SEARCH · Engineering Papers

Results for “agent based simulation”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 253 records · Page 14

All sources NASA NTRS DOE OSTI

DOE OSTI2024

A novel digital lifecycle for Material‐Process‐Microstructure‐Performance relationships of thermoplastic olefins foams manufactured via supercritical fluid assisted foam injection molding

Abstract This research significantly enhances the applicability of thermoplastic olefins (TPOs) in the automotive industry using supercritical N 2 as a physical foaming agent, effectively addressing the limitations of traditional chemical agents. It merges experimental results with simulations to establish detailed material‐process‐microstructure‐performance (MP2) relationships, targeting 5–20% weight reductions. This innovative approach labeled digital lifecycle (DLC) helps accurately predict tensile, flexural, and impact properties based on the foam microstructure, along with experimentally demonstrating improved paintability. The study combines process simulations with finite element models to develop a comprehensive digital model for accurately predicting mechanical properties. Our findings demonstrate a strong correlation between simulated and experimental data, with about a 5% error across various weight reduction targets, marking significant improvements over existing analytical models. This research highlights the efficacy of physical foaming agents in TPO enhancement and emphasizes the importance of integrating experimental and simulation methods to capture the underlying foaming mechanism to establish material‐process‐microstructure‐performance (MP2) relationships. Highlights Establishes a material‐process‐microstructure‐performance (MP2) for TPO foams Sustainably produces TPO foams using supercritical (ScF) N 2 with 20% lightweighting Shows enhanced paintability for TPO foam improved surface aesthetics Digital lifecycle (DLC) that predicts both foam microstructure and properties DLC maps process effects & microstructure onto FEA mesh for precise prediction

Engineering↗

NASA NTRS2010

Shorebird Migration Patterns in Response to Climate Change: A Modeling Approach

The availability of satellite remote sensing observations at multiple spatial and temporal scales, coupled with advances in climate modeling and information technologies offer new opportunities for the application of mechanistic models to predict how continental scale bird migration patterns may change in response to environmental change. In earlier studies, we explored the phenotypic plasticity of a migratory population of Pectoral sandpipers by simulating the movement patterns of an ensemble of 10,000 individual birds in response to changes in stopover locations as an indicator of the impacts of wetland loss and inter-annual variability on the fitness of migratory shorebirds. We used an individual based, biophysical migration model, driven by remotely sensed land surface data, climate data, and biological field data. Mean stop-over durations and stop-over frequency with latitude predicted from our model for nominal cases were consistent with results reported in the literature and available field data. In this study, we take advantage of new computing capabilities enabled by recent GP-GPU computing paradigms and commodity hardware (general purchase computing on graphics processing units). Several aspects of our individual based (agent modeling) approach lend themselves well to GP-GPU computing. We have been able to allocate compute-intensive tasks to the graphics processing units, and now simulate ensembles of 400,000 birds at varying spatial resolutions along the central North American flyway. We are incorporating additional, species specific, mechanistic processes to better reflect the processes underlying bird phenotypic plasticity responses to different climate change scenarios in the central U.S.

Smith, James A.↗

NASA NTRSDate not supplied

A Distributed Simulation-to-Flight Framework to Support Investigating Trust/Trustworthiness in Multi-Agent Systems

As autonomous systems continue to grow both in use and complexity, the necessity for robust and extensible simulation-to-flight methods is paramount for establishing an effective architecture for autonomous systems. A fundamental objective of the ATTRACTOR (Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability) project was to design and develop a distributed mixed-reality simulation environment to begin establishing a basis for certification of autonomous systems via research into trust and trustworthiness. In this paper, we present an autonomous systems architecture and development framework paired with a persistent distributed modeling and simulation environment for test and evaluation of autonomous systems. The Autonomous Entity Operations Network (AEON) framework enables autonomous system development with an easily extensible collection of libraries and plug-n-play nodes facilitated by the Data Distribution Service (DDS) communication protocol standard. The Baseline Environment for Autonomous Modeling (BEAM) simulation environment is a distributed mixed-reality Unity™-based environment built around the same DDS communication paradigm allowing for easy integration with AEON-based autonomous applications. They were designed under ATTRACTOR in order to measure and establish trustworthiness and trust in single- and multi-agent human-machine systems whether these machines are fixed-wing general aviation, rotary-wing Unmanned Aerial Vehicles (UAVs), ground rovers, or even spacecraft. Together AEON and BEAM enable sim-to-flight with minimal configuration changes. By using AEON and BEAM, source code that runs in simulation ports directly to hardware and has successfully flown in the lab and in the National Airspace System (NAS) at NASA LaRC many times over the lifetime of ATTRACTOR.

