Comparing real and simulated performance for an off‐road autonomous ground vehicle in obstacle avoidance

Carruth, Daniel W.; Goodin, Christopher; Dabbiru, Lalitha; Scherrer, Nicklaus; Moore, Marc N.; Hudson, Christopher H.; Cagle, Lucas D.; Jayakumar, Paramsothy

doi:10.1002/rob.22289

Cited by 3 publications

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Geometric Fidelity Requirements for Meshes in Automotive Lidar Simulation

Goodin,

Moore,

Carruth

et al. 2024

Virtual Worlds

View full text Add to dashboard Cite

The perception of vegetation is a critical aspect of off-road autonomous navigation, and consequentially a critical aspect of the simulation of autonomous ground vehicles (AGVs). Representing vegetation with triangular meshes requires detailed geometric modeling that captures the intricacies of small branches and leaves. In this work, we propose to answer the question, “What degree of geometric fidelity is required to realistically simulate lidar in AGV simulations?” To answer this question, in this work we present an analysis that determines the required geometric fidelity of digital scenes and assets used in the simulation of AGVs. Focusing on vegetation, we use a comparison of the real and simulated perceived distribution of leaf orientation angles in lidar point clouds to determine the number of triangles required to reliably reproduce realistic results. By comparing real lidar scans of vegetation to simulated lidar scans of vegetation with a variety of geometric fidelities, we find that digital tree models (meshes) need to have a minimum triangle density of >1600 triangles per cubic meter in order to accurately reproduce the geometric properties of lidar scans of real vegetation, with a recommended triangle density of 11,000 triangles per cubic meter for best performance. Furthermore, by comparing these experiments to past work investigating the same question for cameras, we develop a general “rule-of-thumb” for vegetation mesh fidelity in AGV sensor simulation.

show abstract

Geometric Fidelity Requirements for Meshes in Automotive Lidar Simulation

Goodin,

Moore,

Carruth

et al. 2024

Virtual Worlds

View full text Add to dashboard Cite

show abstract

Measurement and Prediction of Override Force of Clumps of Small Vegetation in Off-Road Autonomous Navigation

Goodin,

Moore,

Salmon

et al. 2024

SAE Technical Paper Series

View full text Add to dashboard Cite

<div class="section abstract"> <div class="htmlview paragraph">Autonomous navigation in off-road terrain requires a perception system that can distinguish between vegetation that can easily be overridden and vegetation that cannot. While many autonomous systems struggle to estimate the navigability of vegetation like sparse grass or small shrubs, in this work we use a new vehicle-embedded force sensor to directly measure override forces as the vehicle drives through vegetation, allowing the perception system to learn the navigability of vegetation based on the corresponding sensor signatures. The override force can be estimated using a neural network trained on a combination of lidar and images, and the resulting force prediction can be used as an input into both local and global path-planning algorithms for autonomous navigation. In this work, we show the results for our force measurements and outline the process for extracting training data to predict override force using RESNET-50.</div> </div>

show abstract

A Simulation Framework for Evaluating the Cybersecurity of Autonomous Ground Vehicles

Goodin,

Fuller,

Carruth

et al. 2024

SAE Technical Paper Series

View full text Add to dashboard Cite

<div class="section abstract"> <div class="htmlview paragraph">Autonomous ground vehicles (AGV) are comprised of a network of interconnected components including sensors, drive-by-wire actuators, and on-board computing. This on-vehicle network is often connected to a larger network which may include a ground station, other autonomous systems, or remote servers. While AGV share many features with other mobile networked devices like cell phones, the AGV computing and networking architecture may be vulnerable in ways that other systems are not, and the consequences of an attack may result in more severe physical consequences. In this paper, we present a systematic study of the network architecture of an AGV system, a cross-domain evaluation of possible attack vectors for AGV, and an implementation of a simulated cyberphysical test range that reveals the real-world consequences of cyberphysical attacks on AGV.</div> </div>

show abstract

Comparing real and simulated performance for an off‐road autonomous ground vehicle in obstacle avoidance

Cited by 3 publications

References 77 publications

Geometric Fidelity Requirements for Meshes in Automotive Lidar Simulation

Geometric Fidelity Requirements for Meshes in Automotive Lidar Simulation

Measurement and Prediction of Override Force of Clumps of Small Vegetation in Off-Road Autonomous Navigation

A Simulation Framework for Evaluating the Cybersecurity of Autonomous Ground Vehicles

Contact Info

Product

Resources

About