, M.R.Smereka, J.Jayakumar, P.Kulkarni, K.Gorsich, D.Moradi, L.Vantsevich, V.
ABSTRACT A Model Predictive Control (MPC) LIDAR-based constant speed local obstacle avoidance algorithm has been implemented on rigid terrain and granular terrain in Chrono to examine the robustness of this control method. Provided LIDAR data as well as a target location, a vehicle can route itself around obstacles as it encounters them and arrive at an end goal via an optimal route. Using Chrono, a multibody physics API, this controller has been tested on a complex multibody physics HMMWV model representing the plant in this study. A penalty-based DEM approach is used to model contacts on both rigid ground and granular terrain. We draw conclusions regarding the MPC algorithm performance based on its ability to navigate the Chrono HMMWV on rigid and granular terrain
Haraus, NicholasSerban, RaduFleischmann, Jonathan
ABSTRACT This paper describes work to develop a hands-free, heads-up control system for Unmanned Ground Vehicles (UGVs) under an SBIR Phase I contract. Industry is building upon pioneering work that it has done in creating a speech recognition system that works well in noisy environments, by developing a robust key word spotting algorithm enabling UGV Operators to give speech commands to the UGV completely hands-free. Industry will also research and develop two sub-vocal control modes: whisper speech and teeth clicks. Industry is also developing a system that will enable the Operator to drive a UGV, with a high level of fidelity, to a location selected by the Operator using hands-free commands in conjunction with image segmentation and video overlays. This Phase I effort will culminate in a proof-of-concept demonstration of a hands-free, heads-up system, implemented on a small UGV, that will enable the Operator have a high level of fidelity for control of the system
Brown, JonathanGray, Jeremy P.Blanco, ChrisJuneja, AmitAlberts, JoelReinerman, Lauren
Summary This paper discusses the latest techniques in vehicle modeling and simulation to support ground vehicle performance and fuel economy studies, enable system design optimization, and facilitate detailed control system design. The Autonomie software package, developed at Argonne National Laboratory, is described with emphasis on its capabilities to support Model-in-the-Loop, Software-in-the-Loop (SIL), Component-in-the-Loop (CIL), and Hardware-in-the-Loop simulations. Autonomie supports Model-Based Systems Engineering, which is growing in use as ground vehicles become more sophisticated and complex, with many more subsystems interacting within the vehicle and the environmental conditions in which the vehicles operate becoming more challenging and varied. With the advent of hybrid powertrains, the additional dimension of vehicle architecture has become one of the design variables that must be considered. This complexity results in the need for a simulation tool that is capable of
Michaels, LarryHalbach, ShaneShidore, NeerajRousseau, Aymeric
ABSTRACT A simulation capable of modeling grid-tied electrical systems, vehicle-to-grid (V2G) and vehicle-to-vehicle(V2V) resource sharing was developed within the MATLAB/Simulink environment. Using the steady state admittance matrix approach, the unknown currents and voltages within the network are determined at each time step. This eliminates the need for states associated with the distributed system. Each vehicle has two dynamic states: (1) stored energy and (2) fuel consumed while the generators have only a single fuel consumed state. One of its potential uses is to assess the sensitivity of fuel consumption with respect to the control system parameters used to maintain a vehicle-centric bus voltage under dynamic loading conditions
Jane, Robert S.Parker, Gordon G.Weaver, Wayne W.Goldsmith, Steven Y.
ABSTRACT Upgrading and modernizing vehicle electrical systems in a cost-effective manner has been an ongoing challenge for PEOs and PMs across multiple services. UEC Electronics’ advanced DPCMS achieves that end state
Peterson, Christopher R.Swartzwelter, Scott R.
