Browse Topic: Robotics

Items (1,987)
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.
Hemming is an incremental joining technique used in the automotive industry, it involves bending the flange of an outer panel over an inner panel to join two sheet metal panels. Different hemming methods are available such as Press die hemming, Table-top hemming and Robot roller hemming. Robot roller hemming is superior to press hemming and tabletop hemming because of its ability to hem complex-shaped parts and is typically used in low-volume automotive production lines. For higher production volumes, such as 120 Jobs per Hour (JPH), press hem or tabletop hem is generally preferred. However, to achieve high-volume production from roller hemming method multi station setup is used. This static multi station setup can be configured into a Turntable setup. This new method eliminates the robot load and unload time at each station in the existing setup, resulting in a 40% increase in hemming robot utilization. Therefore, this process reduces the number of robots and the required floor space
Raju, GokulRoy, AmlanSahu, ShishirPalavelathan, Gowtham RajJagadeesh, NagireddiChava, Seshadri
Liebherr and Fortescue unveiled their first autonomous battery-electric T 264 haul truck at MINExpo 2024, garnering a steady stream of attendees eyeing and climbing on the giant machine. The truck is the culmination of nearly three years of development work and collaboration among the autonomy and zero-emission units of Liebherr and Fortescue. The T 264 electric hauler features a 3.2-MWh battery system, comprising eight sub-packs, developed by Fortescue Zero. Fortescue also developed a stationary fast-charging solution to support the new T 264. The charger will be available in both manual and robotic versions. An automated quick charger of up to 6 MW with two megawatt charging system (MCS) plugs can reportedly charge the current battery-electric T 264 in 30 minutes
Gehm, Ryan
ABSTRACT U.S. Army Combat Capabilities Development Command (CCDC) Ground Vehicle Systems Center (GVSC) has been managing and developing a variety of autonomous systems throughout its existence. Two of the most important from the past decade include the Autonomous Mobility Appliqué System (AMAS) developed by Lockheed Martin Corporation (LMC) and the Robotic Technology Kernel (RTK) developed by GVSC in collaboration with DCS Corp and Southwest Research Institute (SwRI). Rather than continuing to develop and maintain two separate autonomous software systems, GVSC has decided to integrate any capabilities that were unique to AMAS into RTK and devote efforts to developing RTK going forward. The goal of integrating AMAS into RTK is to leverage the best features of each system. The process of this integration involves multiple steps. This paper describes the historical and current efforts involved in the integration of AMAS into RTK. Citation: D. Pirozzo, J.P. Hecker, A. Dickinson, T
Pirozzo, DavidHecker, Joshua P.Dickinson, AlanSchulteis, TimRatowski, JeffTheisen, Bernard
ABSTRACT The Robotic Technology Kernel (RTK) is a government-owned library of reusable software modules based on the first generation Robotic Operating System (“ROS 1”) that can be formed into “autonomy stacks” for integration onto defense robotic platforms. RTK has been used to demonstrate autonomous ground vehicle capabilities spanning many programs and mission scenarios over the past five years. Future use of RTK is dependent, however, on migrating it to be compatible with the 2nd generation of ROS middleware (“ROS 2”) scheduled to replace ROS 1 in May, 2025. This paper summarizes the methodologies, systems, results, and lessons learned thus far from a project to migrate RTK to ROS 2 for the purpose of informing similar ongoing or future large software-centric activities within the ROS and defense robotics communities. A key conclusion is that a well-defined set of organizational practices and technical guidance can enable a large, heterogeneous team of developers from multiple
Boulet, MichaelDelGizzi, RyanLathrop, ScottLeahy, BrendanMontez, JakeRucinski, GarySpinola, MatthewThomasmeyer, WilliamTowler, Jerry
ABSTRACT The importance of hardening robotic and autonomous systems (RAS) considered for field deployment against cyber threats has been recognized by organizations across the Department of Defense (DoD). Among these needs is the ability to securely provide these modern military vehicles with software updates containing critical new functionality and security improvements. A secure update process and system for military RAS has been implemented building on a framework designed for the automotive industry. Demonstrations of the capabilities and mitigations against possible attacks on the update process will be performed on a RAS MRZR in a mock field environment. Citation: S. Pereira, C. Mott, D. Mikulski, “Secure Update Process For Robotic And Autonomous Systems,” In Proceedings of the Ground Vehicle Systems Engineering and Technology Symposium (GVSETS), NDIA, Novi, MI, Aug. 15-17, 2023
Pereira, SabrinaMott, CameronMikulski, Dariusz
