Development of a novel neural network-based control scheme for autonomous farming vehicles
Bibliographic record
Abstract
Agriculture industries call upon autonomous tractors to speed up the process of farming tasks. Although there has been a lot of research on autonomous vehicles, this research mostly concerns road vehicles, which operate in a controlled road environment.This thesis is a part of the ongoing Arion project, from Institut du Véhicule Innovant (IVI). The ultimate goal of the Arion project is to develop an autonomous farming vehicle, which can operate independently and safely. This research is dedicated to designing a robust controller to maintain the accuracy of the autonomous farming vehicle path on different types of soil.The autonomous farming vehicle designed at IVI is an electrical four-wheel-drive vehicle. In this study, the dynamics equations of the vehicle are derived. The model used here is a four-wheel model, with two steerable wheels in the front. Moreover, realistic terramechanics equations, regarding the interaction between the soil and the wheels, are established. The equations of terramechanics are then solved offline, to be used as a lookup table online. This method will increase the efficiency, as the equations need to be solved numerically, and are computationally expensive. The lookup tables are created for four different soil types: Clay, Loam, Sand, and Sandyloam.We introduce a novel scheme for the control of the vehicle. The system contains two controllers: a PID controller for longitudinal speed, and a Model Predictive Controller (MPC) for steering angle. In this scheme, a neural network is used to classify the soil type, and to act as a switch to adapt the MPC controller to the new soil type.The neural network is trained on physical features that can be measured with inexpensive sensors on the vehicle, such as velocity, slip angle, slip ratio, and wheel's sinkage in the soil.The performance of the controller for each soil type is evaluated independently, as well as the performance of the vehicle operating on a field with various soil types. The results show a considerable improvement in accuracy when the proposed controller is used
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".