Bucket Trajectory Research Articles

A bucket fill factor estimation method in construction environments by fusing deep learning and machine vision

The need for high productivity in the construction field is becoming increasingly urgent, and the efficiency of loading and unloading materials by construction vehicles is one of the main influencing factors. The fill factor, which refers to the percentage of the volume of materials in the shovel bucket to the capacity of the shovel bucket, can significantly affect the productivity of construction vehicles, and thereby affect the environmental pollution caused by these vehicles. Therefore, an effective estimation of the fill factor is a prerequisite for improving productivity and suppressing pollution in construction vehicles. However, previous studies have been conducted under ideal environments, the actual harsh environments of the construction sites are not in the purview. Therefore, in this paper, the fill factor of a loader is estimated in nine construction environments, including six ideal environments and three harsh environments. First, the corresponding image processing pipelines are proposed for a variety of environmental characteristics. Then, a stereo segmentation map is constructed based on the loader bucket trajectory and the knowledge of different color space characteristics, which not only addresses the environmental limitations but also significantly improves the accuracy. Finally, an improved CNN is combined with probabilistic knowledge for the fill factor estimation, and transfer learning is also applied to improve the training speed and accuracy. The results show that a satisfactory accuracy of 96.89% is achieved for the abovementioned construction environments, which results in a more efficient and cleaner production of construction vehicles.

LSTM-based Prediction of Excavating Resistive Force Using Bucket Trajectory Shape

Unmanned construction machine has become a promising technology in the civil engineering field. The machine is still less efficient, especially in excavating soil, than the manned construction because the unmanned machine works carefully to avoid potential hazards due to unpredicted soil deformation as well as excavation force. This research aims to predict time-series resistive force of bucket during soil excavation based on the Recurrent Neural Network. First, we experimentally obtain excavating resistive force for various excavation trajectories. In the experiment, a bucket follows pre-determined trajectories with four different elliptical arcs, and the resistive force acting on the bucket is measured. The prediction model of the resistive force is then elaborated by indexing the bucket trajectories. The model validation confirms that the aspect ratio of the ellipse of the trajectories is an effective index for accurately predicting the excavating resistive force.

A deep learning approach for construction vehicles fill factor estimation and bucket detection in extreme environments

AbstractThe development of autonomous detection technology is imperative in the field of construction. The bucket fill factor is one of the main indicators for evaluating the productivity of construction vehicles. Bucket detection is a prerequisite for bucket trajectory planning. However, previous studies have been conducted under ideal environments, a specific single environment, and several normal environments without considering the actual harsh environments at construction sites. Therefore, seven extreme environments are set in this paper to fill this gap, and an effective method is proposed. First, a novel framework for image restoration under extreme environments is proposed. It applies to all tasks conducted by vision on construction sites. Second, a combination of segmentation and classification networks is used for the first time in this area. Multitask learning is used to discover a positive correlation between fill factor estimation and bucket detection. Furthermore, probabilistic methods and transfer learning were introduced, and excellent results were achieved (97.40% accuracy in fill factor estimation and 99.76% accuracy in bucket detection for seven extreme environments).

An online estimation algorithm to predict external forces acting on a front-end loader

One of the most significant goals of earthmoving equipment is to maximize productivity during loading cycles. A real-time knowledge of the forces exchanged between the machine implement and the surrounding, that is, while digging, can be used in different ways to increase productivity. It can be used to determine the amount of material moved by the machine; or to find the optimal bucket trajectory; moreover, as input to traction control systems. This article presents an online force estimation algorithm able to predict vertical and horizontal forces exchanged between the front-loader and the surrounding environment, as well as the reaction forces through the implement itself. Taking the case of a 14-ton wheel loader as reference, this article illustrates the development of a simulation model for the analysis of the machine digging system, along with the instrumentation and testing of the proposed estimation algorithm. The model is divided into two sections describing, respectively, system kinematic and system dynamics. The kinematic model of the front-loader is compared against measurements, and results show an average error lower than 1%. The dynamic model predicts both hydraulic and dynamic features of the machine implement, achieving an accuracy on the payload mass within 2%–3%, even during dynamic conditions. The estimated pushing force reflects the expected behavior when tested for various pushing efforts and in different ground conditions. Eventually, the algorithm was tested on a complete loading cycle and the results show good consistency considering the measured front-loader trajectory and vehicle speed. The proposed model overcomes some drawbacks of the currently used technologies. For example, it allows for an online estimation of the bucket forces for any position of the implement. Although the results discussed in this article pertain to a specific reference machine, the proposed method can be extended to most wheel loaders equipped with standard digging equipment.

Bucket Trajectory Optimization under the Automatic Scooping of LHD

We propose an optimal planning scheme of the bucket trajectory in the LHD (Load-Haul-Dump) automatic shoveling system to improve the effectiveness of the scooping operation. The research involves simulation of four typical shoveling methods, optimization of the scooping trajectory, establishment of a reaction force model in the scooping process and determination of optimal trajectory. Firstly, we compared the one-step, step-by-step, excavation and coordinated shoveling method by the Engineering Discrete Element Method (EDEM) simulation. The coordinated shoveling method becomes the best choice on account of its best comprehensive performance among the four methods. Based on the coordinated shoveling method, the shape of the optimized trajectory can be roughly determined. Then, we established a model of bucket force during the shoveling process by applying Coulomb’s passive earth pressure theory for the purpose of calculating energy consumption. The trajectory is finally determined through optimizing the minimum energy consumption in theory. The theoretical value is verified by the EDEM simulation.