ABSTRACT This paper develops a linear closed form equation as required for automatic plowing depth control of a mine clearing combat vehicle. The vehicle will be tasked with using its Mine Clearing Blade (MCB) to remove surface laid and buried land mines on undulating terrain so that other vehicles can follow its path without the threat of mines. Blade control must be automatic to ensure that the target depth of the cleared path is achieved and all mines on the path are removed. A closed form solution for real-time computing relating the MCB motion and hydraulic actuator movement is developed and implemented. The equations are provided in symbolic form so that the dimensions of the mechanism can be directly substituted and/or modified without re-derivation. Results were verified with field measured data and implemented in the controller of a real vehicle to successfully achieve objective goal of Automatic Mine Clearing
Tsai, Fuh-FengStrittmatter, Kevin
ABSTRACT Building upon the foundation of thermal management system metrics developed and published from earlier studies, this paper addresses the incorporation of the vehicle Environmental Control Systems (ECS) into this framework. Case studies are presented that look at the implications of several ECS alternatives on a conceptual military, hybrid electric vehicle platform through exemplar calculations of thermal management system (TMS) metrics. Utilization of these metrics allows for the comparison of design alternatives through a conceptual design case study. Two sets of case studies are evaluated in tandem within this study. In the first, the effect of cabin air-cooled component heat rejection is compared to direct TMS liquid-cooled heat rejection alternatives. The considerations of performance, packaging and reliability concerns are discussed. In the second set of case studies, variations in vapor compression cycle thermodynamic states are considered to provide metric-based
Jones, StanleyMendoza, JohnFrazier, GeorgeKhalil, Ghassan
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
ABSTRACT This paper presents results that quantify how the homogenous and heterogeneous parallel interconnection of lithium-ion battery packs affect adversely their cycle-life, and how this problem can be corrected. Laboratory tests and modeling/simulation of two different lithium-ion battery packs are presented that highlight the importance of monitoring and controlling battery packs in parallel. A solution to this problem was designed and a prototype implemented that has the potential to fit within the available space of a commercially available lithium-ion 6T battery pack [1], [2]. This solution controls the sharing of load among heterogeneous and homogeneous lithium-ion 6T batteries with an efficiency of 95% or better, which is anticipated via simulations, to provide an improvement of cycle life of at least 3% for homogeneous and 10% for heterogeneous interconnections. This solution provides additional benefits including terminal voltage regulation and the flexibility to work as an
Rentel, Carlos H.Cheng, ShuoXing, LauraPecht, Michael
ABSTRACT The mechanical behavior of a military vehicle during off-highway operation is complex and highly nonlinear. Some current vehicle concepts include added intelligence through the implementation of sensors and controllers to enable autonomous or semi-autonomous operations. Control systems have typically been developed with controls software where the mechanical plant and sensors are represented as simplified and often linearized blocks, resulting in a poor vehicle assessment. This paper describes the development of an integrated environment for a control system, mechanical system dynamics, and sensor simulation for an improved assessment of the vehicle system performance. The vehicle chosen is an autonomous robot that attempts to follow a prescribed path along an off-highway terrain. The effect of including a stability controller for vehicle mobility is assessed. The architecture of the integrated simulation environment is described and its potential to improve schedule and
Jayakumar, ParamsothySmith, WilliamRoss, Brant A.Jategaonkar, RohitKonarzewski, Krystian
ABSTRACT The IGVC offers a design experience that is at the very cutting edge of engineering education, with a particular focus in developing engineering control/sensor integration experience for the college student participants. A main challenge area for teams is the proper processing of all the vehicle sensor feeds, optimal integration of the sensor feeds into a world map and the vehicle leveraging that world map to plot a safe course using robust control algorithms. This has been an ongoing challenge throughout the 26 year history of the competition and is a challenge shared with the growing autonomous vehicle industry. High consistency, reliability and redundancy of sensor feeds, accurate sensor fusion and fault-tolerant vehicle controls are critical, as even small misinterpretations can cause catastrophic results, as evidenced by the recent serious vehicle crashes experienced by self-driving companies including Tesla and Uber Optimal control techniques & sensor selection
Kosinski, AndrewIyengar, KiranTarakhovsky, JaneLane, JerryCheok, KaCTheisen, BernieOweis, Sami
