Sim2Real Deep Reinforcement Learning of Compliance-based Robotic Assembly Operations

Petrovic, Oliver; Schaper, Lukas; Roggendorf, Simon; Storms, Simon; Brecher, Christian

doi:10.1109/mmar55195.2022.9874304

Cited by 3 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Simulating to real-world transfer (Sim2Real) has become a cornerstone in robotics, proving invaluable for training agents in simulated settings before their real-world application. This method's efficacy in translating simulated learning to practical scenarios is comprehensively analyzed in references [26,27], with specific applications to mobile robotics discussed in [28,29]. Extending beyond traditional robotics, Sim2Real has also facilitated advancements in diverse areas.…”

Section: State Of Artmentioning

confidence: 99%

RL-Based Sim2Real Enhancements for Autonomous Beach-Cleaning Agents

Quiroga,

Hermosilla,

Varas

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

This paper explores the application of Deep Reinforcement Learning (DRL) and Sim2Real strategies to enhance the autonomy of beach-cleaning robots. Experiments demonstrate that DRL agents, initially refined in simulations, effectively transfer their navigation skills to real-world scenarios, achieving precise and efficient operation in complex natural environments. This method provides a scalable and effective solution for beach conservation, establishing a significant precedent for the use of autonomous robots in environmental management. The key advancements include the ability of robots to adhere to predefined routes and dynamically avoid obstacles. Additionally, a newly developed platform validates the Sim2Real strategy, proving its capability to bridge the gap between simulated training and practical application, thus offering a robust methodology for addressing real-life environmental challenges.

show abstract

Section: State Of Artmentioning

confidence: 99%

RL-Based Sim2Real Enhancements for Autonomous Beach-Cleaning Agents

Quiroga,

Hermosilla,

Varas

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

Deep Visual-guided and Deep Reinforcement Learning Algorithm Based for Multip-Peg-in-Hole Assembly Task of Power Distribution Live-line Operation Robot

Zheng,

Ai,

Wang

et al. 2024

J Intell Robot Syst

View full text Add to dashboard Cite

The inspection and maintenance of power distribution network are crucial for efficiently delivering electricity to consumers. Due to the high voltage of power distribution network lines, manual live-line operations are difficult, risky, and inefficient. This paper researches a Power Distribution Network Live-line Operation Robot (PDLOR) with autonomous tool assembly capabilities to replace humans in various high-risk electrical maintenance tasks. To address the challenges of tool assembly in dynamic and unstructured work environments for PDLOR, we propose a framework consisting of deep visual-guided coarse localization and prior knowledge and fuzzy logic driven deep deterministic policy gradient (PKFD-DPG) high-precision assembly algorithm. First, we propose a multiscale identification and localization network based on YOLOv5, which enables the peg-hole close quickly and reduces ineffective exploration. Second, we design a main-auxiliary combined reward system, where the main-line reward uses the hindsight experience replay mechanism, and the auxiliary reward is based on fuzzy logic inference mechanism, addressing ineffective exploration and sparse reward in the learning process. In addition, we validate the effectiveness and advantages of the proposed algorithm through simulations and physical experiments, and also compare its performance with other assembly algorithms. The experimental results show that, for single-tool assembly tasks, the success rate of PKFD-DPG is 15.2% higher than the DDPG with functionized reward functions and 51.7% higher than the PD force control method; for multip-tools assembly tasks, the success rate of PKFD-DPG method is 17% and 53.4% higher than the other methods.

show abstract

Robotic Assembly of Shaft Sleeves in Different Sizes Based on Deep Reinforcement Learning

Ma,

2024

Int. J. Precis. Eng. Manuf.

View full text Add to dashboard Cite

Sim2Real Deep Reinforcement Learning of Compliance-based Robotic Assembly Operations

Cited by 3 publications

References 12 publications

RL-Based Sim2Real Enhancements for Autonomous Beach-Cleaning Agents

RL-Based Sim2Real Enhancements for Autonomous Beach-Cleaning Agents

Deep Visual-guided and Deep Reinforcement Learning Algorithm Based for Multip-Peg-in-Hole Assembly Task of Power Distribution Live-line Operation Robot

Robotic Assembly of Shaft Sleeves in Different Sizes Based on Deep Reinforcement Learning

Contact Info

Product

Resources

About