Real-time task-oriented continuous digging trajectory planning for excavator arms

Yao, Zongwei; Zhao, Shuping; Tan, Xiaodan; Wei, Wen‐Cheng J.; Wang, Yong

doi:10.1016/j.autcon.2023.104916

Cited by 13 publications

(2 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By leveraging the well-established applications of image analysis in deep learning, OSA T et al [22] investigated mining tasks through deep image learning techniques, while Kim et al [23] developed a visual-based model for recognizing mining actions in job statistics. On the other hand, YAO et team [24] generated continuous excavation trajectories employing PINN. Furthermore, ZHAO et al [25] also discovered that, under optimally planned trajectories, the fluctuation of excavation angles in unmanned excavators is greater than that observed during manual operations.…”

Section: Introductionmentioning

confidence: 99%

Mining Trajectory Planning of Unmanned Excavator Based on Machine Learning

Jin,

Gong,

Zhao

et al. 2024

Mathematics

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

Mining Trajectory Planning of Unmanned Excavator Based on Machine Learning

Jin,

Gong,

Zhao

et al. 2024

Mathematics

View full text Add to dashboard Cite

show abstract

“…With the continuous expansion of the application scope of machine learning, the combination of machine learning and metaheuristic algorithms is gradually emerging in trajectory planning research. Yao et al [21] used a multi-objective PSO algorithm to optimize cyclic excavation trajectories for the realtime operation tasks of an excavator; they further used the optimization results as training samples to construct a physicsinformed neural network model and build the task-planning framework for autonomous operation. To automatically generate high-efficiency operation trajectories, Guo et al [22] combined data-driven imitation learning and model-based trajectory optimization.…”

Section: Introductionmentioning

confidence: 99%

Time‐energy consumption optimal path‐constrained trajectory planning of excavator robotics

Zhang,

Sun,

Sun

et al. 2024

The Journal of Engineering

View full text Add to dashboard Cite

Reasonable operation of each excavator joint under path constraints directly affects operation efficiency and energy consumption. Efficiency and energy consumption are considerably important performance indicators, particularly for large equipment, such as excavators. Therefore, we propose a quadratic trajectory optimization method based on time–energy consumption. With the pseudo‐path velocity, acceleration, and equivalent convex jerk as constraints, the interior‐point method was used to obtain the time–energy consumption optimal trajectory of an excavator. The time and energy consumption values for different weight coefficients were obtained, and the optimal trajectory planning of the excavator was achieved. Furthermore, the simulation results of the proposed method for lifting 70 kg of materials for a weight coefficient of 0.5 were compared with the result of second‐order cone programming. Experimental results showed that using proposed method to plan the motion of each joint reasonably and effectively reduced the pseudo‐path jerk, acceleration, and velocity peaks by 40.67%, 25.03%, and 12.54%, respectively, ensuring smooth excavator movement. It also improved the working efficiency of the excavator; reduced unnecessary energy consumption; and improved the stability, efficiency, and energy saving of the autonomous operation of the excavator.

show abstract