EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Reinforcement Learning for Adaptive Robotic Grasping and Post-Grasp Manipulation in Simulated Dynamic Environments

Henrique C. Ferreira, Ramiro S. Barbosa

Future Internet · 26.09.2025 · 17 (10) · 437

DOI: 10.3390/fi17100437 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Future Internet, online erschienen am 26.09.2025. Verfasst von Henrique C. Ferreira und 1 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This article presents a deep reinforcement learning (DRL) approach for adaptive robotic grasping in dynamic environments. We developed UR5GraspingEnv, a PyBullet-based simulation environment integrated with OpenAI Gym, to train a UR5 robotic arm with a Robotiq 2F-85 gripper. Soft Actor-Critic (SAC) and Proximal Policy Optimization (PPO) were implemented to learn robust grasping policies for randomly positioned objects. A tailored reward function, combining distance penalties, grasp, and pose rewards, optimizes grasping and post-grasping tasks, enhanced by domain randomization. SAC achieves an 87% grasp success rate and 75% post-grasp success, outperforming PPO 82% and 68%, with stable convergence over 100,000 timesteps. The system addresses post-grasping manipulation and sim-to-real transfer challenges, advancing industrial and assistive applications. Results demonstrate the feasibility of learning stable and goal-driven policies for single-arm robotic manipulation using minimal supervision. Both PPO and SAC yield competitive performance, with SAC exhibiting superior adaptability in cluttered or edge cases. These findings suggest that DRL, when carefully designed and monitored, can support scalable learning in manipulation tasks.

Zitieren

APA

Ferreira, H. C., & Barbosa, R. S. (2025). Deep Reinforcement Learning for Adaptive Robotic Grasping and Post-Grasp Manipulation in Simulated Dynamic Environments. Future Internet, 17(10), 437. https://doi.org/10.3390/fi17100437

Vancouver

Ferreira HC, Barbosa RS. Deep Reinforcement Learning for Adaptive Robotic Grasping and Post-Grasp Manipulation in Simulated Dynamic Environments. Future Internet. 2025;17(10):437. doi:10.3390/fi17100437

BibTeX
@article{Ferreira2025,
  author = {Ferreira, Henrique C. and Barbosa, Ramiro S.},
  title = {Deep Reinforcement Learning for Adaptive Robotic Grasping and Post-Grasp Manipulation in Simulated Dynamic Environments},
  journal = {Future Internet},
  year = {2025},
  volume = {17},
  number = {10},
  pages = {437},
  doi = {10.3390/fi17100437}
}
Kostenlos starten →