ABSTRACT A detailed methodology employing a system model of a tracked vehicle with a gun turret is used to analyze the stresses and loads applied to the gun mount as a result of gun firing events. The vehicle system model combines a Virtual Lab.Motion model of the tracked vehicle and gun mount which includes track super element, flexible gun mount body, and a beam element representation of the gun and gun tube sleeve coupled with a MATLAB/Simulink model of the hydraulic/pneumatic recoil system and gun pointing control system. This coupled system model with flexible components is needed for this analysis to determine the portion of the impulse that results in gun mount deformation. A brief overview of the vehicle system model, a detailed description of the gun mount model, and analysis of the gun mount loads and stress is included
Youtt, Dan
ABSTRACT Modern electronic control units (ECUs) typically contain many physically based models represented by a complex structure of maps, curves and scalar parameters. The purpose of these models is to monitor or predict engine values that are normally measured by actual sensors. If the model structure is a good representation of the physical system and the parameters are well fitted, such a model can replace the sensor and serve as a virtual sensor to reduce the cost and complexity of the overall system. Virtual sensors are commonly used in the ECU for predicting engine torque, air pressure and flow, emissions, catalyst temperature, and exhaust gas temperatures. To ensure an optimal prediction quality of these models, their parameters need to be calibrated using real measurement data collected, e.g., in the vehicle or in the test cell. Due to the models’ complexity and the high number of parameters, a manual calibration is very time consuming or even impossible. Instead, iterative
Gutjahr, TobiasKleinegraeber, HolgerKruse, Thomas
ABSTRACT The United States Army Tank Automotive Research, Development and Engineering Center (TARDEC) is actively investigating and researching ways to advance the state of combat hybrid-electric power system technology for use in military vehicles including the Future Combat Systems’ family of manned and unmanned ground vehicles. Science Applications International Corporation (SAIC) is the lead contractor for operating the Power and Energy System Integration Laboratory (P&E SIL) in Santa Clara, CA. The P&E SIL houses a combat hybrid electric power system including a diesel engine, generator, high voltage bus, DC-DC converter, lithium ion battery pack, left and right induction motors, and left and right dynamometers. The power system is sized for a 20-22 ton tracked vehicle. The dynamometers are responsible for emulating loads that the vehicle would see while running over a course. This paper discusses the control system design for achieving mobility load emulation. Mobility load
Goodell, JarrettSmith, WilfordWong, Byron
ABSTRACT Automatic guided vehicles (AGV) have made big inroads in the automation of assembly plants and warehouse operations. There are thousands of AGV units in operation at OEM supplier and service facilities worldwide in virtually every major manufacturing and distribution sector. Although today’s AGV systems can be reconfigured and adapted to meet changes in operation and need, their adaptability is often limited because of inadequacies in current systems. This paper describes a wireless navigated (WN) omni-directional (OD) autonomous guided vehicle (AGV) that incorporates three technical innovations that address the shortfalls. The AGV features consist of: 1) A newly developed integrated wireless navigation technology to allow rapid rerouting of navigation pathways; 2) Omnidirectional wheels to move independently in different directions; 3) Modular space frame construction to conveniently resize and reshape the AGV platform. It includes an overview of the AGVs technical features
Cheok, Ka CRadovnikovich, MichoFleck, PaulHallenbeck, KevinGrzebyk, SteveVanneste, JerryLudwig, WolfgangGarner, Robert
ABSTRACT A Non-linear Model Predictive Controller (NMPC) was developed for an unmanned ground vehicle (UGV). The NMPC uses a particle swarm pattern search algorithm to optimize the control input, which contains a desired steer angle and a desired longitudinal velocity. The NMPC is designed to approach a target whilst avoiding obstacles that are detected using a light detection and ranging sensor (lidar). Since not all obstacles are stationary, an obstacle tracking algorithm is employed to track obstacles. Two point cluster detection algorithms were reviewed, and a constant velocity Kalman filter-based tracking loop was developed. The tracked obstacles’ positions are predicted using a constant velocity model in the NMPC; this allows for avoidance of both stationary and dynamic obstacles
Stamenov, VelislavGeiger, StephenBevly, DavidBalas, Cristian
ABSTRACT The concept of handheld control systems with modular and/or integrated display provides the flexibility of operator use that supports the needs of today’s warfighters. A human machine interface control system that easily integrates with vehicle systems through common architecture and can transition to support dismounted operations provides warfighters with functional mobility they do not have today. With Size, Weight and Power along with reliability, maintainability and availability driving the needs of most platforms for both upgrade and development, moving to convertible (mounted to handheld) and transferrable control systems supports these needs as well as the need for the warfighter to maintain continuous control and command connectivity in uncertain mission conditions
Roy, Monica V.
