End-to-end learning for off-road terrain navigation using the Chrono open-source simulation platform

Benatti, Simone; Young, Aaron; Elmquist, Asher; Taves, Jay; Tasora, Alessandro; Serban, Radu; Negrut, Dan

doi:10.1007/s11044-022-09816-1

Cited by 4 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An extended version of the SCM is available in the open-source multiphysics package Chrono [45][46][47]. In recent times, the Chrono implementation of the SCM has been utilized for researching teaching artificial intelligence to control vehicles on deformable terrains [48,49]. The AESCO soft soil tire model (AS2TM) also utilizes Bekker's equations as the basis for simulating both rigid and flexible tires on deformable terrains [50].…”

Section: Modeling Of Tire Soil-interaction and Agricultural Machinery...mentioning

confidence: 99%

Effect of Soil Properties and Powertrain Configuration on the Energy Consumption of Wheeled Electric Agricultural Robots

Kivekäs,

Lajunen

2024

Energies

View full text Add to dashboard Cite

Agricultural emissions can be significantly reduced with smart farming, which includes moving away from large conventional tractors to fleets of compact wheeled electric robots. This paper presents a novel simulation modeling approach for an ATV-sized wheeled electric agricultural robot pulling an implement on deformable terrain. The 2D model features a semiempirical tire–soil interaction model as well as a powertrain model. Rear-wheel drive (RWD), front-wheel drive (FWD), and all-wheel drive (AWD) versions were developed. Simulations were carried out on two different soils to examine the energy consumption and tractive performance of the powertrain options. The results showed that energy consumption varies the least with AWD. However, RWD could provide lower energy consumption than AWD with light workloads due to lower curb weight. However, with the heaviest workload, AWD had 7.5% lower energy consumption than RWD. FWD was also found to be capable of lower energy consumption than AWD on light workloads, but it was unsuited for heavy workloads due to traction limitations. Overall, the results demonstrated the importance of taking the terrain characteristics and workload into account when designing electric agricultural robots. The developed modeling approach can prove useful for designing such machines and their fleet management.

show abstract

Section: Modeling Of Tire Soil-interaction and Agricultural Machinery...mentioning

confidence: 99%

Effect of Soil Properties and Powertrain Configuration on the Energy Consumption of Wheeled Electric Agricultural Robots

Kivekäs,

Lajunen

2024

Energies

View full text Add to dashboard Cite

show abstract

A Survey of Integrated Simulation Environments for Connected Automated Vehicles: Requirements, Tools, and Architecture

Stepanyants,

Romanov

2024

IEEE Intell. Transport. Syst. Mag.

View full text Add to dashboard Cite

Real-Time Simulation of Ground Vehicles on Deformable Terrain

Serban

Taves

Zhou

2023

Journal of Computational and Nonlinear Dynamics

View full text Add to dashboard Cite

Techniques for modeling deformable terrain span an entire range varying in complexity, representation accuracy, and ensuing computational effort. While formulations such as fully-resolved granular dynamics, continuum representation of granular material, or finite element can provide a high level of accuracy, they do so at a significant cost, even when the implementation leverages parallel computing and/or hardware accelerators. Real-time or faster than real-time terramechanics is a highly desired capability (in applications such as training of autonomous vehicles and robotic systems) or critical capability (in applications such as human-in-the-loop or hardware-in-the-loop). We present a real-time capable deformable soil implementation, extended from the Soil Contact Model (SCM) developed at the German Aerospace Center which in turn can be viewed as a generalization of the Bekker-Wong and Janosi-Hanamoto semi-empirical models for soil interaction with arbitrary three-dimensional shapes and arbitrary contact patches. This SCM implementation is available, alongside more computationally intensive deformable soil representations, in the open-source multi-physics package Chrono. We describe the overall implementation and the features of the Chrono SCM model, the efficient underlying data structures, the current multi-core parallelization aspects, and its scalability properties for concurrent simulation of multiple vehicles on deformable terrain.

show abstract

End-to-end learning for off-road terrain navigation using the Chrono open-source simulation platform

Cited by 4 publications

References 15 publications

Effect of Soil Properties and Powertrain Configuration on the Energy Consumption of Wheeled Electric Agricultural Robots

Effect of Soil Properties and Powertrain Configuration on the Energy Consumption of Wheeled Electric Agricultural Robots

A Survey of Integrated Simulation Environments for Connected Automated Vehicles: Requirements, Tools, and Architecture

Real-Time Simulation of Ground Vehicles on Deformable Terrain

Contact Info

Product

Resources

About