Real-time states estimation of a farm tractor using dynamic mode decomposition

Wang, Hao; Noguchi, Noboru

doi:10.1007/s10291-020-01051-5

Cited by 8 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine-learning-based control methods learn robot behaviors by combining data-driven formulations into predefined robot models [39], [40]. Early methods used Dynamics Mode Decomposition (DMD) [41] and Sparse Identification of Non-Linear Dynamics (SINDy) [42] to learn data-driven models based on system identification and performed terrain navigation [43], [44]. Later, evolutionary algorithms were developed to optimize parameters of a robot model in an online learning fashion for robust navigation [45], [46].…”

Section: Related Workmentioning

confidence: 99%

NAUTS: Negotiation for Adaptation to Unstructured Terrain Surfaces

Siva¹,

Wigness²,

Rogers³

et al. 2022

Preprint

View full text Add to dashboard Cite

When robots operate in real-world off-road environments with unstructured terrains, the ability to adapt their navigational policy is critical for effective and safe navigation. However, off-road terrains introduce several challenges to robot navigation, including dynamic obstacles and terrain uncertainty, leading to inefficient traversal or navigation failures. To address these challenges, we introduce a novel approach for adaptation by negotiation that enables a ground robot to adjust its navigational behaviors through a negotiation process. Our approach first learns prediction models for various navigational policies to function as a terrain-aware joint local controller and planner. Then, through a new negotiation process, our approach learns from various policies' interactions with the environment to agree on the optimal combination of policies in an online fashion to adapt robot navigation to unstructured off-road terrains on the fly. Additionally, we implement a new optimization algorithm that offers the optimal solution for robot negotiation in real-time during execution. Experimental results have validated that our method for adaptation by negotiation outperforms previous methods for robot navigation, especially over unseen and uncertain dynamic terrains.

show abstract

Section: Related Workmentioning

confidence: 99%

NAUTS: Negotiation for Adaptation to Unstructured Terrain Surfaces

Siva¹,

Wigness²,

Rogers³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Inertial navigation is a navigation method that is based on the properties of inertial bodies and is autonomous, that is, it does not require external landmarks or signals. The disadvantage of this type of navigation is that the error obtained from accelerometers and gyroscopes accumulates over time, so the position should be periodically adjusted from another type of navigation system [9,10].…”

Section: Main Partmentioning

confidence: 99%

“…The accuracy of satellite navigation can be affected by weather conditions, signal reflection from houses or trees, and the quality of receivers. The advantage of satellite navigation is that error does not accumulate over time [10,11].…”

Section: Main Partmentioning

confidence: 99%

Model and Algorithms for Determining the Location and Position of Agricultural Machinery During the Movement

Podorozhniak

Balenko

Sobol

2021

ITSSI

View full text Add to dashboard Cite

The subject of research is the navigation subsystem of autonomous control system to determine the location and position of agricultural machinery during the movement. The purpose of the work is to develop and research model and algorithms to determine the location and position of mobile agricultural machinery using a physical model. The following tasks are solved in the article: development of agricultural machinery physical model to collect information from sensors during movement, further development and research of applicability of algorithms for location and position determination. The following methods are used: methods of mathematical statistics, methods of information systems theory and data processing, methods of random signals filtration. The following results were obtained: during research, the agricultural machinery physical model to collect information from sensors during movement was created. The model includes a GPS receiver, an accelerometer, gyroscope and infrared encoders, to count the rotation of the wheels, as well as its own four wheelbase of agricultural machinery. The modernized GPS coordinate filtration algorithm using a geochex algorithm is proposed, which according to several successively obtained GPS coordinates calculates the hash received coordinates; if the coordinates have the same hash, it can be argued that the vehicle is in the segment of the area that corresponds to this hash. To determine the physical model position during the movement data from the accelerometer and the gyroscope was processed using Savitzky-Golay and Madgwick filters. With the use of wheels’ rotation data, the odometric algorithms for movement and location determining of the agricultural machinery physical model in motion were implemented. Conclusions: to improve the accuracy of estimating the location and position agricultural machinery, algorithms complexation of indicators from different navigation systems should be used to reduce the total error. Research results can be applied in the development of new and modifications of existing navigation subsystems of agricultural machinery autonomous control systems.

show abstract

Research on state-parameter estimation of unmanned Tractor—A hybrid method of DEKF and ARBFNN

Xu,

Chen,

et al. 2024

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Real-time states estimation of a farm tractor using dynamic mode decomposition

Cited by 8 publications

References 28 publications

NAUTS: Negotiation for Adaptation to Unstructured Terrain Surfaces

NAUTS: Negotiation for Adaptation to Unstructured Terrain Surfaces

Model and Algorithms for Determining the Location and Position of Agricultural Machinery During the Movement

Research on state-parameter estimation of unmanned Tractor—A hybrid method of DEKF and ARBFNN

Contact Info

Product

Resources

About