Deep Learning-Based Autonomous Excavation: A Bucket-Trajectory Planning Algorithm

Abstract

The increased risk to the safety of excavator personnel and difficulty in training them, combined with a manpower shortage, have led to an increased demand for machine automation. This study applies a long short-term memory algorithm for automating a bucket-tip trajectory planning AI system. Unlike other autonomous excavation techniques, the proposed approach in this study performs the buckettrajectory planning of the excavator without prior knowledge of nonlinear bucket-soil interaction dynamics during excavation, which requires precise adjustment of parameters with the heuristic analysis of correlation between them. Based on data acquisition from excavation of excavator experts, this method uses the threedimensional point cloud of terrain and bucket motion data in excavation process for training and application of the AI. Especially, we transform the point cloud, which comprises massive number of points and increases the computation complexity, into the much smaller number of values, which are sufficient for representing the three-dimensional shape of target terrain. To ensure safety against collision with underground obstacles, a collision avoidance algorithm is applied to prevent crashes during excavations along the given path, based on continuous monitoring of the pressure in the excavator's hydraulic cylinder. Comparative experiments reveal that the bucket-tip trajectory planning AI system with the collision avoidance algorithm generates a traceable trajectory for the machine controller, equipped in the excavator, and yields the desired excavation volume and lead time without collision, regardless of the topographic change caused through successive excavations.INDEX TERMS Automated excavation, bucket-tip trajectory planning, collision avoidance algorithm, field robots, long short-term memory, point cloud data

Mining Trajectory Planning of Unmanned Excavator Based on Machine Learning

“…Machine learning is currently an increasingly mature solution. Several scholars have already conducted research on motion trajectory generation using machine learning techniques [15,16,20,23,33,34]. However, this paper distinguishes itself by employing bootstrap resampling [32] to augment the operator's limited sample data, resulting in relatively conservative yet diverse samples.…”

Predictive Algorithm Based Control Method for Safe Operation of Excavators in a Restricted Area

“…[3][4] J Huh and Jangho Bae propose an algorithm that applies a long and short-term memory algorithm to automate a barrel-tip trajectory planning artificial intelligence (AI) system. [5] Since the bucket is a key component of the excavator, real-time and accurate bucket attitude estimation plays a vital role in improving the intelligence level of mining excavators. The existing bucket attitude estimation method is achieved by installing multiple non-visual sensors.…”

The Learning Trajectory Based on STEM of Elementary School Pupils’ in Solving Proportion Material: Didactical Design-Research

“…From its origins in ancient geometry to its applications in algebra, statistics, and various real-world disciplines, the concept of proportion remains essential in mathematics education and problem-solving (Haggarty, 2002). Proportion in mathematics dates back to ancient times and has evolved with new perspectives and technological advances, making it essential in mathematics (Huh, 2023). The concept of proportionality is highly significant in many aspects of life, including mathematics, natural sciences, engineering, and so on (Zou, 2023).…”