Benjamin N Kelley↗

NASA NTRSDate not supplied

A Distributed Simulation-to-Flight Framework to Support Investigating Trust/Trustworthiness in Multi-Agent Systems

Benjamin N Kelley↗

DOE OSTI2026

Optimal CO 2 storage management considering safety constraints in multi-stakeholder multi-site GCS projects: A Markov game perspective

Geological carbon storage (GCS) projects could involve a diverse array of stakeholders or players from public, private, and regulatory sectors, each with different objectives and responsibilities. Given the complexity, scale, and long-term nature of GCS operations, determining whether individual stakeholders can independently optimize their interests — or whether collaborative coalition agreements are needed — remains a central question for effective GCS project planning and management. To access large, high-quality storage resources, future GCS deployment may increasingly occur in geologically connected sites, where shared geological features such as pressure space and reservoir pore capacity can lead to competitive behavior among stakeholders. In this work, we propose a paradigm based on Markov games to quantitatively investigate how different coalition structures affect the goals of stakeholders. We frame this multi-stakeholder multi-site problem as a multi-agent reinforcement learning problem with safety constraints. Our approach enables agents to learn optimal strategies while complying with safety regulations. We present an example where multiple operators are injecting CO 2 into their respective project areas in a geologically connected basin. To address the high computational cost of repeated simulations of high fidelity models, a previously developed surrogate model based on the Embed-to-Control (E2C) framework is employed. Our results demonstrate the effectiveness of the proposed framework in addressing optimal management of CO 2 storage when multiple stakeholders with different objectives and goals are involved.

58 GEOSCIENCES↗

NASA NTRSDate not supplied

AMMPER: a user-friendly agent-based model that recapitulates simple metabolic responses of yeast to deep-space radiation

For humans venturing to deep space, radiation exposure poses a major health risk. Fundamental research into the biological effects of space radiation are essential for enabling exploration, and the first experimental organisms we send to deep space will be microbial. Yet there are many ways in which microorganisms are likely to experience the effects of high-energy particle radiation (such as Galactic Cosmic Rays) differently from multicellular animals, partly due to the simple fact that microbes are small and unicellular-- less likely to get hit in the first place, and less likely to communicate damage between cells. Computational modeling can aid in designing experiments and predicting the biological effects of radiation, but thus far particle radiation models have not focused on microbes. Here we present the latest developments in AMMPER, the Agent-based Model for Microbial Populations Exposed to Radiation. Originally written in 2021, AMMPER is a Python-based model that incorporates radiation track data from NASA's RITRACKS software and simulates the growth, damage, and death of yeast cells in 3D. It is now freely available as an open-source package on NASA's GitHub repository. Recent improvements include the ability to simulate the dynamics of alamarBlue, a color-changing redox dye commonly used to track metabolic activity in microbial spaceflight experiments. We demonstrate that a simple blue-pink-clear transition model is able to recapitulate key features observed in empirical data from ground studies. AMMPER also includes a new graphical user interface and introductory tutorial to facilitate ease of use by a wider audience. AMMPER can help us to understand how spatially heterogeneous particle radiation damage at the single-cell level can translate to growth differences at the population level, ultimately allowing us to better interpret experiments using microbes as model organisms and how well their results apply to humans.

