Compliant Motion Planning Integrating Human Skill for Robotic Arm Collecting Tomato Bunch Based on Improved DDPG
Plants · 20.02.2025 · 14 (5) · 634
DOI: 10.3390/plants14050634 ↗Kurz gefasst
Fachartikel in der Zeitschrift Plants, online erschienen am 20.02.2025. Verfasst von Yifan Zhang und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Beijing Nova Program, China International Science and Technology Cooperation, BAAFS Innovation Capacity Building Project.
Abstract (Originalsprache)
Dexterous manipulation and gradual placement are crucial for preserving fruit integrity during harvesting. Addressing the limitations of conventional path planning methods in learning manual compliant skills, we propose a novel method for tomato bunch collection that integrates human-robot skill transfer with Deep Deterministic Policy Gradient (DDPG). In our method, a demonstrator manually guided the robotic arm using an existing tomato collection mechanism, with spatial trajectories recorded as demonstration paths. We then developed an enhanced DDPG-Z model that incorporates human skill replay for pre-training, expert reward regression loss to stabilize pre-training, and dynamic step-length returns to balance short- and long-term rewards. Subsequently, the agent was trained to minimize the deviations of key points between the demonstration paths and actual paths, effectively approximating human operations. In a highly realistic simulation environment, our method achieved a 25% improvement in convergence speed, a 10.3% increase in post-convergence reward, and a 51.3% boost in destination accuracy compared to the case without the demonstrations, whereas classical models such as DDPG, SAC (Soft Actor-Critic), and TD3 (Twin Delayed Deep Deterministic Policy Gradient) failed to converge within the prescribed episodes. This work provides valuable insights for enhancing the compliant operational performance of agricultural robots.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China.
- Intelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China.
- Beijing Key Laboratory of Intelligent Equipment Technology for Agriculture, Beijing 100097, China.
ORCID-Profile: Qingchun Feng
Förderung
- Beijing Nova Program
- China International Science and Technology Cooperation
- BAAFS Innovation Capacity Building Project
- Youth Research Foundation
- Beijing Natural Science Foundation
- Major science and technology support project of Hebei Province
Zitieren
APA
Zhang, Y., Li, Y., Feng, Q., Sun, J., Peng, C., Gao, L., & Chen, L. (2025). Compliant Motion Planning Integrating Human Skill for Robotic Arm Collecting Tomato Bunch Based on Improved DDPG. Plants, 14(5), 634. https://doi.org/10.3390/plants14050634
Vancouver
Zhang Y, Li Y, Feng Q, Sun J, Peng C, Gao L, et al. Compliant Motion Planning Integrating Human Skill for Robotic Arm Collecting Tomato Bunch Based on Improved DDPG. Plants. 2025;14(5):634. doi:10.3390/plants14050634
BibTeX
@article{Zhang2025,
author = {Zhang, Yifan and Li, Yajun and Feng, Qingchun and Sun, Jiahui and Peng, Chuanlang and Gao, Liangzheng and Chen, Liping},
title = {Compliant Motion Planning Integrating Human Skill for Robotic Arm Collecting Tomato Bunch Based on Improved DDPG},
journal = {Plants},
year = {2025},
volume = {14},
number = {5},
pages = {634},
doi = {10.3390/plants14050634}
}
EUVIMED