Unmanned Excavator Research Articles

Physics-Informed Neural Networks-Based Online Excavation Trajectory Planning for Unmanned Excavator

As a large-scale mining excavator, the electric shovel (ES) has been extensively employed in open-pit mines for overburden removal and mineral loading. In the development of unmanned operations for ES, dynamic excavation trajectory planning is essential, as it directly influences operational efficiency and energy consumption by guiding the dipper during excavation. However, conventional optimization-based methods for excavation trajectory planning typically start from scratch, resulting in a time-consuming process that fails to meet real-time requirements. To address this challenge, we propose an innovative online trajectory planning framework based on physics-informed neural networks (PINNOTP) that utilizes advanced data-driven techniques. The input to PINNOTP consists of on-site working conditions, including the initial state of the ES and the material surface being excavated. The output is a smooth, polynomial-based curve that serves as the reference trajectory for the dipper. To ensure smooth execution of the generated trajectory, prior domain knowledge—such as physics-based target-oriented constraints, essential system dynamics, and mechanical constraints—is explicitly incorporated into the loss function during training. A case study is presented to validate the proposed method, demonstrating that PINNOTP effectively addresses the challenges of online excavation trajectory planning.

MPC motion control of boom descending of unmanned excavator based on regenerative valve

The control precision of the working device has always been a challenging aspect in unmanned excavator research due to the adoption of a triangular drive mode and a complex hydraulic system in the working mechanism. The article focuses on the research of autonomous control for the downward motion of a robotic arm in an unmanned excavator equipped with a regeneration valve. The study aims to achieve precise tracking of fast movement trajectories during operator manipulation, utilizing Model Predictive Control (MPC). Furthermore, the exceptional disturbance rejection capability of the MPC algorithm is demonstrated through interference application. A comprehensive model considering mechanical, hydraulic, and electrical factors is established for the excavator boom. The MPC algorithm is applied to achieve precise control over the boom descent process, providing a foundation for motion control in unmanned excavators. This article presents a theoretical analysis to elucidate the robustness principle of MPC in the descent control of uncertain dynamic arms. By incorporating real parameters, we successfully track predetermined planned paths at different speeds and validate them on a 20-ton hydraulic excavator. The results demonstrate that the MPC control algorithm accurately manipulates the boom descent motion while exhibiting excellent disturbance rejection performance. Compared to PID control algorithms, MPC offers wider target adaptability range and better disturbance rejection performance, making it suitable for rapid application in controlling working devices of unmanned excavators.

Mining Trajectory Planning of Unmanned Excavator Based on Machine Learning

Trajectory planning plays a crucial role in achieving unmanned excavator operations. The quality of trajectory planning results heavily relies on the level of rules extracted from objects such as scenes and optimization objectives, using traditional theoretical methods. To address this issue, this study focuses on professional operators and employs machine learning methods for job trajectory planning, thereby obtaining planned trajectories which exhibit excellent characteristics similar to those of professional operators. Under typical working conditions, data collection and analysis are conducted on the job trajectories of professional operators, with key points being extracted. Machine learning is then utilized to train models under different parameters in order to obtain the optimal model. To ensure sufficient samples for machine learning training, the bootstrap method is employed to adequately expand the sample size. Compared with the traditional spline curve method, the trajectories generated by machine learning models reduce the maximum speeds of excavator boom arm, dipper stick, bucket, and swing joint by 8.64 deg/s, 10.24 deg/s, 18.33 deg/s, and 1.6 deg/s, respectively; moreover, the error does not exceed 2.99 deg when compared with curves drawn by professional operators; and, finally, the trajectories generated by this model are continuously differentiable without position or velocity discontinuities, and their overall performance surpasses that of those generated by the traditional spline curve method. This paper proposes a trajectory generation method that combines excellent operators with machine learning and establishes a machine learning-based trajectory-planning model that eliminates the need for manually establishing complex rules. It is applicable to motion path planning in various working conditions of unmanned excavators.

Design and development of intelligent unmanned construction system for open-pit mine

China’s huge mineral outputs support the national economy and people’s livelihood. However, the mining operation is rough and the safety accident happens frequently. Consequently, the demand for unmanned mining operations is urgent, which is of great significance to safe production. Facing the complex operation scenarios of open-pit mines, an unmanned construction system framework is proposed based on intelligent construction machinery. On this basis, an unmanned excavation subsystem is designed and developed based on the hydraulic excavator, and an unmanned transportation subsystem is designed and developed based on the mining truck. Equipped with advanced sensors and controllers, the unmanned excavation subsystem and the unmanned transportation subsystem possess sensing, decision-making, and control abilities by using AI algorithms. The experiment of the unmanned construction systems is successfully conducted on the open-pit mine test site. This study provides equipment and technical support for improving the intelligent level of mine construction and ensuring safe production for the open-pit mine.