ABSTRACT Future autonomous combat vehicles will need to travel off-road through poorly mapped environments. Three-dimensional topography may be known only to a limited extent (e.g. coarse height), but this will likely be noisy and of limited resolution. For ground vehicles, 3D topography will impact how far ahead the vehicle can “see”. Higher vantage points and clear views provide much more useful path planning data than lower vantage points and occluded views from trees and structures. The challenge is incorporating this knowledge into a path planning solution. When should the robot climb higher to get a better view or else continue moving along the shortest path predicted by current information? We investigated the use of Deep Q-Networks (DQN) to reason over this decision space, comparing performance to conventional methods. In the presence of significant sensor noise, the DQN was more successful in finding a path to the target than A* for all but one type of terrain. Citation: E
Martinson, EricPurman, BenDallas, Andy
ABSTRACT Modern robotic technologies enable the development of semiautonomous ground robots capable of supporting military field operations. Particular attention has been devoted to the robotic mule concept, which aids soldiers in transporting loads over rugged terrain. While existing mule concepts are promising, current configurations are rated for payloads exceeding 1000 lbs., placing them in the size and weight class of small cars and ATVs. These large robots are conspicuous by nature and may not successfully carry out infantry resupply missions in an active combat zone. Conversations with soldiers and industry professionals have spotlighted a need for a compact, lightweight, and low-cost robotic mule. This platform would ensure reliable last-mile delivery of critical supplies to predetermined rally points. We present a design for such a compact robotic mule, the µSMET. This versatile platform will be integrated with the Squad Multipurpose Equipment Transport (SMET), to ferry
Grenn, KatharinaAdam, CristianKleinow, TimothyMason, BrianSapunkov, OlegMuench, PaulLakshmanan, Sridhar
ABSTRACT The Soar Cognitive Architecture is a reasoning system that enables knowledge-rich, mission focused reasoning including integration of bottom-up, sensor-driven reasoning and top-down, context-driven reasoning, and more intelligent use of existing sensors. This reasoning is a combination of deliberate (e.g., planning) and reactive (e.g., hard-coded) behaviors. We are applying Soar on a current effort to (1) increase autonomy and (2) achieve equivalent or superior performance while controlling weight, energy, and costs
Marinier, RobertBechtel, RobertDallas, Andrew
ABSTRACT Main Battle Tanks (MBTs) remain a key component of most modern militaries. While the best way to ‘kill a tank’ is via the employment of another tank, matching enemy armor formations one-for one is not always possible. Light infantry lack organic armor and their shoulder launched anti-tank capabilities do not defeat the latest generation of MBTs. To compensate for this capability gap, the U.S. Army has employed precision guided anti-tank munitions, such as the “Javelin.” However, these are expensive to produce in quantity and require risking the forward presence of dismounted Soldiers to employ. Mine fields offer another option but are immobile once employed. The ‘Guillotine’ Attack System proposes to change the equation by pairing an AI enabled, adaptive unmanned delivery system with a shaped charge payload. Guillotine can loiter for hours, reposition itself to hunt for targets, and- when ready- deliver a precision shaped charge strike from the air. Citation: “The ‘Guillotine
Dooley, MatthewLacaze, Alberto
ABSTRACT The Department of Defense has identified the need for increased expeditionary, long range, and mobile capabilities to support standard logistics resupply, as well as the ability to perform logistics resupply in austere and special operations environments. The purpose of such a system is to quickly provide critical supplies to the Warfighter on the ground. In order to quickly get the supplies to the designated target location, a vertical take-off aircraft is used. Stratom has developed the eXpeditionary Robo-Platform (XR-P)™ which is a vertically inserted semi-autonomous robotic logistical vehicle designed to meet the demanding logistical needs of the warfighter. The XR-P will be able to carry, among other things, two standard pallets of 120mm rifled mortar rounds weighing 2700 pounds and have the capability to tow a trailer, all while meeting strict MV-22 cargo air certification requirements when fully loaded. By automating various aspects of the transport task of the resupply
Rosenblum, Mark