CONSTRUCTION AND TESTING OF THE MEASUREMENT SYSTEM FOR EXCAVATOR PRODUCTIVITY

Hydraulic excavator is one of the most used machines in mining, construction and geotechnics. Monitoring its productivity can gain benefits like savings in fuel consumption and maintenance, cost optimization of working parameters and higher working efficiency. Measurement system for such purpose can be complex and expensive, requires special equipment from manufacturer and does not exist as out of the box solution that would measure working parameters such as bucket trajectory, digging energy, digging force etc. Measuring system was designed to monitor productivity and gather working parameters. It consists of three pressure transmitters for measuring cylinder pressures, three draw wire sensors for cylinder elongations, one inertial measurement unit for measurement of swing angle and one logger unit for data acquisition and storage. Logger unit, equipped with SD card module and 12-bit AD converter, is based on Atmega328 microcontroller, which allows for usage of Arduino IDE and already developed libraries. The system was tested in a laboratory to determine its accuracy, resolution and usable sample rate. Cylinder pressure can be measured in range 0-500 bar with excellent accuracy of 0.026 % FSO and 0.15 bar resolution. Cylinder elongation can be measured in range 0-2300 mm with accuracy of 0.26 % FSO and 0.58 mm resolution. Swing angle measurement accuracy is 1.5° per circle. Usable sample rate of the system is found to be 39 Hz-588 Hz, depending on the logger executing code.

1A1-Q12 ホイールローダによる大塊掬い取り手法の提案(建設・解体ロボット・メカトロニクス)

We have proposed scooping homogeneous rock piles automatically by wheel loader until now. However actual rock piles are not homogeneous because they include massive rocks which haven't been considered yet. So, a new method of scooping of a massive rock in rock piles is proposed. As a fundamental experiment, horizon reaction forces acting on the bucket are measured during the scooping of two type models assumed massive rock by a miniature wheel loader, and their horizon reaction forces are formulated. In addition, the amount of energy required to scoop a massive rock is calculated to design an optimal bucket trajectory.

Loading Excavator Analysis for Trajectory Control Improvement

Automatic control assistance to improve the digging and bucket-filling trajectory of loading excavators is moving from concept to industrial applications. Directly controlling the path of the bucket instead of controlling individual hydraulic joints by human operators is possible using robotics. The task may be achieved by redefining the excavator kinematics and enhancing it with a software-controlled “virtual kinematics.” It is necessary to determine what type of kinematics transformation of the excavator would be best from its “as-built” motion pattern to an “as-desired” machine for the loading tasks. If known, this loading kinematics then can be programmed into the machine motion control system. Since no loading movement and bite is exactly the same as the previous one, a man-machine interface is needed for easy access for adjustment. Such loading task is analyzed for cycle time, energy consumption, and machine wear. Static and dynamic forces, torques, energy, and power consumption is evaluated for any given digging bucket trajectory for an EX3500 Hitachi excavator. Typical digging trajectories from published data are used to evaluate the potential benefits of a new bucket loading kinematics by “bucket steering,” a motion kinematics which requires two joysticks control actions only. One joystick serves for interactive adjustment to the trajectory shape, and the other is for loading velocity control. The paper describes the potential benefit to mining front shovel operations.

Bucket trajectory classification of mining excavators

Abstract Large mining excavators impose numerous challenges to the operator during a dig. A semi-automated or fully automated machine that could assist the operator during excavation would positively affect efficiency, ore selectivity, and reduce machine wear at the same time. Besides, the dependence on operator skills and attentiveness will be reduced. In order to realize any control on an excavator, it is prudent to know the dig patterns followed by the operator during a real time dig. This paper aims to classify the dig by analyzing the actual task performed by the operator. The trajectories are classified based on the location and angle of the bucket. Both 2-dimensional and 3-dimensional analyses of the bucket trajectory were performed on a EX 3500 mining excavator at the Newmont open pit mine using Arial Performance Analysis System (APAS).

휠로더 굴착 자동화를 위한 버킷 부하특성 연구

The front end wheel loader is widely used for the loading of materials in mining and construction fields. It has repetitive digging, loading and dumping procedures. The bucket is subjected to large resistance force from the soil during scooping. We considered the soil reaction force characteristics from scooping procedure, the protection by overload and automatic scooping mode algorithm. The main topic of this paper is the analysis of the soil reaction force characteristics. The analysis of soil mechanics is carried out and the developed soil model is verified by experimental results from the simplified experimental equipment. A simplified model of the soil shape and bucket trajectory is used to determine the scooping direction based on an estimation of the resistance force applied on the bucket during the scooping motion. In the future, this model will be used for the generation of an appropriate path for the wheel loader automation.

Ratonal positioning of a bucket hinge

1. For the conditions of maximum filling with minimum energy consumption, the optimal bucket hinge height is about half the radius of swivel. 2. Good filling of the bucket can be obtained not only with combined but also with separate scooping, given the necessary bucket trajectory, by adjusting the hinge height.