Comprehensive Performance Evaluation of an Unmanned Excavator Based on Signal Stability Extraction

The comprehensive performance of unmanned excavators is crucial for the development and optimization of the field of construction machinery. To effectively improve the unmanned excavator to meet the needs of the market, it is imperative to quantify the evaluation method of the comprehensive performance of unmanned excavators. In this study, an evaluation method combining a fuzzy analytic hierarchy process and multivariate image area analysis method is proposed. Firstly, based on the feature extraction of the signal stability of the unmanned excavators, fifteen evaluation indexes were proposed. Then, the case study is used to obtain the scores corresponding to these indexes. The fuzzy analytic hierarchy process is applied to determine the relative weight of the selected evaluation criteria, in which the uncertain and imprecise judgments of decision makers are converted into fuzzy numbers. At the same time, the braking performance of the three types of unmanned excavators was comprehensively evaluated and ranked using the multivariate image area analysis method as an empirical example. Finally, a weight analysis is performed to check the robustness of the ranking results. The results show that the proposed method is effective and feasible. It provides a reference for the performance improvement and efficiency optimization of unmanned excavators.

Model Predictive Control for Unmanned Excavator Based on Skilled Operator’s Operation Trajectory

Model Predictive Control for Unmanned Excavator Based on Skilled Operator’s Operation Trajectory

Lever Working Area Mapping and Safe Posture Return Algorithm for Improvement of Unmanned Excavator Robot System

건설용 굴착기는 토목 및 건축 공사에 자주 쓰이는 중장비 기계로 현장에서 사망사고 재해에 많은 비율을 차지하고 있다. 건설 현장의 사고율을 줄이고자, 기존에 상용화된 굴착기를 활용하여 무인화하는 방식에 대한 연구가 진행되고 있다. 해당 시스템의 문제점으로는 레버 작업 공간과 원격 조종 모듈의 작업 공간이 불일치로 인해 굴착 작업 범위에 제한을 받고 있다. 본 연구에서는 무개조 기반 굴착기 무인화 로봇 시스템을 활용하고자 하며, 기존에 문제가 되었던 작업 영역의 불일치를 해결하고자 레버 작업 공간의 맵핑 알고리즘을 개선하였다. 또한 원격 조종 시, 시야 확보의 어려움이나 잦은 사고 발생 위험성을 해결하고자 안전 자세 복귀 알고리즘을 개발하였다. 레버 작업 공간의 맵핑 알고리즘을 개선하여 기존 대비 5.8~17.4% 작업 공간이 확장되었으며, 안전 자세 복귀 알고리즘을 무인화 로봇 시스템에 적용하여 내부 실험을 통해 검증하였다. 복잡한 굴착기 작업이나 작업시간이 길어질 경우, 캐빈 타입의 원격 조종 시스템을 이용하여 5m 배수로 작업 기준으로 4.6~7% 작업 효율을 보였으며, 비숙련자에게는 영상 지원개수가 많을수록 43~71%의 작업 시간이 감소하는 것을 확인하였다.

Interactive Physically Based Simulation of Roadheader Robot

Roadheader is an engineering robot widely used in underground engineering and mining industry. Interactive dynamics simulation of roadheader is a fundamental problem in unmanned excavation and virtual reality training. However, current research is only based on traditional animation techniques or commercial game engines. There are few studies that apply real-time physical simulation of computer graphics to the field of roadheader robot. This paper aims to present an interactive physically-based simulation system of roadheader robot. To this end, an improved multibody simulation method based on generalized coordinates is proposed. First, our simulation method describes robot dynamics based on generalized coordinates. Compared to state-of-the-art methods, our method is more stable and accurate. Numerical simulation results showed that our method has significantly less error than the game engine in the same number of iterations. Second, we adopt the symplectic Euler integrator instead of the conventional fourth-order Runge-Kutta (RK4) method for dynamics iteration. Compared with other integrators, our method is more stable in energy drift during long-term simulation. The test results showed that our system achieved real-time interaction performance of 60 frames per second (fps). Furthermore, we propose a model format for geometric and robotics modeling of roadheaders to implement the system. Our interactive simulation system of roadheader meets the requirements of interactivity, accuracy and stability.

