The automation of hydraulic excavators is significant for enhancing productivity and safety in uncertain and dynamic environments. Achieving autonomous operation requires advanced control strategies capable of handling system constraints, nonlinear hydraulic dynamics, and complex environmental interactions. This study proposes a reinforcement learning (RL)-based methodology to perform a complete excavation cycle by controlling proportional valves. A comprehensive joint simulation tool is developed, in which a hydraulic system model is detailed based on a real machine, and it is integrated with an excavator mechanism and working environment to create a realistic interaction environment for RL training. The RL agent, trained using Proximal Policy Optimization (PPO), incorporates a customized reward shaping method that ensures operational safety and accuracy, considering constraints such as pump flow saturation and geometric constraints. In addition, an Adaptive Control Frequency (ACF) method is developed to enhance training efficiency by dynamically adjusting the control frequency based on task complexity. Comparative validations demonstrate the RL agent’s ability to successfully complete a full excavation cycle, satisfy operational constraints, and generalize across varying initial conditions and valve responses. Furthermore, the controller operates effectively in a soil environment despite being trained without soil, demonstrating robustness to uncertain, time-varying loads.

Automation of mobile machinery is critical in the construction industry to improve efficiency and ensure safety. Perception technologies, particularly for detecting and monitoring the actions of construction machinery, are essential for optimizing workflows and mitigating accident risks. However, the complex nature of construction environments, the variety of machines, and the dynamic interactions at construction sites pose significant challenges for reliable object detection and action recognition. This study introduces a deep learning approach using temporal vision information for object detection and action recognition of mobile machinery in construction environments. In particular, a novel strategy called Integrated YL-SF is proposed, which integrates the YOLOv8 framework with the SlowFast model enhanced by Transformers to achieve robust action recognition and motion analysis of construction machinery. The proposed method is evaluated on a custom dataset with a variety of machine types and real-world operating environments, and it is benchmarked against the standard YOLOv8 model. The results show that the Integrated YL-SF framework outperforms existing methods and effectively addresses challenges such as dynamic scenarios, object occlusion, and multi-machine interactions in complex environments.

Loading multiple different materials with wheel loaders is a challenging task because various materials require different loading techniques. It’s, therefore, difficult to find a single controller capable of handling them all. One solution is to use a base controller and fine-tune it for different materials. Reinforcement Learning (RL) automates this process without the need for collecting additional human-annotated data. We investigated the feasibility of this approach using a full-size 24-tonnes wheel loader in the real world and demonstrated that it’s possible to fine-tune a neural network controller that was originally trained with imitation learning on blasted rock for use with an unknown gravel material, requiring 20 bucket fillings. Additionally, we showcased the adaptability of a controller pre-trained on woodchips for an unknown gravel material, requiring 40 bucket fillings. We also proposed a novel reward function for the material loading task. Finally, we examined how the sampling time of the reinforcement learning algorithm affects convergence speed and adaptability. Our results demonstrate that it’s optimal to match the sampling time of the RL algorithm to the delays of the wheel loader’s hydraulic actuators.

Ensuring an accurate and robust localization is one of the most significant problems in the field of mobile robotics. In this context, map-based localization methods utilizing 3D LiDARS for environmental perception are widely used. Even if there exist multiple promising techniques in this field, the majority of approaches can only guarantee an accurate and robust operation if there is no deviation between the map and the real surroundings. Consequently, state of the art localization methods frequently suffer from unreliable results or even complete failure in the case of changing environments. In this paper, we propose an efficient technique for a precise and robust maintenance of localization maps through real-time incorporation of 3D LiDAR scans. Our map update procedure is based on a novel way of estimating the interference between laserbeams and map contents, denoted as Ray-Bundle-Impact-Factor (RBIF). Our technique additionally solves the widespread problem of disruptive hole creation caused by discretization effects. Experiments on real-world as well as synthetic data demonstrate the precision and stability of our method under various challenging conditions and evaluate our approach in comparison to multiple SOTA map maintenance algorithms.

The fleet management of mobile working machines with the help of connectivity can increase not only safety but also productivity. However, rare mobile working machines have taken advantage of V2X. Moreover, no one published the simulation results that are suitable for evaluating the performance of the ad-hoc network at a working site on the highway where is congested, with low mobility, and without building. In this paper, we suggested that IEEE 802.11p should be implemented for fleet management, at least for the first version. Furthermore, we proposed an analytical model for machines to estimate the ad-hoc network performance, i.e., the delay and the packet loss probability in real-time based on the simulation results we made in ns-3. The model of this paper can be further used for determining when shall ad-hoc or cellular network be used in the corresponding scenarios.

This paper introduces the newest development of a driver assistance system for log-hauling trucks, which transport long heavy timber from harvesting sites to distant storage yards or sawmills through off-road paths and on urban highway. Using suitable control strategies on the trailer steering unit, the long timber transportation can be more maneuverable and less hazardous. In this paper we proposed two control strategies for different driving conditions. The first one is a feedback control based on the measured articulation angles between the tractor truck and the payload as well as between the payload and the trailer. The simulation results show that the trailer could follow the trajectory of the tractor satisfactorily, if a normal road curvature was applied. On an extremely curvy road with a curvature larger than 0.1 (according to a turning radius of 10 meters), it was difficult to keep the trailer on the track of the tractor and an unstable situation could happen. As a solution to overcome this problem on extremely curvy narrow path in the forest, a feed-forward control strategy based on path prediction was investigated. Both control strategies have been applied on a 3-DOF linear yaw/plane model in computer simulations and presented promising results for the tests on real vehicles.

This paper presents a method to develop an intelligent master-slave system between agricultural vehicles, which will enable a semi-autonomous agricultural vehicle (slave) to follow a leading tractor (master) with a given lateral and longitudinal offset. In our study not only the follow-up motions but also the site-specific control of the apparatus such as rear and front power lift was considered. In the first part of this paper the recent research works in the area autonomous farming were discussed and the restrictions of these research works were illustrated. In the second part an approach to construct a master-slave system between two agricultural vehicles was demonstrated. In the next part the mathematic modeling of this master-slave system and the simulation results about the control algorithm were demonstrated. Afterwards the result of a real field test was presented and the safety considerations about such an intelligent vehicle system were made.