Experimental Investigation on Traction, Mobility, and Energy Usage of a Tracked Autonomous Ground Vehicle on a Sloped Soil Bin

Badgujar, Chetan; Flippo, Daniel; Brokesh, Edwin; Welch, Stephen

doi:10.13031/ja.14860

Cited by 11 publications

(9 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The vehicle was powered with a 24 V and 50 Ah Lithium battery, sufficient for 3–4 h of continuous operation at standard operating conditions. More details on the AGV can be found in Badgujar, Flippo, Brokesh, et al (2022).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Deep neural networks to predict autonomous ground vehicle behavior on sloping terrain field

Badgujar

Das

Figueroa

et al. 2023

Journal of Field Robotics

Self Cite

View full text Add to dashboard Cite

Conventional large agricultural machinery or implements are unsafe and unsuitable to operate on slopes > 6 ∘ $\gt {6}^{\circ }$ or 10%. Tractor rollovers are frequent on slopes, precluding farming on arable hills, uneven or highly sloped land. Therefore, a fleet of autonomous ground vehicles (AGV) is proposed to cultivate highly sloped land (> 6 ∘ $\gt {6}^{\circ }$). The fleet aims to expand agricultural land to the slopes and to strengths the human‐robot collaboration in an unsafe sloped environment. However, the fleet's success largely depends on vehicle behavior models regarding traction, mobility, and energy consumption on varying slopes. The vehicle intelligent behavior models are essential and would solve multiple objectives ranging from simulations to path planning & navigation. Therefore, this study aimed to build a deep learning‐based vehicle behavior models on sloping terrain. A standard drawbar test was performed on a single AGV operating on an actual sloped field at varying speeds and load conditions. The drawbar test quantified the AGV's behavior on slopes in metrics related to traction (traction efficiency), mobility (travel reduction), and energy consumption (power number). Deep learning‐based models were developed from the experimental data to predict the AGV's behavior on slopes as a function of vehicle velocity, drawbar, and slope. A special model called the proposed model, which combined multiple deep neural networks with a mixture of Gaussians, was developed and trained with a hybrid training method. The proposed model consistently outperformed the other well‐known machine learning models. This study explored the capabilities of machine learning algorithms to simulate the behavior of small‐track vehicle or AGV on sloping terrain. The fleet aims to provide safer agriculture keeping human safety in focus, and the developed predictive vehicle behavior models would empower the fleet's operation on currently unsafe sloped terrain by assisting in vehicle path planning, route optimization, and decision making.

show abstract

Section: Methodsmentioning

confidence: 99%

“…We would like to operate the AGV to a maximum PN value of 25. Therefore, all samples with

PN\ge 100

were discarded from the data set since operating the AGV above this number became an inefficient operation (Badgujar, Flippo, Brokesh, et al, 2022).…”

Section: Methodsmentioning

confidence: 99%

Deep neural networks to predict autonomous ground vehicle behavior on sloping terrain field

Badgujar

Das

Figueroa

et al. 2023

Journal of Field Robotics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The basic motorized unit was an Autonomous Ground Vehicle (AGV) developed by Kansas State University (KSU) specifically designed for high slope field operations, and more details on the vehicle can be found in Badgujar et al (2022aBadgujar et al ( , 2022b. The AGV is a small (1.10×0.64 m), lightweight (90 kg) tracked vehicle fitted with an on-board microcontroller; re-configurable input-output device (myRIO, National Instruments, Austin, TX, USA) requiring a systemdesign platform in LabVIEW.…”

Section: Platformmentioning

confidence: 99%

Development and Evaluation of Pasture Tree Cutting Robot

Badgujar

Flippo

Badua

et al. 2022

Croat. j. for. eng. (Online)

View full text Add to dashboard Cite

The encroachment of Eastern redcedar (ERC) (Juniperus virginiana L.) onto Great Plains prairies has become a serious threat to ecosystem functioning and grazing productivity. The uncontrolled spread of this invasive tree species has been called a »green glacier« converting grasslands into closed canopy woodlands. A pasture tree cutting robot was developed using a tracked Autonomous Ground Vehicle (AGV) equipped with a chainsaw bar to mitigate this green glacier dilemma. The prototype was fitted with amperage and voltage sensors to measure average power consumption and peak power requirements of tree cutting. It was evaluated on ERC and Honeylocust trees up to 20 cm in diameter. Cutting energy and time were determined to evaluate energy optimization and cutting time estimates. A pasture tree clearing energy consumption of the developed prototype was estimated for selected tree density/hectare. The prototype robot was successful in cutting down the intended size trees at a manageable power usage.

show abstract

“…The soil’s moisture content, a tracked vehicle’s weight, and how its mechanical treads contact the soil’s granular structure raise concerns. Controlled soil container experiments have examined pressure sinkage and bearing capacity [ 5 , 33 , 34 ]. However, laboratory environments have often limited these revolutionary discoveries, emphasizing the importance of real-time validations.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Ground Pressure, Bearing Capacity, and Sinkage in Rigid-Flexible Tracked Vehicles on Characterized Terrain in Laboratory Conditions

Rauf,

Ning,

Ming

et al. 2024

Sensors

View full text Add to dashboard Cite

Trafficability gives tracked vehicles adaptability, stability, and propulsion for various purposes, including deep-sea research in rough terrain. Terrain characteristics affect tracked vehicle mobility. This paper investigates the soil mechanical interaction dynamics between rubber-tracked vehicles and sedimental soils through controlled laboratory-simulated experiments. Focusing on Bentonite and Diatom sedimental soils, which possess distinct shear properties from typical land soils, the study employs innovative user-written subroutines to characterize mechanical models linked to the RecurDyn simulation environment. The experiment is centered around a dual-tracked crawler, which in itself represents a fully independent vehicle. A new three-dimensional multi-body dynamic simulation model of the tracked vehicle is developed, integrating the moist terrain’s mechanical model. Simulations assess the vehicle’s trafficability and performance, revealing optimal slip ratios for maximum traction force. Additionally, a mathematical model evaluates the vehicle’s tractive trafficability based on slip ratio and primary design parameters. The study offers valuable insights and a practical simulation modeling approach for assessing trafficability, predicting locomotion, optimizing design, and controlling the motion of tracked vehicles across diverse moist terrain conditions. The focus is on the critical factors influencing the mobility of tracked vehicles, precisely the sinkage speed and its relationship with pressure. The study introduces a rubber-tracked vehicle, pressure, and moisture sensors to monitor pressure sinkage and moisture, evaluating cohesive soils (Bentonite/Diatom) in combination with sand and gravel mixtures. Findings reveal that higher moisture content in Bentonite correlates with increased track slippage and sinkage, contrasting with Diatom’s notable compaction and sinkage characteristics. This research enhances precision in terrain assessment, improves tracked vehicle design, and advances terrain mechanics comprehension for off-road exploration, offering valuable insights for vehicle design practices and exploration endeavors.

show abstract

Experimental Investigation on Traction, Mobility, and Energy Usage of a Tracked Autonomous Ground Vehicle on a Sloped Soil Bin

Cited by 11 publications

References 0 publications

Deep neural networks to predict autonomous ground vehicle behavior on sloping terrain field

Deep neural networks to predict autonomous ground vehicle behavior on sloping terrain field

Development and Evaluation of Pasture Tree Cutting Robot

Evaluation of Ground Pressure, Bearing Capacity, and Sinkage in Rigid-Flexible Tracked Vehicles on Characterized Terrain in Laboratory Conditions

Contact Info

Product

Resources

About