ABSTRACT The Army Operating Concept and the Cross Domain Maneuver Concept describe more capable Brigade Combat Teams that can operate semi-independently across wide areas on the future battlefield. Robotics and Autonomous Systems can increase capabilities of Brigade Combat Teams by increasing situational awareness, facilitating movement and maneuver, improving protection, extending a small unit’s area of operations, and sustaining the force with increased distribution, throughput, and efficiency. Army industry partners, in concert with Army labs, must provide the affordable technologies that can provide these autonomous and semi-autonomous operational capabilities to the future force. While acknowledging that there must be significant technology development to realize this vision, this concept paper aims to take a realistic look at enabling Brigade Combat Teams with third-offset capabilities by 2035
Nuckols, COL Willie T.Sadowski, RobertHarber, GaryBosscher, Paul
ABSTRACT Information is critical to successful deployment and operation of unmanned vehicles. The increasing use of unmanned vehicles in modern conflicts has substantially increased the strategic and tactical value of these vehicles and the information they gather. It is now common public knowledge that the video streams of some predator drones were unencrypted and militants were able to use cheap commercially available software to intercept these feeds. This is an example of security as an afterthought. Encryption and security are critical to unmanned systems and should be implemented early in the development process. This paper explores some of the issues related to encryption and security of unmanned vehicles and communication
Phillips, Ramie
ABSTRACT The objective is to develop a human-multiple robot system that is optimized for teams of heterogeneous robots control. A new human-robot system permits to ease the execution of remote tasks. An operator can efficiently control the physical multi-robots using the high level command, Drag-to-Move method, on the virtual interface. The innovative virtual interface has been integrated with Augmented Reality that is able to track the location and sensory information from the video feed of ground and aerial robots in the virtual and real environment. The advanced feature of the virtual interface is guarded teleoperation that can be used to prevent operators from accidently driving multiple robots into walls and other objects
Lee, SamHunt, ShawnCao, AlexPandya, Abhilash
ABSTRACT Off-road autonomous navigation poses a challenging problem, as the surrounding terrain is usually unknown, the support surface the vehicle must traverse cannot be considered flat, and environmental features (such as vegetation and water) make it difficult to estimate the support surface elevation. This paper will focus on Robotic Research’s suite of off-road autonomous planning and obstacle avoidance tools. Specifically, this paper will provide an overview of our terrain detection system, which utilizes advanced LADAR processing techniques to provide an estimate of the surface. Additionally, it will describe the kino-dynamic off-road planner which can, in real-time, calculate the optimal route, taking into account the support surface, obstacles sensed in the environment, and more. Finally, the paper will explore how these technologies have been applied to a wide variety of different robotic applications
Lacaze, AlbertoMottern, EdwardBrilhart, Bryan
ABSTRACT This paper reports on a prototype project to develop and mature a common, open, comprehensive, collaboratively developed, Government-owned, autonomy software architecture for ground robotic and autonomous systems (RAS). The prototype architecture, codenamed “SCION” promises the flexibility needed by the both the Government and industry research, development, testing, and engineering (RDT&E) communities to leverage reusable software and more rapidly innovate new capabilities; while ensuring the discipline and enabling the modularity required to develop RDT&E software structured to meet the software safety, cybersecurity, upgradeability, and other needs of RAS programs of record. Accordingly, program offices can adopt an acquisition strategy that requires compatibility with the de facto, military RAS standard, SCION architecture, while providing OEMs with baseline, SCION-compatible, GFE software (e.g. a future version of RTK). Such a strategy encourages optimal innovation
Thomasmeyer, WilliamJohn, Jon St.Martin, DaveMattes, Rich
ABSTRACT Gas metal arc pulse directed energy deposition (GMA-P DED) offers large-scale additive manufacturing (AM) capabilities and lower cost systems compared to laser or electron beam DED. These advantages position GMA-DED as a promising manufacturing process for widespread industrial adoption. To enable this “digital” manufacturing of a component from a computer-aided design (CAD) file, a computer-aided manufacturing (CAM) solver is necessary to generate build plans and utilize welding parameter sets based on feature and application requirements. Scalable and robot-agnostic computer-aided robotics (CAR) software is therefore essential to provide automated toolpath generation. This work establishes the use of Autodesk PowerMill Ultimate software as a CAM/CAR solution for arc-based DED processes across robot manufacturers. Preferred aluminum GMA-P DED welding parameters were developed for single-pass wide “walls” and multi-pass wide “blocks” that can be configured to build a wide
Canaday, J.Harwig, D.D.Carney, M.