yeast↗

NASA NTRSDate not supplied

Agent-based modeling of microbes in space

Space is tough on organisms. Microorganisms traveling to space experience stress from environmental features such as ionizing radiation and lack of normal microgravity; however, much remains unknown about the mechanisms by which those environmental features affect microbial physiology. Microbes experience changes in gravity not directly but rather through changes in their fluid environment, and deep-space particle radiation causes cell damage that is complex but rare. Computational modeling at the single-cell level (agent-based modeling) can allow us to probe the spatially heterogeneous processes that characterize space stresses, to gain insight into the relationships of microbial cells with their environments and with each other. Here we present two software packages for simulating microbial population dynamics in space conditions: CAMDLES and AMMPER. Microbes growing in liquid culture medium in the microgravity of an orbital space station experience a quiescent, poorly-mixed fluid environment. CAMDLES (CFD-DEM Artificial Microgravity Developments for Living Ecosystem Simulation) simultaneously simulates biological, chemical, and mechanical processes to predict microbial ecological dynamics in microgravity, and in the rotating culture vessels used to create an artificial microgravity environment in the lab. Initial results demonstrate that the growth of a cross-feeding microbial consortium, dependent on the exchange of soluble metabolites, is sensitive to the initial spatial distribution of cells, and grows differently in real versus artificial microgravity. Microbial populations exposed to deep-space radiation experience spatially and temporally heterogeneous damage from the traversal of high-energy particles. AMMPER (Agent-Based Model for Microbial Populations Exposed to Radiation) pairs a 3d model of energy deposition along a radiation particle track with a microbial population growth and damage model to predict the effects of localized radiation damage on population-level responses. It includes a user-friendly graphical interface. AMMPER results agree with experimental data indicating that indirect effects of radiation (reactive oxygen species generation, metabolic impairment) have a greater impact on microorganisms than direct effects (DNA damage).

Jessica A Lee↗

NASA NTRS2022

Agent-Based Modeling of Microbes in Space

Space is tough on organisms. Microorganisms traveling to space experience stress from environmental features such as ionizing radiation and lack of normal gravity, and much remains unknown about the mechanisms by which those environmental features affect microbial physiology. Microbes experience changes in gravity not directly but rather through changes in their fluid environment, and deep-space particle radiation causes cell damage that is complex but rare. Computational modeling at the single-cell level (agent-based modeling) can allow us to probe the spatially heterogeneous processes that characterize space stresses, to gain insight into the relationships of microbial cells with their environments and with each other. Here we present two software packages for simulating microbial population dynamics in space conditions: CAMDLES and AMMPER. Microbes growing in liquid culture medium in the microgravity of an orbital space station experience a quiescent, poorly-mixed fluid environment. CAMDLES (CFD-DEM Artificial Microgravity Developments for Living Ecosystem Simulation) simultaneously simulates biological, chemical, and mechanical processes to predict microbial ecological dynamics in microgravity, and in the rotating culture vessels used to create an artificial microgravity environment in the lab. Initial results demonstrate that the growth of a cross-feeding microbial consortium, dependent on the exchange of soluble metabolites, is sensitive to the initial spatial distribution of cells, and grows differently in real versus artificial microgravity. Microbial populations exposed to deep-space radiation experience spatially and temporally heterogeneous damage from the traversal of high-energy particles. AMMPER (Agent-Based Model for Microbial Populations Exposed to Radiation) pairs a 3d model of energy deposition along a radiation particle track with a microbial population growth and damage model to predict the effects of localized radiation damage on population-level responses. It includes a user-friendly graphical interface. AMMPER growth curves recapitulate experimental results, and allow comparison between direct effects (DNA damage) and indirect effects (reactive oxygen species generation, metabolic impairment) of radiation.

microbiology↗

NASA NTRS2013

Unified Simulation and Analysis Framework for Deep Space Navigation Design

As the technology that enables advanced deep space autonomous navigation continues to develop and the requirements for such capability continues to grow, there is a clear need for a modular expandable simulation framework. This tool's purpose is to address multiple measurement and information sources in order to capture system capability. This is needed to analyze the capability of competing navigation systems as well as to develop system requirements, in order to determine its effect on the sizing of the integrated vehicle. The development for such a framework is built upon Model-Based Systems Engineering techniques to capture the architecture of the navigation system and possible state measurements and observations to feed into the simulation implementation structure. These models also allow a common environment for the capture of an increasingly complex operational architecture, involving multiple spacecraft, ground stations, and communication networks. In order to address these architectural developments, a framework of agent-based modules is implemented to capture the independent operations of individual spacecraft as well as the network interactions amongst spacecraft. This paper describes the development of this framework, and the modeling processes used to capture a deep space navigation system. Additionally, a sample implementation describing a concept of network-based navigation utilizing digitally transmitted data packets is described in detail. This developed package shows the capability of the modeling framework, including its modularity, analysis capabilities, and its unification back to the overall system requirements and definition.

