Umeå University's logo

DEM is computationally intensive for granular dynamics simulation, leading to a need for efficient strategies. This study explores using local particle refinement, scaling particle size based on expected spatial resolution needs, inspired by adaptive mesh refinement in FEM. Finer particles are used where intense interaction occurs, and coarser particles further away.

We hypothesize this method can maintain good accuracy while reducing particle count and computational effort. Fine particles are used on the soil bed's top, with coarser particles at greater depth, creating a particle size gradient. By adjusting the gradient we introduce a “scaling aggressiveness”, allowing control over the trade-off between efficiency and accuracy.

We use triaxial tests to verify that the method is scale invariant. Pressure-sinkage and shear displacement tests are then used to evaluate the method's effectiveness and accuracy in terramechanics applications. All beds were compared to a reference bed with homogenous particle size, where the mean static sinkage was 1.25 mm for a 50 kPa load. The dynamic sinkage was 73 mm for the full simulation time. For quasi-2D simulations, mild scaling aggressiveness reduced the particle count by 2-4 times with relative error up to 4% for dynamic sinkage (11%for static sinkage). For medium aggressiveness, 4-6 times reduction with relative error of 4%(19% static). For highest aggressiveness, 6-8 times reduction with relative error of 7% (29%static). The internal friction proved to be very resistant to gradient changes, with errors within 1%. When extending the model to full 3D, we estimate up to a reduction in particle count of up to a factor 25.

Safety berms (also called safety bunds or windrows), widely employed in surface mining and quarry operations, are typically designed based on rules of thumb. Despite having been used by the industry for more than half a century and accidents happening regularly, their behaviour is still poorly understood. This paper challenges existing practices through a comprehensive investigation combining full-scale experiments and advanced numerical modelling. Focusing on a Volvo A45G articulated dump truck (ADT) and a CAT 773B rigid dump truck (RDT), collision scenarios under various approach conditions and different safety berm geometries and materials are rigorously examined. The calibrated numerical model is used to assess the energy absorption capacity of safety berms with different geometry and to predict a critical velocity for a specific scenario. Back analysis of an actual fatal accident indicated that an ADT adhering to the speed limit could not be stopped by the safety berm designed under current guidelines. The study highlights the importance of considering the entire geometry and the mass and volume of the material used to build the safety berm alongside the speed and approach conditions of the machinery. The findings of the study enable operators to set speed limits based on specific berm geometries or adapt safety berm designs to match speed constraints for specific machinery. This will reduce the risk of fatal accidents and improve haul road safety.

We investigate how well a physics-based simulator can replicate a real wheel loader performing bucket filling in a pile of soil. The comparison is made using field-test time series of the vehicle motion and actuation forces, loaded mass, and total work. The vehicle was modeled as a rigid multibody system with frictional contacts, driveline, and linear actuators. For the soil, we tested discrete-element models of different resolutions, with and without multiscale acceleration. The spatiotemporal resolution ranged between 50–400 mm and 2–500 ms, and the computational speed was between 1/10,000 to 5 times faster than real time. The simulation-to-reality gap was found to be around 10% and exhibited a weak dependence on the level of fidelity, e.g., compatible with real-time simulation. Furthermore, the sensitivity of an optimized force-feedback controller under transfer between different simulation domains was investigated. The domain bias was observed to cause a performance reduction of 5% despite the domain gap being about 15%.

Forwarder trafficability is a function of terrain and vehicle properties. Predicting trafficability is vital for energy efficient planning- and operator-assisting systems, as well as for remote and autonomous driving. Inaccurate or insufficient information can lead to inefficient paths, excessive fuel usage, equipment wear, and soil damages. Training trafficability models require data in a quantity hard to collect solely from in-field experiments, especially considering the need for data from situations ranging from very easy to non-traversable.

To circumvent this problem, we perform in-field system identification for a forwarder in the Nordic cut-to-length system, to obtain a calibrated multi-body dynamics simulation model traversing firm but potentially rough and blocky terrain. By letting the real-world forward derdrive in very difficult terrain, the model is able to reflect a wide range of real conditions. The model is used in simulations, where collecting large amounts of data from a variety of situations is easy, cheap, and hazard free. Using this data, a deep neural network is trained to predict trafficability in terms of attainable driving speed, energy consumption, and machine wear.