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 In this paper, we will present the results of our efforts developing the Autonomy Kit for the Tank Automotive Research Development and Engineering Center’s (TARDEC) Autonomous Ground Resupply (AGR) Sustainment Operations (SO) program. Robotic Research, LLC was responsible for the design, build, and implementation of the “Autonomy Kit” for the AGR SO. The Autonomy Kit is designed to be a fault-tolerant, vehicle-agnostic applique kit that provides the hardware and software needed to perform higher-level autonomous driving and planning functions. In the first Increment, the main focus was developing a “Leader/Follower” capability, where a manned “Leader” vehicle could perform a mission with a number of unmanned “Followers” reproducing its trajectory, maintaining convoy constraints, and avoiding obstacles in the path
Schneider, AnneBecker, WilliamHoward, JohnCichosz, AlanTheisen, BernardConger, David
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 This paper surveys the state of autonomous systems and outlines a novel command and control (C2) paradigm that seeks to accommodate the environmental challenges facing warfighters and their robotic counterparts in the future. New interface techniques will be necessary to reinforce the paradigm that supports the C2 of multiple human-machine teams completing diverse missions as part of the Third Offset Strategy. Realizing this future will require a new approach to teaming and interfaces that fully enable the potential of independent and cooperative decision-making abilities of fully autonomous machines while maximizing the effectiveness of human operators on the battlefield
Michelson, W. Stuart
ABSTRACT Militaries worldwide are increasing their Research and Development (R&D) into RAS. Within the next 10 – 15 years RAS will play an active part in operations as the future battlefield becomes more complex. CRT technology can significantly reduce platform weight, fuel consumption, noise and vibration levels[1][2][3]. Armies and vehicle manufacturers have initiated a series of independent trials that confirmed the benefits and reliability of CRT on a tracked military vehicle. With the increase in RAS technologies comes a desire to utilize the proven benefits identified from manned platforms. The author’s objective is to highlight the findings of these trials[1][2][3] and provide substantiated data on how CRT technology can benefit RAS in terms of weight saving, whilst reducing maintenance and vibration. Citation: Fabien Lagier, Ing. MBA, “Composite Rubber Track (CRT) for Robotic & Autonomous System (RAS)”, In Proceedings of the Ground Vehicle Systems Engineering and Technology
Lagier, Fabien
ABSTRACT This paper presents the conceptual design, development, and implementation of the Robotic Technology Kernel (RTK) in a Polaris GEM e2 by the United States Military Academy's autonomy research team. RTK is the autonomous software suite of the U.S. Army Combat Capabilities Development Command Ground Vehicles Systems Center and to this point has primarily been used within off-road environments. The research team's primary objectives were to verify RTK's platform-agnostic characteristic by implementing the control software on a small, low-speed electric vehicle and augmenting the software to provide the additional capability of operating within an established infrastructure rule set. Citation: J. Cymerman, S. Yim, D. Larkin, K. Pegues, W. Gengler, S. Norman, Z. Maxwell, N. Gasparri, M. Pollin, C. Calderon, J. Angle, J. Collier, “Evolving the Robotic Technology Kernal to Expand Future Force Autonomous Ground Vehicle Capabilities,” In Proceedings of the Ground Vehicle Systems
Cymerman, JosephYim, SangLarkin, DominicPegues, KathrynGengler, WyattNorman, SamuelMaxwell, ZacharyGasparri, NicholasPollin, MaryCalderon, ClementAngle, JeremyCollier, Jaylen
ABSTRACT Presented are two designs for compact, low-profile UGVs with high cross-country mobility, intended for underbody operations with heavy manned vehicles. These UGVs are designed to remotely detect and assess combat damage incurred during combat operations, and analyze wear, leaks, and cracks, without the need for a human technician to be exposed to enemy fire, allowing crews to rapidly assess the conditions of their vehicles. Since robots required for underbody inspection would necessarily maintain a low, compact profile, they could also perform effective last-mile resupply in a contested environment, their small size allowing them to hide behind terrain and battlefield debris much more effectively than a heavy logistics robot. Naturally, a robotic vehicle that is capable of rapid underbody inspection of friendly vehicles or last-mile resupply could also be easily adapted as a combat platform to be used against enemy vehicles. Citation: A. Washington, et al., “Expendable Low
Washington, AnastasyaStempien, AndrewSchouster, RyanWilson, DrewRead, CallumSvoboda, GarretBurton, JaredPendergrass, JacobYoung, FreddieBennett, JacobSapunkov, Oleg B.