Design of Unmanned Cable Shovel Based on Multiobjective Co-Design Optimization of Structural and Control Parameters

Abstract In autonomous excavation, design and optimization of the unmanned cable shovels (UCS) are important issues in the full life cycle of the equipment. However, the design of physical structure and control system of the UCS are performed at different stages, which makes it difficult for traditional sequential optimization strategy to generate global optimal solution. To enhance the working performance of the UCS, in this article, a multistage multiobjective (MSMO) co-design optimization strategy is proposed to perform global optimization considering excavation and loading processes by simultaneous optimization for the structure and control parameters of UCS. Under this framework, first, a point-to-point motion model based on 4-5-4 piecewise polynomial is proposed to describe the motion trajectory, and the dynamical model of the working device is established to predict the energy consumption in the working process. Then, the physical and geometric constraints in practical working are analyzed, and a multiobjective optimization model considering excavation and loading processes is established to improve mining efficiency and reduce energy consumption in unmanned excavation scenarios. Finally, the structural and control parameters are optimized synchronously to generate optimal physical structure, excavation, and loading trajectory. Numerical results show that the proposed MSMO co-design method can further improve the operational performance of UCS compared with the traditional optimization strategy.

버킷 위치 제어용 입력성형기에 관한 연구

To perform work of unmanned excavator, such as leveling, stumping and digging, working paths had to generate and motion of bucket had to follow this generated paths. However the motion of bucket had moved like undamped system when bucket was far from the body of excavator. In this condition, the movement of bucket couldn’t follow the suggested path easily due to relatively huge mass and spring constant. To adjust the path of bucket, the unmaned excavator needs extra controller that can control a displacement of the bucket with feed back signal. However, this solution requires extra cost and it also increases energy loss to control itself. An input shaper is a feed forward controller that can reduce the residual vibration with reference input modification. This controller doesn’t need any extra equipment and energy that improve the performance of the system. However, hydraulic cylinder system still has problem where it has a huge difference between natural frequency of the system and frequency response of actuator. Indeed, hydraulic actuator is too slow to use an input shaperBR The purpose of this paper is to suggest an input shaper that can import a hydraulic system. To satisfy this purpose, at first, kinematics and inverse kinematics of the excavator was induced. The position of the bucket was controlled by hydraulic cylinders which can be assumed like 3-axis robot. This mechanical analysis can be used to set up the command signal. After that, an input shaper was designed to reduce the residual vibration. A boom cylinder has residual vibration when bucket cylinder was moved despite a damping effect of this system. A residual vibration can be assumed a second order system and it can be adjusted by an input shaper. This result was compared with path trajectory on a fifth order polynomial. After that, the suggested input shaper was induced from the principal of the input shaper. Consequently, the suggested input shaper was verified with computer simulation.

Development of Unmanned Excavator Vehicle System for Performing Dangerous Construction Work.

Of all the machinery and equipment used on construction sites, excavators are responsible for the greatest number of fatal accidents. Excavation is an inherently risky process due to imprecise work processes and the unstable external environment on most work sites. The resulting accidents cause serious injuries that threaten the lives of not only the excavator pilots but also those working around them. In this study, we propose a mechanical device that is capable of operating the excavator remotely from a nearby safe location such as a site office. To ensure worker safety and at the same time boost the productivity of excavation operations, data from 3D scanners, cameras, and sensors were combined to create a detailed 3D picture of the area surrounding the excavation site to guide a remotely operated excavating system. Rather than modifying the excavator itself, a removable manipulator was mounted on the joystick in the excavator’s cockpit. Our proposed system was tested on a standard commercial excavator to verify its performance for a real-world excavation task.

Modeling of Operation Function of the Unmanned Excavator in the Deterministic Surfacing Process

Unmanned excavator has been developed for the improvement of operation efficiency and the decrease of economics cost, on which the researches have attracted widely research enthusiasms. Deterministic surfacing method is an effective technique for the intelligent control of the unmanned excavator, and the key point is modeling of operation function. Through analysis of operation process, kinematic trajectory of the relieving tool is obtained. By simplifying structures and parameters of the operation system, both cross-sectional line and 3D feature which represent character of the operation function are obtained. Modeling of the operation function will promote application of the unmanned excavator and supply experience for advanced control of other unmanned construction machines.