The resulting predictor model uses laser scanned terrains to efficiently produce trafficability measures with high fidelity and accuracy, e.g., depending on the vehicle’s precise location, speed, heading, and weight. Trafficability on wet and weak soil is not addressed in this work. The predictor model is machine specific, but general enough for practical application in diverse terrain conditions. Our emphasis on energy consumption enables elaborate calculations of emissions, profoundly contributing to sustainable forest operations. Apart from the benefits from reduced emissions, the model can also be used to optimize extraction trail routing, which is a major contributor to the total extraction cost. Rough terrain trafficability is only part of an optima loute, but it has been neglected in previous research. We see big potential in combining our predictor model with existing route optimization methods to achieve a more complete result. By creating an open library of annotated machine data and code for preparing input terrain-data and running the trafficability model, we enable adoption of the results by others and application in existing and new software.

We explore multi-log grasping using reinforcement learning and virtual visual servoing for automated forwarding in a simulated environment. Automation of forest processes is a major challenge, and many techniques regarding robot control pose different challenges due to the unstructured and harsh outdoor environment. Grasping multiple logs involves various problems of dynamics and path planning, where understanding the interaction between the grapple, logs, terrain, and obstacles requires visual information. To address these challenges, we separate image segmentation from crane control and utilise a virtual camera to provide an image stream from reconstructed 3D data. We use Cartesian control to simplify domain transfer to real-world applications. Because log piles are static, visual servoing using a 3D reconstruction of the pile and its surroundings is equivalent to using real camera data until the point of grasping. This relaxes the limits on computational resources and time for the challenge of image segmentation, and allows for data collection in situations where the log piles are not occluded. The disadvantage is the lack of information during grasping. We demonstrate that this problem is manageable and present an agent that is 95% successful in picking one or several logs from challenging piles of 2–5 logs.

We create partially annotated datasets from field measurements for developing models and algorithms for perception and control of forest machines using artificial intelligence, simulation, and experiments on physical testbeds.  The datasets, algorithms, and trained models for object identification, 3D perception, and motion planning and control will be made publicly available through data and code-sharing repositories.

The data is recorded using forest machines and other equipment with suitable sensors operating in the forest environment. The data include the machine and crane tip position at high resolution, and event time logs (StanForD) while the vehicle operates in high-resolution laser-scanned forest areas.  For annotation, the plan is to use both CAN-bus data and audiovisual data from operators that are willing to participate in the research. Also, by fusing visual perception with operator tree characteristics input or decision, we aim to develop a method for auto-annotation, facilitating a rapid increase in labeled training data for computer vision. In other activities, images of tree plants and bark are collected.

Research questions include, how to automate the process of creating annotated datasets and train models for identifying and positioning forestry objects, such as plants, tree species, logs, terrain obstacles, and do 3D reconstruction for motion planning and control? How large and varied datasets are required for the models to handle the variability in forests, weather, light conditions, etc.? Would additional synthetic data increase model inference accuracy?

In part we focus on forwarders traversing terrain, avoiding obstacles, and loading or unloading logs, with consideration for efficiency, safety, and environmental impact. We explore how to auto-generate and calibrate forestry machine simulators and automation scenario descriptions using the data recorded in the field. The demonstrated automation solutions serve as proofs-of-concept and references, important for developing commercial prototypes and for understanding what future research should focus on.

Extraction of timber is expensive, energy intensive, and potentially damaging to the forest soil. Machine development aims to mitigate risks for environmental impact and decrease energy consumption while maintaining or increasing cost efficiency. Development of rubber-tracked forwarders have gained renewed interest, partly due to climate change leading to unreliable weather, and the urgency of reducing emissions. The increased cost of rubber-tracks compared to wheels are believed to be compensated by higher driving speeds and larger payloads. Thus, the aim of this study was to theoretically investigate how productivity and cost efficiency of rubber-tracked forwarders can exceed that of wheeled equivalents. The calculations were made with fixed parameters, to evaluate performance in different conditions, and with parameters from 2 500 final felling stands in central Sweden, to evaluate performance in varied working conditions. Scenarios were compared to a baseline corresponding to mid-sized wheeled forwarders. The results show higher productivity with the increased driving speed and load weight enabled by rubber-tracks at all extraction distances, with larger differences at long extraction distances. Assuming 15% higher machine price for the rubber-tracked forwarder, increased speed and load weight lead to 40% cost reduction for 400 meters extraction distance. Furthermore, a rubber-tracked forwarder is likely to give access to a larger part of the harvest areas during longer seasons. The year-round accessible volumes are estimated to increase from 9% to 92% with a rubber-tracked forwarder. With rubber-tracks, good accessibility can be combined with low soil impact in a favourable way for both industry and ecosystem.

