Timo Oksanen

Peter Buckel, Timo Oksanen, Thomas Dietmueller

Dust in the agricultural landscape is a significant challenge and influences, for example, the environmental perception of autonomous agricultural machines. Image enhancement algorithms can be used to reduce dust. However, these require dusty and dust-free images of the same environment for validation. In fact, to date, there is no dataset that we are aware of that addresses this issue. Therefore, we present the agriscapes RB-Dust dataset, which is named after its purpose of reference-based dust removal. It is not possible to take pictures from the cabin during tillage, as this would cause shifts in the images. Because of this, we built a setup from which it is possible to take images from a stationary position close to the passing tractor. The test setup was based on a half-sided gate through which the tractor could drive. The field tests were carried out on a farm in Bavaria, Germany, during tillage. During the field tests, other parameters such as soil moisture and wind speed were controlled, as these significantly affect dust development. We validated our dataset with contrast enhancement and image dehazing algorithms and analyzed the generalizability from recordings from the moving tractor. Finally, we demonstrate the application of dust removal based on a high-level vision task, such as person classification. Our empirical study confirms the validity of RB-Dust for vision-based dust removal in agriculture.

Timo Oksanen, Karl Th. Renius

Direct electric drivelines without power-split open new design freedom for frame and suspension design, along with often lower energy losses. This paper focuses on self-propelled agricultural machinery (combine and forage harvest-ers, root crop harvesters), equipment carriers, propelled trailers and field robots. For a typical vehicle with four driven wheels, the electric motors can be packaged as two axle modules or four wheel modules, both defined herein as self-contained mechatronic units with integrated power electronics, distributed control intelligence and steering. Axle module and wheel module concepts are compared in detail against engineering requirements including loads, effi-ciency, steerability, controllability, braking, suspension, structural load support, asymmetric wheel loading and manu-facturing cost. The wheel module offers maximum design freedom, redundancy and controllability, while the axle module provides lower cost, structural rigidity, automatic load sharing through the differential and the ability to be used in existing vehicle structures. Both concepts are defined such that distributed control intelligence and steering are integral to each unit, requiring only a DC power bus and communication interface from the vehicle.

Samuel Brodie, Henri Hornburg, Daniel Ostermeier et al.

The current state of the art in the agricultural industry for inter-manufacturer, plug-and-play communications is the ISO 11783 standard series, which mandates the use of 250 Kb/s CAN bus. To support higher data rates, the ISO 23870 series is under development, defining a gigabit automotive Ethernet physical layer for next-generation machine-to-machine communication networks. However, middleware is needed to handle the complexity of the system by providing an additional layer of abstraction. It should address the future needs of the industry such as higher levels of automation, additional data logging, modern data types, quality of service configuration, and best-practice cybersecurity. Data Distribution Service (DDS) is a potential middleware for use in such a network. DDS provides many features not present in the current ISO 11783, it is a standardised protocol for data sharing between distributed applications. This work analyses the extent to which DDS can be used to develop a system which meets the requirements for next-generation communication networking for agricultural machinery. A proof-of-concept design is presented, including a Task Controller and implement and it is shown that the requirements are fulfilled. A new DDI concept is proposed that decomposes the monolithic numeric DDI of ISO 11783 into separate typed Enums for handling group, handling feature, and SI units, enabling more flexible signal definitions. Four security configurations are tested in the proof-of-concept implementation and it is shown that enabling security features has a significant impact on throughput.

Ruben Hefele, Timo Oksanen

Tillage operations account for a large share of on-farm diesel consumption, yet the fuel efficiency of the combined tractor-implement system is not optimised in current practice. Modern continuously variable transmission (CVT) tractors minimise engine fuel consumption internally, but they treat the implement as an unknown load and do not account for the effect of vehicle speed on implement draft force. This paper presents EcoTIM, a distributed fuel-optimisation concept in which the tractor and tillage implement cooperate through the extended ISO 11783 (ISOBUS) Tractor Implement Management (TIM) interface to minimise fuel consumption per hectare in real time. In the EcoTIM concept, the tractor Electric Control Unit fuses its internal engine, transmission, and traction efficiencies into a single combined efficiency value and its derivative with respect to vehicle speed, and broadcasts both to the implement at the standard 100 ms CAN bus cycle. The implement ECU combines these two received scalars with its own analytically known draft force model to evaluate the fuel-consumption gradient, and commands the optimal speed, and as a novel TIM extension, the desired acceleration, back to the tractor. Because only two scalar values are exchanged and neither party discloses proprietary subsystem models, the architecture is inherently multi-brand and plug-and-play. The required data exchange is realised with three new messages and one backward-compatible byte-level extension to the standard TIM speed command, and this paper proposes that these messages are standardised within ISO 11783. The acceleration command enables feed-forward torque and CVT ratio planning on the tractor side, improving transient response compared with speed-only TIM commands. This paper also contains a proof-of-concept simulation with six tillage scenarios and a spatially varying 1km test track for initial concept validation.

Maximilian Harnot, Sebastian Komarnicki, Michal Polok et al.

Manual development of automatic tests for embedded C software is a strenuous and time-consuming task that does not scale well. With the accelerating pace of software release cycles, verification increasingly becomes the bottleneck in the embedded development workflow. This paper presents a Retrieval-Augmented Generation (RAG) pipeline as a solution for partial automation of the verification process. By grounding a large language model in project-specific artifacts, the approach reduces hallucinations and improves project alignment. An industrial evaluation showed that the generated tests are 100 % syntactically correct, with 85 % successfully passing runtime validation. The proposed solution has the potential to save up to 66 % of the testing time compared to manual test writing while generating 270 tests per hour.

Julius Gun, Timo Oksanen

We present a case study evaluating large language models (LLMs) with 128K-token context windows on a technical question answering (QA) task. Our benchmark is built on a user manual for an agricultural machine, available in English, French, and German. It simulates a cross-lingual information retrieval scenario where questions are posed in English against all three language versions of the manual. The evaluation focuses on realistic "needle-in-a-haystack" challenges and includes unanswerable questions to test for hallucinations. We compare nine long-context LLMs using direct prompting against three Retrieval-Augmented Generation (RAG) strategies (keyword, semantic, hybrid), with an LLM-as-a-judge for evaluation. Our findings for this specific manual show that Hybrid RAG consistently outperforms direct long-context prompting. Models like Gemini 2.5 Flash and the smaller Qwen 2.5 7B achieve high accuracy (over 85%) across all languages with RAG. This paper contributes a detailed analysis of LLM performance in a specialized industrial domain and an open framework for similar evaluations, highlighting practical trade-offs and challenges.

Erkin Türköz, Ertug Olcay, Timo Oksanen

This paper proposes a concept of computer vision-based guidance assistance for agricultural vehicles to increase the accuracy in plowing and reduce driver's cognitive burden in long-lasting tillage operations. Plowing is a common agricultural practice to prepare the soil for planting in many countries and it can take place both in the spring and the fall. Since plowing operation requires high traction forces, it causes increased energy consumption. Moreover, longer operation time due to unnecessary maneuvers leads to higher fuel consumption. To provide necessary information for the driver and the control unit of the tractor, a first concept of furrow detection system based on an RGB-D camera was developed.