ABSTRACT The utilization of model-based systems engineering (MBSE) is a key enabler for high quality system design and application of Modular Open Systems Approach (MOSA) principles. The Autonomous Ground Vehicle Reference Architecture (AGVRA) provides meta-models, architectural guidelines, best practices, and a library of reusable model content for the Army Robotics and Autonomous Systems (RAS) community to facilitate the MBSE development of autonomous systems. This paper provides a summary of AGVRA’s models, detailing the categories of model elements along with their overall utility, and describes key applications of AGVRA currently being utilized across the DoD. The applications of the AGVRA MBSE work products are contributing to high quality outcomes in RAS systems, providing new and improved functional and operational autonomous ground vehicle capability. Citation: C. Cheung, S. Griffith, L. Wells, D. Gregory, M. Moore, M. Johannes, D. Hetherington, J. Walters, S. Kang
Cheung, CalvinGriffith, ShannonWells, LarisaGregory, DouglasMoore, MichaelJohannes, MarkHetherington, DavidWalters, JoshuaKang, Sean
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 Acceptance testing is considered a final stage of validation, and performing acceptance tests of an actual UGV system can be expensive and time-consuming. Therefore, this paper discusses simulation based acceptance testing for UGVs, which can significantly reduce the time and cost of the acceptance test. In this paper, both dynamic and static simulation models are developed, and the results from these simulations show that the static simulation can be used, rather than the more complex dynamic simulation, because of the slow operating speed of UGVs. This finding improves the development efficiently at the simulation model development phase. In addition, the developed simulation models provide a better understanding of the UGV failure modes. The static simulations can determine the required joint motor torques for various UGV loadings and maneuvers and provide data for the full range of operating motion. Specifically, given threshold joint torque value, the safe operating range
Lee, Hyo JongJin, Jionghua (Judy)Ulsoy, A. Galip
ABSTRACT Robot path-planning is a central task for navigation and most path-planners perform well in mapped environments with explicit obstacle boundaries. However, many obstacle fields are better defined by the probability of obstacles and obstacle geometries rather than by explicit locations. Few tools and data structures exist, other than repeated simulations, to predict robot mobility in these situations. Previously, it was shown that geometric obstacle properties could be used to estimate properties of paths routing around these obstacles, looking only at maps and avoiding the task of path planning [1]. This required knowing obstacle geometries relative to travel direction. This work presents a method for representing obstacle geometry, at arbitrary orientations and positions, and therefore a probabilistic model for determining if space near an obstacle is occupied. This paper explains the theory behind this method, uses this method to calculate the portion of a straight path
Harnett, Stephen J.Brennan, SeanReichard, KarlPentzer, Jesse
ABSTRACT Modelling and simulation together with well-defined development processes have become key approaches for creating high quality, reliable consumer products. This is particularly true for passenger cars and trucks. In parallel, the evolving area of mobile ground robotics has found a variety of useful applications over the past twenty years: helping users accomplish tasks in hospitals, warehouses, factories, and on the battlefield. While many of these robotic systems have proven highly valuable, many also lack the mobility, flexibility, reliability and/or robustness desired by the users. In this paper, the authors posit that these non-idealities are in part the result of underutilization of modelling and simulation and an appropriate processes to implement them. This underutilization is partially due to a historical lack of appropriate M&S tools. Recently, however, a new generation of real-time, highly visualized, interactive tools has emerged that has the potential to make a
Rohde, Mitchell M.Rohde, Steve M.