자동화 굴삭로봇의 운용단위 작업계획수립을 위한 로컬영역설계모듈 개발

오늘날 숙련된 굴삭기 운전자의 부족현상은 갈수록 심화되고 있으며, 자원개발 및 새로운 생활공간 창출 등을 목적으로 운전자가 접근하기 어려운 극한환경에서 토공작업의 필요성이 증가함에 따라 전 세계적으로 토공완전자동화를 위한 무인화 굴삭로봇 개발의 노력이 경주되고 있다. 국내에서도 지난 2006년 말부터 국토해양부 건설기술혁신사업의 일환으로 '지능형 굴삭시스템' 연구단을 구성하여 연구를 지속하고 있다. 본 논문에서는 지능형 굴삭시스템의 작업계획생성시스템이 갖추어야 할 세부요소기술 중, 굴착작업의 위치, 범위, 목표, 순차 등 굴삭로봇의 운용단위 작업명령정보를 생성하기 위한 정보화단위를 제공하는 로컬영역설계모듈의 연구개발내용에 대하여 설명한다. 로컬영역의 설계는 굴삭로봇의 제원, 작업메커니즘, 휴리스틱 및 구조적안전성 등 여러 영향요소가 고려되어야 안전하고 효율적인 굴착작업을 보장하는 작업계획을 생성할 수 있다. 따라서 로컬영역의 설계요소를 분석하기 위하여 현장조사를 통한 개념적 설계를 수행하고, 상세설계를 통해 설계변수를 도출하였으며, 휴리스틱 및 구조적 해석요건을 만족하도록 설계내용을 정량화하였다. 마지막으로 로컬영역설계모듈을 개발하기 위한 알고리즘을 구축하고, 개발된 모듈을 검증하였다. Today, a shortage of the skilled operator has been intensified gradually and the necessity of an earthwork in extreme environment operators are difficult to access is increasing for the purpose of resource development and new living space creation. For this reason, an effort to develop an unmanned excavation robot for fully automated earthwork system is continuing globally. In Korea, a research consortium called 'Intelligent Excavation System' has been formed since 2006 as a part of Construction Technology Innovation Program of Ministry of Land, Transport and Maritime Affairs of Korea. Among detailed technologies of the Task Planning System is one of the core technologies of IES, this paper explains research and development process of the Local Area Design Module, which provides informatization unit to create automated excavators' work command information at operation level such as location, range, target, and sequence for excavation work. Designing of Local Area should be considered various influential factors such as excavator's specification, working mechanism, heuristics, and structural stability to create work plan guaranteed safety and effectiveness. For this research, conceptual and detail design of the Local Area is performed for analyzing design element and variable, and quantization method of design specification corresponding with heuristics and structural safety is generated. Finally, module is developed through constructed algorithm and developed module is verified.

Field Measurements and Finite-Element Method Simulation of a Tunnel Shaft Constructed by Pneumatic Caisson Method in Shanghai Soft Ground

Characterized by unmanned excavation and remote controlling, the new pneumatic caisson (NPC) method has advantages in deep excavation such as deep shield tunnel shafts and some underground construction close to the existing structures or facilities. When adopted in urban areas, it is very important to control the ground deformation during a caisson construction. For this purpose, field measurements of ground deformation were conducted during a tunnel shaft construction in Shanghai soft ground, in which the NPC method was used. On the basis of the particular construction procedure of a pneumatic caisson, one kinematic mechanical model was proposed for evaluating the influence of NPC construction on the surrounding strata. This model was incorporated into a finite-element (FE) program. By comparing the FE-predicted results of the proposed model and the field measurements, the accuracy and reliability of this model were verified.

Modelling and control of an unmanned excavator vehicle

This paper investigates the modelling and control of a full-scale excavator vehicle. A detailed analytical model for an unmanned excavator vehicle is developed. The model takes into account the kinematics and dynamics of the mobile platform (vehicle) and the excavation arm (links and hydraulic system). The model describes the dynamic relationship between the operator input commands (fuelling and joystick commands to excavation arm and steering lever) and the trajectories and forces of the excavator vehicle. The dynamic model of the excavation arm system is validated against measured data. The validation of the model is conducted in collaboration with QinetiQ Limited (the new science and technology company formed from the major part of DERA, the British Government's defence research and development organization). A unified model is important for design of control strategies, since in order to move the bucket of a mobile excavator, movements of the entire vehicle are required. A key requirement for automating the excavation task is automated trajectory tracking, and a proportional-integral-derivative (PID) controller for trajectory tracking is developed and tested. It is noted that even though the results presented in this paper are focused on a particular excavator, the research is generic and can be adapted to any tracked ground vehicle with an on-board closed-chain manipulator.

Modelling and control of an unmanned excavator vehicle

This paper investigates the modelling and control of a full-scale excavator vehicle. A detailed analytical model for an unmanned excavator vehicle is developed. The model takes into account the kinematics and dynamics of the mobile platform (vehicle) and the excavation arm (links and hydraulic system). The model describes the dynamic relationship between the operator input commands (fuelling and joystick commands to excavation arm and steering lever) and the trajectories and forces of the excavator vehicle. The dynamic model of the excavation arm system is validated against measured data. The validation of the model is conducted in collaboration with QinetiQ Limited (the new science and technology company formed from the major part of DERA, the British Government's defence research and development organization). A unified model is important for design of control strategies, since in order to move the bucket of a mobile excavator, movements of the entire vehicle are required. A key requirement for automating the excavation task is automated trajectory tracking, and a proportional-integral-derivative (PID) controller for trajectory tracking is developed and tested. It is noted that even though the results presented in this paper are focused on a particular excavator, the research is generic and can be adapted to any tracked ground vehicle with an on-board closed-chain manipulator.