Continuous trajectory planning method for excavator working device

By adopting a continuous trajectory planning method on the excavator, using simulation models, particle swarm optimization and deep reinforcement learning, the problems of high operation strength and low efficiency of traditional excavators are solved, and efficient and safe automated operations are achieved.

CN119692582AActive Publication Date: 2025-03-25JILIN UNIVERSITY
6 Cites 1 Cited by

Patent Information

Application Number
CN202411764721.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-04
Publication Date
2025-03-25
Estimated Expiration
2044-12-04

AI Technical Summary

Technical Problem

Traditional excavators rely on manual operation and face the problems of high strength, harsh environment, high risks and shortage of skilled operators. Single excavation trajectory planning cannot meet the needs of real-time and continuity.

Method used

The continuous trajectory planning method of excavator working device is adopted, including establishing a simulation model, overall task decomposition, curve interpolation method to plan a single trajectory, particle swarm optimization algorithm multi-objective optimization, deep reinforcement learning TD3 algorithm training model, and generating a complete mining trajectory of the target area.

Benefits of technology

It improves the efficiency and safety of excavator operations, realizes real-time trajectory planning and adaptability improvement, and reduces dependence on manual operations.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention is suitable for the technical field of excavator operation, and provides a continuous trajectory planning method for an excavator working device. According to the method, a regional mining strategy is adopted, and a single mining task is clearer and more controllable through clear task decomposition. The strategy is beneficial to optimizing the mining path and reducing unnecessary repeated mining, so that the mining efficiency is improved; a TD3 algorithm based on deep reinforcement learning is introduced, and the application of the algorithm improves the real-time performance and adaptability of trajectory planning, so that the excavator can quickly respond to various complex operation conditions and environment changes, and efficient operation is ensured; automatic trajectory planning is achieved, and dependence on manual operation is reduced. And through automatic planning, the accuracy and stability of operation are improved, and the safety of operation is further improved.
Need to check novelty before this filing date? Find Prior Art