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 As unmanned ground vehicle technology matures and autonomous platforms become more common, such platforms will invariably be in close proximity to one another both in formation and independently. With an increasingly crowded field, the risk of collisions between these platforms grows, and with it the need for path deconfliction. This paper presents two complementary technological developments to this end: a pipeline for affirmatively identifying and classifying dynamic objects, e.g., vehicles or pedestrians; and a pipeline for preventing collisions with such objects. The efficacy of these techniques is demonstrated in simulation, and validation on robotic platforms will be undertaken in the near future. Citation: Matthew Grogan, “Dynamic Object Collision Avoidance for Autonomous Multi-Vehicle Systems in the Robotic Technology Kernel”, In Proceedings of the Ground Vehicle Systems Engineering and Technology Symposium (GVSETS), NDIA, Novi, MI, Aug. 13-15, 2019
Grogan, Matthew
ABSTRACT All-Terrain off-road environments are the next frontier for autonomous vehicles to overcome. However, there are many obstacles in the way of this goal. Artificial intelligence has proven to be an invaluable asset in developing perception and path planning systems capable of overcoming these obstacles, but these AI systems fundamentally rely on the availability of data related to the operational environment in order to succeed. Currently, there is no unifying ontology for this data. This has inhibited progress on training AI by reducing the availability of cross-integrable datasets. We present ATLAS: A labeling ontology composed of over 200 labels specifically designed to encompass all-terrain off-road environments. This ontology will lay the ground work for creating scalable standardized all terrain off-road data and will enable future AI by providing an expansive and well labeled ontology that can push the field of autonomous vehicles to new heights. Citation: W. Smith, D
Smith, WestonGrabowsky, DavidMikulski, Dariusz
ABSTRACT Currently, many small Army ground robots have mobility configurations containing tracks with sets of dual or quad flipper configurations. Many of these robots include the iRobot PackBot, Talon, and Dragon Runner. While the preceding robotic designs have allowed these robots to navigate over obstacles and across low traction environments, an increasing need for agile robotic platforms in complex environments involving subterranean and urban structure missions will be critical in the future. Therefore, a new mobility system for dismounted ground robots is being researched to aid in the exploration, mapping, and identification by targets of interest for dense urban environments. This paper discusses one possibility for a new small CRS-I sized ground robot mobility system that is inspired by the rocker-bogie designs of the Mars rover systems. Citation: Timothy Pietrzyk, Ty Valascho “Robotic Rocker-Bogie Mechanism Prototype”, In Proceedings of the Ground Vehicle Systems Engineering
Pietrzyk, TimothyValascho, Ty
ABSTRACT Multi-robot bounding overwatch requires timely coordination of robot team members. Symbolic motion planning (SMP) can provide provably correct solutions for robot motion planning with high-level temporal logic task requirements. This paper aims to develop a framework for safe and reliable SMP of multi-robot systems (MRS) to satisfy complex bounding overwatch tasks constrained by temporal logics. A decentralized SMP framework is first presented, which guarantees both correctness and parallel execution of the complex bounding overwatch tasks by the MRS. A computational trust model is then constructed by referring to the traversability and line of sight of robots in the terrain. The trust model predicts the trustworthiness of each robot team’s potential behavior in executing a task plan. The most trustworthy task and motion plan is explored with a Dijkstra searching strategy to guarantee the reliability of MRS bounding overwatch. A robot simulation is implemented in ROS Gazebo to
Zheng, HuanfeiSmereka, Jonathon M.Mikulski, DariuszRoth, StephanieWang, Yue
ABSTRACT This paper presents a Gaussian process model of terrain slope for use in a GPS-free localization algorithm for ground robots operating in unstructured terrain. A wheeled skid-steer robot is used to map the terrain slope within an operational area of interest. The slope data is sampled sparsely and used as training data for a Gaussian process model with a two-dimensional input. Three different covariance functions for the Gaussian process model are evaluated with hyperparameters selected through maximizing the log marginal likelihood. The resulting Gaussian process model is used in the measurement update function of a localization particle filter to generate expected slope values at particle positions. Preliminary localization testing shows sub-ten meter accuracy with no initial knowledge of position. However, the overall performance of the filter is highly dependent on the variability of the terrain that the robot traverses. Citation: J. Pentzer, K. Reichard, “Gaussian Process
Pentzer, JesseReichard, Karl
ABSTRACT Situations exist that require the ability to preposition a basic level of energy infrastructure. Exploring and developing the arctic’s oil potential, providing power to areas damaged by natural or man-made disasters, and deploying forward operating bases are some examples. This project will develop and create a proof-of-concept electric power prepositioning system using small autonomous swarm robots each containing a power electronic building block. Given a high-level power delivery requirement, the robots will self-organize and physically link with each other to connect power sources to storage and end loads. Each robot mobile agent will need to determine both its positioning and energy conversion strategy that will deliver energy generated at one voltage and frequency to an end load requiring a different voltage and frequency. Although small-scale robots will be used to develop the negotiation strategies, scalability to existing, large-scale robotic vehicles will be
Weaver, Wayne W.Mahmoudian, NinaParker, Gordon G.