Summary Growing environmental concerns coupled with the complex issue of global crude oil supplies drive automobile industry towards the development of fuel-efficient vehicles. Due to the possible multiple-power-source nature and the complex configuration and operation modes, the control strategy of a military vehicle is more complicated than that of a conventional vehicle. Furthermore, military vehicles often have heavier weights and are used to operate multiple functions such as engaging weapons, turning on sensors, silent watch, etc., which results in big load fluctuation. In this paper we present our research in optimizing power flow in a heavy vehicle for a given mission plan. A mission plan consists of a sequence of operations and speed profiles. The vehicle architecture will be modeled based on Stryker power system which consists of a diesel engine, a main battery pack, an auxiliary battery pack, and an APU. The APU can supply power to the auxiliary loads and auxiliary batteries
Murphey, Yi L.Masrur, M. AbulNeumann, Donald E.
ABSTRACT The United States Army Tank-Automotive Research, Development and Engineering Center (TARDEC) is actively researching methods to advance the state of hybrid-electric power system technology for use in military vehicles. Supporting this research, Science Applications International Corporation (SAIC) is the lead contractor for developing the Hybrid Electric Re-Configurable Movable Integration Test-bed (HERMIT), which is operated at TARDEC in Warren, Michigan. The HERMIT is a ground-vehicle-sized series hybrid-electric test-bed featuring a diesel engine, permanent magnet generator, high voltage bus, DC-DC converter, lithium ion battery pack, left and right traction motors, thermal management system, and left and right bi-directional dynamometers. The power system is sized for a 20-22 ton tracked vehicle. The dynamometers are responsible for emulating loads that the tracked vehicle would see while running over a military theater-type course. This paper discusses the control system
Goodell, JarrettConnolly, TomLeslie, EdSmith, Wilford
ABSTRACT The use and operation of unmanned systems are becoming more commonplace and as missions gain complexity, our warfighters are demanding increasing levels of system functionality. At the same time, decision making is becoming increasingly data driven and operators must process large amounts of data while also controlling unmanned assets. Factors impacting robotic/unmanned asset control include mission task complexity, line-of-sight/non-line-of-sight operations, simultaneous UxV control, and communication bandwidth availability. It is critical that any unmanned system requiring human interaction, is designed as a “human-in-the-loop” system from the beginning to ensure that operator cognitive load is minimized and operator effectiveness is optimized. Best practice human factors engineering in the form of human machine interfaces and user-centered design for robotic/unmanned control systems integrated early in platform concept and design phases can significantly impact platform
MacDonald, Brian
ABSTRACT Raytheon is in the final stages of production of three high performance thermal imaging / fire control systems being integrated on existing USMC and US Army armored vehicles. A goal in the design of these systems was to provide integration into the host vehicle that when viewed by the customer and user provided the enhanced capabilities of today’s latest thermal imaging and image processing technology as well as operating in concert with the vehicle as originally designed. This paper will summarize the technical solutions for each of these programs emphasizing the thermal imaging, fire control, image processing and vehicle integration technologies. It will also outline guiding philosophies and lessons learned used to focus the design team in achieving the successful integration. The programs to be reviewed are; USMC 2nd Gen Thermal Imaging System, the USMC LAV-25 Improved Thermal Sight System (ITSS) and the USMC / US Army M1A1 50 Cal Thermal Sight / DayTV System
LaSala, Paul V.Raaum, Bryan J.