Anzalone, Evan↗

DOE OSTI2022

Mucus-Inspired Tribology, a Sticky Yet Flowing Hydrogel

The mucus blanket can trap foreign particles before they enter the lungs, while at the same time, it flows up to remove these particles. This manifests the dual nature of mucus: sticky, on one hand, and fluid, on the other. Inspired by this function of mucus in the lungs, we designed a mucus simulant which emulates this dual nature. While many existing mucus simulants do not target bioadhesion particularly, poly(vinyl alcohol) (PVA)-based simulants make an exception. Despite their bioadhesion tendency, unlike mucus, they do not gelate. In this study, we added a physical cross-linking agent to PVA in order to add the gelation aspect and to better represent mucous properties. We show that the resultant mucus simulant develops into two regions: a highly sticky region near the surface of a foreign object (we used hydrophobized silicon to mimic the foreign object) and a fluid region far away from that surface. We show that the sticky part can slide past the less sticky part, while the foreign object is stuck to it. However, this mechanism changes with time. At short gelation times, this tendency to separate into two parts is enhanced and the foreign object remains stuck, while the rest of the gel flows. With time, the force required to allow the sticky part to slide over the fluid part is further reduced. However, if the gelation is allowed to proceed for even longer times without disturbance, the force required to slide the two parts past each other increases and the separation between the two parts is inhibited. The hydrogel becomes a sticky goo, which requires a higher force to move or unclog if placed in a duct (much like what happens with mucus in the tracheal duct). We explain the physics of our findings in terms of a competition between the tendency of the polymer to form a gel network and the tendency of the polymer to adsorb onto the foreign object.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2022

Simulation-Based Model for Facility-Scale Eagle Presence Mapping

This talk presents the recent progress in building a predictive movement model for predicting conflict between soaring raptors and wind turbines. In particular, it details the recently developed numerical tool called Stochastic Soaring Raptor Simulator for simulating updraft-subsidized paths for soaring raptors through variety of wind conditions and the associated directional intent.

agent-based model↗

DOE OSTI2026

Learning to Trigger: Reinforcement Learning at the Large Hadron Collider

High-throughput scientific facilities such as the Large Hadron Collider depend on real-time event filtering (\textit{triggering}) under tight constraints on bandwidth, latency, and storage. In practice, trigger menus are largely static and hand-tuned and can become suboptimal as detector conditions, pileup, and background composition drift over time. We cast online threshold tuning as a sequential decision-making problem: a reinforcement learning agent ingests streaming summaries of recent rates and signal-sensitive features and updates trigger thresholds to maximize signal efficiency while tracking a target background rate within a tolerance band. We adapt Group-Filtered Policy Optimization (GFPO) to streaming control and introduce two variants (GFPO-F, GFPO-FR) that enforce background rate feasibility during training. On a benchmark that emulates realistic collider operation, we study two representative triggers: a total transverse energy ($H_{T}$) trigger sensitive to pileup variation, and an anomaly-detection (AD) trigger based on reconstruction loss for rare or non-standard signatures. On Monte Carlo streams, our agent increases the fraction of in-tolerance time intervals by 48% ($H_T$) and 28% (AD), with a cumulative gain of up to 2% in signal efficiency on those in-tolerance intervals. Transferring from simulation to \emph{real} collision data (CMS Run 283408), the same agent, without fine-tuning, achieves a 56% ($H_T$) and 28% (AD) in-tolerance improvement over baselines, with further signal-efficiency gain on both triggers. To our knowledge, this is the \emph{first} demonstration of RL-based trigger control on real Large Hadron Collider collision data. Code is available at https://github.com/Zixind/GFPO_LHC (see repo for details).