ABSTRACT This research proposes a human-multirobot system with semi-autonomous ground robots and UAV view for contaminant localization tasks. A novel Augmented Reality based operator interface has been developed. The interface uses an over-watch camera view of the robotic environment and allows the operator to direct each robot individually or in groups. It uses an A* path planning algorithm to ensure obstacles are avoided and frees the operator for higher-level tasks. It also displays sensor information from each individual robot directly on the robot in the video view. In addition, a combined sensor view can also be displayed which helps the user pin point source information. The sensors on each robot monitor the contaminant levels and a virtual display of the levels is given to the user and allows him to direct the multiple ground robots towards the hidden target. This paper reviews the user interface and describes several initial usability tests that were performed. This research
Lee, SamLucas, Nathan P.Cao, AlexPandya, AbhilashEllis, R. Darin
ABSTRACT The main goal of this paper is to report recent progress on two example projects supported within the Ground Robotics Reliability Center (GRRC), a TARDEC supported research center headquartered at the University of Michigan. In the first project, the concept of Velocity Occupancy Space (VOS), a new navigation algorithm that allows a robot to operate using only a range finding sensor in an unknown environment was developed. This method helps a mobile robot to avoid stationary and moving obstacles while navigating towards a target. The second project highlighted is related to energy and power requirement of mobile robots. Hazardous terrains pose challenges to the operation of mobile robots. To enable their safe and efficient operations, it is necessary to detect the terrain type and to modify operation and control strategies in real-time. A research project supported by GRRC has developed a closed-form wheel-soil model. Computational efficiency of this model is improved by
Peng, HueiUlsoy, A. Galip
ABSTRACT This paper presents a new terrain traversability mapping method integrated into the Robotic Technology Kernel (RTK) that produces ground slope traversability cost information from LiDAR height maps. These ground slope maps are robust to a variety of off-road scenarios including areas of sparse or dense vegetation. A few simple and computationally efficient heuristics are applied to the ground slope maps to produce cost data that can be directly consumed by existing path planners in RTK, improving the navigation performance in the presence of steep terrain. Citation: J. Ramsey, R. Brothers, J. Hernandez, “Creation of a Ground Slope Mapping Methodology Within the Robotic Technology Kernel for Improved Navigation Performance,” In Proceedings of the Ground Vehicle Systems Engineering and Technology Symposium (GVSETS), NDIA, Novi, MI, Aug. 16-18, 2022
Ramsey, JacksonBrothers, RobertHernandez, Joseph
Abstract RedRAVEN is a pioneered autonomous robot utilizing the innovative Linked-Bogie dynamic frame, which minimizes platform tilt and movement, and improves traction while maintaining all the vehicle’s wheels in contact with uneven surfaces at all times. Its unique platform design makes the robot extremely maneuverable since it allows the vehicle’s horizontal center of gravity to line up with the center of its differential-drive axle. Where conventional differential-drive vehicles use one or more caster wheels either in front or in the rear of the driving axle to balance the vehicle’s platform, the Linked-Bogie design utilizes caster wheels both in the front and in the rear of the driving axle. Without using any springs or shock absorbers, the dynamic frame allows for compensation of uneven surfaces by allowing each wheel to move independently. The compact and lightweight ground vehicle also features a driving-wheel neutralizing mechanism, a rigid aluminum frame, and a translucent
Mekhtarian, AraHorvath, JosephLin, C.T.