ABSTRACT Supporting Open Architecture is a key to most major automation and control suppliers. In every industry, there is a desire to make a unified control system architecture that can easily integrate control system equipment from multiple suppliers. Whether it is a Navy military application or an industrial application, the needs are almost identical. Some of the keys to providing this transparency among control systems are utilizing an open standard that can pull together communications from multiple suppliers. In this paper, SIEMENS will demonstrate the capabilities of utilizing an open standard, which is PROFINET. By adhering to the PROFINET standards, Open Architecture is achieved at many levels in a naval application. Open Architecture is intended to yield modular, interoperable systems that adhere to open standards with published interfaces. As will be demonstrated by this paper, PROFINET provides these capabilities and more. By implementing PROFINET as the infrastructure for
Cantrell, Wayne
ABSTRACT Latencies as small as 170 msec significantly degrade ground vehicle teleoperation performance and latencies greater than a second usually lead to a “move and wait” style of control. TORIS (Teleoperation Of Robots Improvement System) mitigates the effects of latency by providing the operator with a predictive display showing a synthetic latency-corrected view of the robot’s relationship to the local environment and control primitives that remove the operator from the high-frequency parts of the robot control loops. TORIS uses operator joystick inputs to specify relative robot orientations and forward travel distances rather than rotational and translational velocities, with control loops on the robot making the robot achieve the commanded sequence of poses. Because teleoperated ground vehicles vary in sensor suite and on-board computation, TORIS supports multiple predictive display methods. Future work includes providing obstacle detection and avoidance capabilities to support
Kluge, Karl C.Lacaze, AlbertoCelle, Zach LaLegowik, SteveMurphy, KarlThomson, Rob
ABSTRACT Over time, the National Institute of Standards and Technology (NIST) has refined the 4Dimension / Real-time Control System (4D/RCS) architecture for use in Unmanned Ground Vehicles (UGVs). This architecture, when applied to a fully autonomous vehicle designed for missions in urban environments, can greatly assist in the process of saving time and lives by creating a more intelligent vehicle that acts in a safer and more efficient manner. Southwest Research Institute (SwRI®) has undertaken the Southwest Safe Transport Initiative (SSTI) aimed at investigating the development and commercialization of vehicle autonomy as well as vehicle-based telemetry systems to improve active safety systems and autonomy. This paper will discuss the implementation of the 4D/RCS architecture to the SSTI autonomous vehicle, a 2006 Ford Explorer
McWilliams, GeorgeBrown, Michael
ABSTRACT Over time, the National Institute of Standards and Technology (NIST) has refined the 4Dimension / Real-time Control System (4D/RCS) architecture for use in Unmanned Ground Vehicles (UGVs). This architecture, when applied to a fully autonomous vehicle designed for missions in urban environments, can greatly assist in the process of saving time and lives by creating a more intelligent vehicle that acts in a safer and more efficient manner. Southwest Research Institute (SwRI®) has undertaken the Southwest Safe Transport Initiative (SSTI) aimed at investigating the development and commercialization of vehicle autonomy as well as vehicle-based telemetry systems to improve active safety systems and autonomy. This paper will discuss the implementation of the 4D/RCS architecture to the SSTI autonomous vehicle, a 2006 Ford Explorer
McWilliams, GeorgeBrown, Michael
ABSTRACT Can convolutional neural networks (CNNs) recognize gestures from a camera for robotic control? We examine this question using a small set of vehicle control gestures (move forward, grab control, no gesture, release control, stop, turn left, and turn right). Deep learning methods typically require large amounts of training data. For image recognition, the ImageNet data set is a widely used data set that consists of millions of labeled images. We do not expect to be able to collect a similar volume of training data for vehicle control gestures. Our method applies transfer learning to initialize the weights of the convolutional layers of the CNN to values obtained through training on the ImageNet data set. The fully connected layers of our network are then trained on a smaller set of gesture data that we collected and labeled. Our data set consists of about 50,000 images recorded at ten frames per second, collected and labeled in less than 15 man-hours. Images contain multiple