Ding, Zixin [Chicago U.]↗

NASA NTRS2009

Workflow Agents vs. Expert Systems: Problem Solving Methods in Work Systems Design

During the 1980s, a community of artificial intelligence researchers became interested in formalizing problem solving methods as part of an effort called "second generation expert systems" (2nd GES). How do the motivations and results of this research relate to building tools for the workplace today? We provide an historical review of how the theory of expertise has developed, a progress report on a tool for designing and implementing model-based automation (Brahms), and a concrete example how we apply 2nd GES concepts today in an agent-based system for space flight operations (OCAMS). Brahms incorporates an ontology for modeling work practices, what people are doing in the course of a day, characterized as "activities." OCAMS was developed using a simulation-to-implementation methodology, in which a prototype tool was embedded in a simulation of future work practices. OCAMS uses model-based methods to interactively plan its actions and keep track of the work to be done. The problem solving methods of practice are interactive, employing reasoning for and through action in the real world. Analogously, it is as if a medical expert system were charged not just with interpreting culture results, but actually interacting with a patient. Our perspective shifts from building a "problem solving" (expert) system to building an actor in the world. The reusable components in work system designs include entire "problem solvers" (e.g., a planning subsystem), interoperability frameworks, and workflow agents that use and revise models dynamically in a network of people and tools. Consequently, the research focus shifts so "problem solving methods" include ways of knowing that models do not fit the world, and ways of interacting with other agents and people to gain or verify information and (ultimately) adapt rules and procedures to resolve problematic situations.

Clancey, William J.↗

DOE OSTI2023

A Generalization of Threshold-Based and Probability-Based Models of Information Diffusion

Diffusion of information through complex networks is of interest in studies such as propagation prediction and influence maximization, both of which have applications in viral marketing and rumor controlling. There are a variety of information diffusion models, all of which simulate the adoption and spread of information over time. However, there is a lack of understanding of whether, despite their conceptual differences, these models represent the same underlying generative structures. For instance, if two different models utilize different conceptual mechanisms, but generate the same results, does the choice of model matter? A classification of diffusion of information models is developed based on the neighbor knowledge of the model infection requirement and the stochasticity of the model. This classification allows for the identification of models that fall into each respective category. The study involves the analysis of the following agent-based models on directed scale-free networks: (1) a linear absolute threshold model (LATM), (2) a linear fractional threshold model (LTFM), (3) the independent cascade model (ICM), (4) Bass-Rand-Rust model (BRRM) (5) a stochastic linear absolute threshold model (SLATM) (6) a stochastic fractional threshold model (SLFTM), and (7) Dodds–Watts model (DWM). Through the execution of simulations and analysis of the experimental results, the distinctive properties of each model are identified. Our analysis reveals that similarity in conceptual design does not imply similarity in behavior concerning speed, final state of nodes and edges, and sensitivity to parameters. Therefore, we highlight the importance of considering the unique behavioral characteristics of each model when selecting a suitable information diffusion model for a particular application.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

How good are learning-based control v.s. model-based control for load shifting? Investigations on a single zone building energy system

Both model predictive control (MPC) and deep reinforcement learning control (DRL) have been presented as a way to approximate the true optimality of a dynamic programming problem, and these two have shown significant operational cost saving potentials for building energy systems. Furthermore, there is still a lack of in-depth quantitative studies on their approximation levels to the true optimality, especially in the building energy domain. To fill in the gap, this paper provides a numerical framework that enables the evaluation of the optimality levels of different controllers for building energy systems. This framework is then used to comprehensively compare the optimal control performance of both MPC and DRL controllers with given computation budgets for a single zone fan coil unit system. Note the optimality is estimated based on a user-specific selection of trade-off weights among energy costs, thermal comfort and control slew rates. Compared with the best optimality we can find through expensive optimization simulations, the best DRL agent can maximally approximate the optimality by 96.54%, which outperforms the best MPC whose optimality level is 90.11%. However, due to the stochasticity, the DRL agent is only expected to approximate the optimality by 90.42%, which is almost equivalent to the best MPC. Except for Proximal Policy Optimization (PPO), all DRL agents can have a better approximation to the optimality than the best MPC, and are expected to have better approximation than the MPC with a prediction horizon of 32 steps (15 min per step). In terms of reducing energy cost and thermal discomfort, MPC can outperform the rule-based control (RBC) by 18.47%–25.44%. DRL can be expected to outperform RBC by 18.95%–25.65% ,and the best DRL control policy can outperform RBC by 20.29%–29.72%. Although the comparison of the optimality level is performed in a perfect setting, e.g., MPC assumes perfect models, and DRL assumes a perfect offline training process and online deployment process, this can shed insight on their capabilities of approximating to the original dynamic programming problem.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2021

Stopping criteria for ending autonomous, single detector radiological source searches