Abstract On the Mobile Detection Assessment Response System (MDARS) production program, General Dynamics Robotics Systems (GDRS) and International Logistics Systems (ILS), are working with the US Army’s Product Manager – Force Protection Systems (PM-FPS) to reduce system costs throughout the production lifecycle. Under this process, GDRS works through an Engineering Change Proposal (ECP) process to improve the reliability and maintainability of subsystem designs with the goal of making the entire system more producible at a lower cost. In addition, GDRS recommends substitutions of Government requirements that are cost drivers with those that reduce cost impact but do not result in reduced capability for the end user. This paper describes the production lifecycle process for the MDARS system and recommends future considerations for fielding of complex autonomous robotic systems
Frederick, BrianVirtz, PaulGrinnell, Michal
ABSTRACT Autonomous robots can maneuver into dangerous situations without endangering Soldiers. The Soldier tasked with the supervision of a route clearing robot vehicle must be located beyond the physical effect of an exploding IED but close enough to understand the environment in which the robot is operating. Additionally, mission duration requirements discourage the use of low level, fatigue inducing, teleoperation. Techniques are needed to reduce the Soldier’s mental stress in this demanding situation, as well as to blend the high level reasoning of a remote human supervisor with the local autonomous capability of a robot to provide effective, long term mission performance. GDRS has developed an advanced supervised autonomy version of its Robotics Kit (GDRK) under the Robotic Mounted Detection System (RMDS) program that provides a cost effective, high-utility automation solution that overcomes the limitations and burden of a purely teleoperated system. GDRK is a modular robotic
Frederick, BrianRodgers, DanielMartin, JohnHutchison, John
ABSTRACT Robotic Wingman (RW) is an advanced unmanned systems concept integrated with current operational tactics to enhance the force effectiveness of combat vehicle platoon and substantially enhance the survivability of manned vehicles in combat operations. Two approaches to RW; reconfiguring common fleet and new/unique platoon vehicles. Each approach has its advantages in wingman operations. This paper will discuss the approaches, the required technologies and program implementations. RW combat effectiveness and advances in force survivability will be assessed and discussed in both approaches. Advanced technology including sensors, autonomy, communications and automated behaviors will enable the RW to look, move, and act like companion manned vehicle. For its optimum effectiveness, the RW wants to cause the enemy to engage it first. The automation of the manned fleet to implement and achieve unmanned system performance similar to manned operations and is required to fool the enemy
Lane, JerryAntenori, FrankDallas, Andrew
ABSTRACT This paper addresses the Program Management Office’s perspective of the robotic technology needs required to meet the capability gaps identified by the Warfighter. The objective is to relay these needs to the Science and Technology (S&T) community and industry in order to guide their investment dollars in the right direction. The Robotic Systems Joint Project Office (RS JPO) has been working closely with the Tank Automotive Research, Development, and Engineering Center (TARDEC) to establish near, mid and far term needs for robotic technologies. The hope is to communicate those needs to successfully steer the robotic research and development efforts to meet the capabilities most needed by our Warfighters
Brennan, AdamHart, Aaron D.Saxon, NancyRappold, RobertMazzara, Mark
ABSTRACT Although bio-inspired legged robots have advantageous mobility, they can be very inefficient. Their intrinsic walking mobility is sometimes outweighed by the inefficiency of their drive-train. Some of these inefficiencies are due to collision losses, but they are also due to suboptimal powering schemes. This paper addresses the powering schemes and seeks to clearly delineate an optimal solution to powering the walking motion of a two-legged or biped walker. We examine a simplified model of locomotion called the “rocket car” to extract the meaningful parameters that affect time and energy cost. Using Pontryagin’s Maximum Principle, we dissect the cost function, the state equation, co-state equation, and control input constraints to describe the optimal control. The result of the paper shows a “bang-off” control, and we describe the “coasting line” between these extremes. It is not possible to find a complete closed-form solution for the problem, and numerical methods, such as
Muench, PaulCheok, Ka C
ABSTRACT There is a dire need for low-cost mobile robots for the purpose of mine detection and disposal. Countries with low gross domestic product (GDP) and infected with landmines generally cannot support expensive high-tech solution. A de-mining mobile robot has to be cost effective compared to local labor costs. Presently commercially available mobile robots consist of mainly custom made parts. The design and manufacturing of such parts make the robots very expensive. This paper describes how careful selection of commercially available parts leads to reducing the development time and costs for a demining robot while ensuring its reliability, convenient operation and application domain. An actual example of how a low cost mine detection robot was successfully integrated within two months is outlined
Pajaziti, A.Cheok, K.Radovnikovich, M.Baftiu, I.Godo, G.
ABSTRACT This paper describes novel experimental methods aimed at understanding the fundamental phenomena governing the motion of lightweight vehicles on dry, granular soils. A single-wheel test rig is used to empirically investigate wheel motion under controlled wheel slip and loading conditions on sandy, dry soil. Test conditions can be designed to replicate typical field scenarios for lightweight robots, while key operational parameters such as drawbar force, torque, and sinkage are measured. This test rig enables imposition of velocities, or application of loads, to interchangeable running gears within a confined soil bin of dimensions 1.5 m long, 0.7 m wide, and 0.4 m deep. This allows testing of small-scale wheels, tracks, and cone or plate penetrators. Aside from standard wheel experiments (i.e., measurements of drawbar force, applied torque, and sinkage during controlled slip runs) two additional experimental methodologies have been developed. The first relies on high-speed
Senatore, CarmineMacLennan, JamieJayakumar, ParamsothyWulfmeier, MarkusIagnemma, Karl
Items per page:
1 – 50 of 1987