Kawatsu, ChrisKoss, FrankGillies, AndyZhao, AaronCrossman, JacobPurman, BenStone, DaveDahn, Dawn
ABSTRACT Battelle has built multiple auxiliary power generators using liquid logistic fuels that tightly couple fuel cell and fuel processing systems, providing new control challenges. Acting as an auxiliary power supply places difficult requirements for load following and transients. Additional challenges arise from the differing time constraints of the fuel processor and fuel cell systems and the need to maintain water balance. A novel method of controlling the system has been formulated and applied, providing pushbutton start capabilities. The control system has proven to be robust and easily adaptable to system design and operating parameter changes. In addition to control concerns, the requirements for vehicle integration and desulphurization have been investigated
Thornton, DouglasContini, VinceMcCandlish, Todd
ABSTRACT Problem: The traditional four (4) methods for improving reliability; 1) High design safety margin, 2) Reduction in component count or system architectural complexity, 3) Redundancy, and 4) Back-up capability, are often ignored or perceived as being excessively costly in weight, space claim as well as money. Solution 1: Discussed here are the practical and very cost effective methods for achieving improved reliability by Functional Interface Stress Hardening (FISHtm or FISHingtm). The Author has been able to apply FISH to eliminate 70-92% of unscheduled equipment downtime, within 30-60 days, for more than 30 of the Fortune 500 and many other large companies which utilize automation controls, computers, power electronics and hydraulic control systems. Solution 2: From Structured Innovation the 33 DFR Methods & R-TRIZ Tool can be used to grow or improve reliability, via rapid innovation. The R-TRIZ tool) is provided so that users can instantly select the best 2, 3 or 4 of these
Cooper, Howard C
ABSTRACT In order to expedite the development of robotic target carriers which can be used to enhance military training, the modification of technology developed for passenger vehicle Automated Driver Assist Systems (ADAS) can be performed. This field uses robotic platforms to carry targets into the path of a moving vehicle for testing ADAS systems. Platforms which are built on the basis of customization can be modified to be resistant to small arms fire while carrying a mixture of hostile and friendly pseudo-soldiers during area-clearing and coordinated attack simulations. By starting with the technology already developed to perform path following and target carrying operations, the military can further develop training programs and equipment with a small amount of time and investment. Citation: M. Bartholomew, D. Andreatta, P. Muthaiah, N. Helber, G. Heydinger, S. Zagorski, “Bringing Robotic Platforms from Vehicle Testing to Warrior Training,” In Proceedings of the Ground Vehicle
Bartholomew, MeredithAndreatta, DaleMuthaiah, PonaravindHelber, NickHeydinger, GaryZagorski, Scott
ABSTRACT There are an increasing number of simulation tools either available today or coming online for ground vehicle autonomous behavior modeling. Engineers in TARDECs Ground Vehicle Robotics (GVR) area have dedicated a significant portion of effort over the past four plus years reviewing, implementing and promoting the development these tools. This paper provides an overview of these efforts and discusses the current state of these virtual environments from the perspective of TARDEC robotic researchers, developers, engineers and program managers. We specifically touch on experiences implementing control algorithms in Player/Stage, ANVEL and MODSIM/RIDE. While we take specific measures to avoid comparative analysis we provide our insight into the current strengths and limitations of these systems as it relates to utilization on research efforts, a quick development/integration program (Dismounted Soldier Autonomy Tools) and a JCTD effort (AMAS). We also give an overview of other
Frederick, PhilipRose, Mike DelPirozzo, DavidKania, RobertTheisen, BernardRoth, Stephanie
