Multiple peg-in-hole compliant assembly based on a learning-accelerated deep deterministic policy gradient strategy

Li, Xinwang; Xiao, Juliang; Zhao, Wei; Liu, Haitao; Wu, Guodong

doi:10.1108/ir-01-2021-0003

Cited by 11 publications

(6 citation statements)

References 23 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, the application of RL in assembly is focused on three lines of research: improving performance, sample efficiency, and generalization capability and narrowing the simulation-reality gap. Performance improvement spans different domains although research generally focuses on accuracy [15], safety [16], robustness [17], and contact stability [18]. Other studies, such as [19,20], analyzed stability from a different perspective considering that any state trajectory must be bounded and tend to the target position required by the task.…”

Section: Contact-rich Manipulation Tasks: Assembly and Disassemblymentioning

confidence: 99%

Goal-Conditioned Reinforcement Learning within a Human-Robot Disassembly Environment

et al. 2022

View full text Add to dashboard Cite

The introduction of collaborative robots in industrial environments reinforces the need to provide these robots with better cognition to accomplish their tasks while fostering worker safety without entering into safety shutdowns that reduce workflow and production times. This paper presents a novel strategy that combines the execution of contact-rich tasks, namely disassembly, with real-time collision avoidance through machine learning for safe human-robot interaction. Specifically, a goal-conditioned reinforcement learning approach is proposed, in which the removal direction of a peg, of varying friction, tolerance, and orientation, is subject to the location of a human collaborator with respect to a 7-degree-of-freedom manipulator at each time step. For this purpose, the suitability of three state-of-the-art actor-critic algorithms is evaluated, and results from simulation and real-world experiments are presented. In reality, the policy’s deployment is achieved through a new scalable multi-control framework that allows a direct transfer of the control policy to the robot and reduces response times. The results show the effectiveness, generalization, and transferability of the proposed approach with two collaborative robots against static and dynamic obstacles, leveraging the set of available solutions in non-monotonic tasks to avoid a potential collision with the human worker.

show abstract

Section: Contact-rich Manipulation Tasks: Assembly and Disassemblymentioning

confidence: 99%

Goal-Conditioned Reinforcement Learning within a Human-Robot Disassembly Environment

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The peg-in-hole assembly task is among the most commonly researched applications of RL in contact-rich manipulation, with various innovative methods being proposed to address the challenges of this task. The use of model-free RL algorithms is predominant in the literature [13], [14], [15], [16], driven by the challenges of accurately modelling the complex interaction dynamics. Precise modelling of interactions between the peg and hole can be crucial, as even a slight misalignment of the peg can lead to significant friction and impact the success of the task.…”

Section: Related Workmentioning

confidence: 99%

“…Current research predominantly focuses on a small number of pegs that are mostly cylindrical and are often restricted to a tabletop setting with constrained degrees of freedom. Some studies have revolved around specific cases, exemplified by the simultaneous insertion of multiple pegs [15] and deformable holes [17]. However, despite efforts to evaluate generalization capabilities, such as the insertion of USB and LAN connectors [14], the research in this area is limited and has encountered reduced success rates.…”

Section: Related Workmentioning

confidence: 99%

Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learning

Orsula

Bøgh

Olivares-Méndez

et al. 2022

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

The ability to autonomously assemble structures is crucial for the development of future space infrastructure. However, the unpredictable conditions of space pose significant challenges for robotic systems, necessitating the development of advanced learning techniques to enable autonomous assembly. In this study, we present a novel approach for learning autonomous peg-in-hole assembly in the context of space robotics. Our focus is on enhancing the generalization and adaptability of autonomous systems through deep reinforcement learning. By integrating procedural generation and domain randomization, we train agents in a highly parallelized simulation environment across a spectrum of diverse scenarios with the aim of acquiring a robust policy. The proposed approach is evaluated using three distinct reinforcement learning algorithms to investigate the trade-offs among various paradigms. We demonstrate the adaptability of our agents to novel scenarios and assembly sequences while emphasizing the potential of leveraging advanced simulation techniques for robot learning in space. Our findings set the stage for future advancements in intelligent robotic systems capable of supporting ambitious space missions and infrastructure development beyond Earth. The source code is available at https://github.com/AndrejOrsula/drl_omni_peg.

show abstract

“…With the continuous progress of science and technology and the continuous development of industrial design field, designers are facing more and more complex and diverse design requirements while pursuing innovation and efficiency [1] . In industrial design, sketch is one of the key steps in the design process, which carries the designer's initial conception of product concept and form.…”

Section: ⅰ Introductionmentioning

confidence: 99%

The Analysis of Optimization Strategy of Industrial Design in Automatic Sketch Generation Based on Deep Learning

2024

IEEE Access

View full text Add to dashboard Cite

This study is devoted to exploring the strategy of automatic sketch generation and optimization of industrial design based on deep learning. By combining the Generative Adversarial Network (GAN) with the optimization algorithm, this paper proposes an innovative method to realize the automatic generation of highquality and diverse industrial design sketches. In the experiment, this paper selects SketchyCAD and other public data sets, trains them through deep learning model, and introduces genetic algorithm(GA) and differential evolution algorithm to optimize the parameters. In terms of experimental results, we observed that the quality of generated sketches was significantly improved, and the design sketches generated by the mode (GAN+GA) were more realistic and innovative. The introduction of optimization strategy further improves the generation effect and intelligently adjusts the model parameters to adapt to different design styles. In this paper, the influence of hyperparameter tuning is analyzed in detail, and it is found that the adjustment of learning rate plays a key role in generating quality and diversity. However, the experiment also revealed some challenges and room for improvement. We noticed that the generated results may have the risk of over-fitting in the training process, and with the increase of training times, the diversity gradually decreased. This suggests that more complex model structure and richer data sets are needed to improve the generalization performance. Generally speaking, this study provides new ideas and methods for the integration of deep learning and industrial design. By innovatively combining generation model and optimization algorithm, this research has contributed beneficial research results to the development of industrial design automation. This research is of great significance to promote the intelligence and innovation in the field of industrial design.

show abstract

Multiple peg-in-hole compliant assembly based on a learning-accelerated deep deterministic policy gradient strategy

Cited by 11 publications

References 23 publications

Goal-Conditioned Reinforcement Learning within a Human-Robot Disassembly Environment

Goal-Conditioned Reinforcement Learning within a Human-Robot Disassembly Environment

Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learning

The Analysis of Optimization Strategy of Industrial Design in Automatic Sketch Generation Based on Deep Learning

Contact Info

Product

Resources

About