We explore sim-to-real transfer of deep reinforcement learning controllers for a heavy vehicle with active suspensions designed for traversing rough terrain. While related research primarily focuses on lightweight robots with electric motors and fast actuation, this study uses a forestry vehicle with a complex hydraulic driveline and slow actuation. We simulate the vehicle using multibody dynamics and apply system identification to find an appropriate set of simulation parameters. We then train policies in simulation using various techniques to mitigate the sim-to-real gap, including domain randomization, action delays, and a reward penalty to encourage smooth control. In reality, the policies trained with action delays and a penalty for erratic actions perform nearly at the same level as in simulation. In experiments on level ground, the motion trajectories closely overlap when turning to either side, as well as in a route tracking scenario. When faced with a ramp that requires active use of the suspensions, the simulated and real motions are in close alignment. This shows that the actuator model together with system identification yields a sufficiently accurate model of the actuators. We observe that policies trained without the additional action penalty exhibit fast switching or bang–bang control. These present smooth motions and high performance in simulation but transfer poorly to reality. We find that policies make marginal use of the local height map for perception, showing no indications of predictive planning. However, the strong transfer capabilities entail that further development concerning perception and performance can be largely confined to simulation.

Fully autonomous forwarding is a challenge, with more imminent scenarios including operator assistance, remote-controlled machines, and semi-autonomous functions. We present several subsystems for autonomous forwarding, developed using machine learning and physics simulation,

- trafficability analysis and path planning,

- autonomous driving,

- identification of logs and high quality grasp poses, and

- crane control from snapshot camera data.

Forwarding is an energy demanding process, and repeated passages with heavy equipment can damage the soil. To avoid damage and ensure efficient use of energy, it is important with a good path planning, adapted speed, and efficient loading and unloading of logs. The collection and availability of large amounts of data is increasing in the field of forestry, opening up for autonomous solutions and efficiency improvements. This is a difficult problem though, as the forest terrain is rough, and as weather, season, obstructions, and wear present challenges in collecting and interpreting sensor-data.

Our proposed subsystems assume access to pre-scanned, high-resolution elevation maps and snapshots of log piles, captured in between crane cycles by an onboard camera. By utilizing snapshots instead of a continuous image stream in the loading task, we separate image segmentation from crane control. This removes any coupling to specific vehicle models, and greatly increases the limit on computational resources and time for the challenge of image segmentation. Log piles are normally static except at the grasp moments and given good enough grasp poses, this lack of information is not necessarily a problem.

We show how snapshot image data can be used when deploying a Reinforcement Learning agent to control the crane to grasp logs in challenging piles. Given pile RGB-D images, our grasp detection model identifies high quality grasp poses, allowing for multiple logs to be loaded in each crane cycle. Further, we show that our model is able to learn to avoid obstructions in the environment such as tree stumps or boulders. We discuss the possibility of using our model to optimize the loading task over a sequence of grasps.

Finally, we discuss how the solutions can be combined in a multi-agent forwarding system with or without a human operator in-the loop.

This paper presents a method for learning world models for wheel loaders performing automatic loading actions on a pile of soil. Data-driven models were learned to output the resulting pile state, loaded mass, time, and work for a single loading cycle given inputs that include a heightmap of the initial pile shape and action parameters for an automatic bucket-filling controller. Long-horizon planning of sequential loading in a dynamically changing environment is thus enabled as repeated model inference. The models, consisting of deep neural networks, were trained on data from a 3D multibody dynamics simulation of over 10,000 random loading actions in gravel piles of different shapes. The accuracy and inference time for predicting the loading performance and the resulting pile state were, on average, 95% in 1.21.2 ms and 97% in 4.54.5 ms, respectively. Long-horizon predictions were found feasible over 40 sequential loading actions.