ABSTRACT Modern perception systems for autonomous vehicles are often dependent on deep neural networks, however, such networks are unfortunately susceptible to subtle perturbations to their inputs. Due to the interconnected nature of perception/control systems in autonomous vehicles, it is quite difficult to evaluate the autonomy stack’s robustness in different scenarios. Numerous tools have been developed to assist developers increase the robustness of these algorithms for on-road driving, but little has been accomplished for off-road driving. This work aims to bridge this gap by presenting a reinforcement learning framework to identify unsuspecting off-road scenes that confuse a custom autonomy stack with a DNN-based perception algorithm to ultimately lead the vehicle into a collision. Citation: T. Sender, M. Brudnak, R. Steiger, R. Vasudevan, B. Epureanu, “Using Deep Reinforcement Learning to Generate Adversarial Scenarios for Off-Road Autonomous Vehicles,” In Proceedings of the
Sender, TedBrudnak, MarkSteiger, ReidVasudevan, RamEpureanu, Bogdan
ABSTRACT Use of the Model-Based Design (MBD) processes is becoming increasingly common in embedded control system software as a means to manage software complexity, improve quality, and reduce development costs. The MBD process can achieve these goals by combining the design, simulation, and implementation of software features into a single, integrated workflow that reduces development effort and allows extensive software testing to be performed in simulation. In order to realize the full benefit of MBD, engineering organizations must invest resources intelligently in the tools, processes, and infrastructure to avoid common mistakes and pitfalls
Fraser, SteveFenstermacher, DavidDoyle, Chris
ABSTRACT Modern ground vehicles rely on Controller Area Network (CAN) bus for communication between Electronic Control Units (ECUs) as a vital component to connect sensors and actuators together in a mission-critical distributed real-time vehicle control system. CAN is well-suited to this task and over the more than three decades since its inception it has become a proven and ubiquitous technology. But its age means that it was not designed for modern security threats of local and remote attacks and special techniques must be deployed to protect CAN. This paper provides a simple taxonomy of attacks on CAN, including how an attack accesses a CAN bus, and discusses four techniques used to defend against these attacks. Citation: K Tindell, “Defending In-vehicle CAN Buses From Attacks,” In Proceedings of the Ground Vehicle Systems Engineering and Technology Symposium (GVSETS), NDIA, Novi, MI, Aug. 16-18, 2022
Tindell, Kenneth
ABSTRACT Time lags are known to reduce performance in human-in-the-loop control systems. Performance decrements for human-in-the-loop control systems as a result of time lags are generally associated with the operator’s inability to predict the outcome of their control input and are dependent upon the characteristics of the lag (e.g., magnitude and variability). Further, the effects of variable time lags are not well studied or understood, but may exacerbate the effects on human control actions observed with fixed lags. Several studies have demonstrated mechanisms that can help combat the effects of lag including adaptation, mathematical predictors (e.g., filters), and predictive displays. This experiment examined the effects of lag and lag variability on a simulated driving task, as well as a possible mitigation (predictive display) for the effects of lag. Results indicated that lag variability significantly reduced driving performance, and that the predictive display significantly
Davis, JamesSmyth, ChristopherMcDowell, Kaleb
ABSTRACT The concept of handheld control systems with modular and/or integrated display provides the flexibility of operator use that supports the needs of today’s warfighters. A human machine interface control system that easily integrates with vehicle systems through common architecture and can transition to support dismounted operations provides warfighters with functional mobility they do not have today. With Size, Weight and Power along with reliability, maintainability and availability driving the needs of most platforms for both upgrade and development, moving to convertible (mounted to handheld) and transferrable control systems supports these needs as well as the need for the warfighter to maintain continuous control and command connectivity in uncertain mission conditions
Roy, Monica V.