While the localization of radiological sources has traditionally been handled with statistical algorithms, such a task can be augmented with advanced machine learning methodologies. The combination of deep and reinforcement learning has provided learning-based navigation to autonomous, single-detector, mobile systems. However, these approaches lacked the capacity to terminate a surveying/search task without outside influence of an operator or perfect knowledge of source location (defeating the purpose of such a system). Two stopping criteria are investigated in this work for a machine learning navigated system: one based upon Bayesian and maximum likelihood estimation (MLE) strategies commonly used in source localization, and a second providing the navigational machine learning network with a “stop search” action. A convolutional neural network was trained via reinforcement learning in a 10 m × 10 m simulated environment to navigate a randomly placed detector-agent to a randomly placed source of varied strength (stopping with perfect knowledge during training). The network agent could move in one of four directions (up, down, left, right) after taking a 1 s count measurement at the current location. During testing, the stopping criteria for this navigational algorithm was based upon a Bayesian likelihood estimation technique of source presence, updating this likelihood after each step, and terminating once the confidence of the source being in a single location exceeded 0.9. A second network was trained and tested with similar architecture as the previous but which contained a fifth action: for self-stopping. The accuracy and speed of localization with set detector and source initializations were compared over 50 trials of MLE-Bayesian approach and 1000 trials of the CNN with self-stopping. The statistical stopping condition yielded a median localization error of ~1.41 m and median localization speed of 12 steps. The machine learning stopping condition yielded a median localization error of 0 m and median localization speed of 17 steps. This work demonstrated two stopping criteria available to a machine learning guided, source localization system.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗

DOE OSTI2022

Variational multiscale reinforcement learning for discovering reduced order closure models of nonlinear spatiotemporal transport systems

Abstract A central challenge in the computational modeling and simulation of a multitude of science applications is to achieve robust and accurate closures for their coarse-grained representations due to underlying highly nonlinear multiscale interactions. These closure models are common in many nonlinear spatiotemporal systems to account for losses due to reduced order representations, including many transport phenomena in fluids. Previous data-driven closure modeling efforts have mostly focused on supervised learning approaches using high fidelity simulation data. On the other hand, reinforcement learning (RL) is a powerful yet relatively uncharted method in spatiotemporally extended systems. In this study, we put forth a modular dynamic closure modeling and discovery framework to stabilize the Galerkin projection based reduced order models that may arise in many nonlinear spatiotemporal dynamical systems with quadratic nonlinearity. However, a key element in creating a robust RL agent is to introduce a feasible reward function, which can be constituted of any difference metrics between the RL model and high fidelity simulation data. First, we introduce a multi-modal RL to discover mode-dependant closure policies that utilize the high fidelity data in rewarding our RL agent. We then formulate a variational multiscale RL (VMRL) approach to discover closure models without requiring access to the high fidelity data in designing the reward function. Specifically, our chief innovation is to leverage variational multiscale formalism to quantify the difference between modal interactions in Galerkin systems. Our results in simulating the viscous Burgers equation indicate that the proposed VMRL method leads to robust and accurate closure parameterizations, and it may potentially be used to discover scale-aware closure models for complex dynamical systems.

97 MATHEMATICS AND COMPUTING↗

NASA NTRSDate not supplied

Towards Autonomous Lunar Resource Excavation via Deep Reinforcement Learning

To support sustainable infrastructure on the Moon, NASA needs to leverage lunar resources for in-situ processing and construction. NASA’s Regolith Advanced Surface Systems Operations Robot (RASSOR) is principally designed to mine and deliver regolith for these tasks. To reliably perform these operations on the lunar surface, RASSOR's sensors and control systems need to be robust and maximize information extracted from a reduced sensor payload. Herein, we present our findings from the Intelligent Capabilities Enhanced RASSOR project. We created reduced-order simulation environments in which we applied reinforcement learning algorithms to learn autonomous trenching controllers and produced state estimation architectures. We developed two simulations: a 2D excavation simulation used to facilitate parameter selection, and a 3D simulation developed using a game physics engine to simulate simplified soil interactions and incorporate robotic agents parameterized by dynamic models. Within these simulations, we learned autonomous excavation routines that exceed excavation efficiency measures as compared against RASSOR's existing control and teleoperation-based methods.

RASSOR↗