ABSTRACT Embedded systems are becoming increasingly complex and more distributed. Cost and quality requirements necessitate reuse of the functional software components for multiple deployment architectures. An important step is the allocation of software components to hardware. During this process the differences between the hardware and application software architectures must be reconciled. In this paper we discuss an architecture driven approach involving model-based techniques to resolve these differences and integrate hardware and software components. The system architecture serves as the underpinning based on which distributed real-time components can be generated. Generation of various embedded system architectures using the same functional architecture is discussed. The approach leverages the following technologies – IME (Integrated Modeling Environment), the SAE AADL (Architecture Analysis and Design Language), and Ocarina. The approach is illustrated using the electronic
Raghav, GopalGopalswamy, SwaminathanRadhakrishnan, KarthikeyanDelange, JulienHugues, Jérôme
ABSTRACT With the increase in electric power on military ground vehicle platforms, electrically driven accessories are replacing existing hydraulic, belt, and gear-driven loads. Permanent Magnet Synchronous Machines (PMSM) are often selected to drive these accessories, and are under consideration for the main engine generator, due to their torque density and efficiency being among the highest available. To maximize the efficiency of a PMSM, accurate knowledge of its parameters is required across the entire operating range. Efficient control of the onboard electric drives will help reduce fuel consumption in the ground vehicle fleet. This paper presents the effects of iron saturation on the performance of a PMSM drive. Iron saturation depends on the amount of current injected into the motor and it restricts the amount of flux linkage that can be generated. PMSMs are controlled using a two axis space vector representation. Ideally, the control is decoupled, such that the flux linkage
Cintron-Rivera, Jorge G.Foster, Shanelle N.Zanardelli, Wesley G.Strangas, Elias G.
ABSTRACT Modern medium and heavy duty Commercial Off The Shelf (COTS) diesel engines take advantage of state-of-the-art technologies to deliver excellent performance while meeting the most stringent emissions legislation. While some of these technologies offer significant advantages in terms of engine efficiency, performance and weight versus traditional military engines, others are driven purely by the need to meet emissions standards. In order to successfully adapt these COTS engines for military use and fuel (JP-8), the emissions-only systems must be removed and the engine recalibrated for maximum efficiency. The downsized, turbocharged engine would enable a simultaneous improvement in engine weight, performance and efficiency in one of the DoD’s largest fleet of vehicles - High Mobility Multipurpose Wheeled Vehicle (HMMWV), when compared to the current configuration. This paper will illustrate how a modern diesel engine was quickly developed from COTS to military-ready
Johnson, Gustav
ABSTRACT A novel energy management strategy has been developed by AVL Powertrain Engineering, Inc. (PEI) that includes a unique power split and optimization approach and is used successfully for the FED BRAVO program. In this program, AVL is responsible for developing and delivering the full hybrid propulsion system integrated into the Fuel Efficient Demonstrator (FED) Bravo vehicle, designed by PRIMUS. This paper presents control system development and tuning using both simulations and vehicle testing carried out at multiple proving grounds. It summarizes important lessons learnt, in particular balancing fuel economy and drivability. It presents correlation results of AVL CRUISE simulations with data from vehicle testing at Chelsea Proving Grounds (CPG) and Aberdeen Proving Grounds (APG
Holtz, Jeffery BUppal, Faisal JCook, Andrew
ABSTRACT Automated systems can have a hard time completing complex tasks in a timely manner. When controlling a robot outside of autonomous mode, a good control device needs to give the user full control of the system while enabling the mission to be completed in a quick, accurate and efficient manner. This paper outlines the potential features of a puppet style control device and the lessons learned while implementing such a device
Rusbarsky, DavidGray, Jeremy P.Grebinoski, JimMor, Andrew B.
Items per page:
1 – 50 of 5569