A Reinforcement Learning-Based Framework for Robot Manipulation Skill Acquisition

Liu, Dong; Wang, Zitu; Lu, Binpeng; Cong, Ming; Yu, Honghua; Zou, Qiang

doi:10.1109/access.2020.3001130

Cited by 15 publications

(12 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Gualtieri et al [16] studied a method for learning Manipulation Skills through Hierarchical Spatial Attention to deal with the difficulty of learning a good attention policy and the added partial observability induced by a narrowed window of focus. Liu et al [17] proposed a reinforcement learning based framework for robot manipulation skill acquisition. Errante et al [18] reviewed and concluded that studies on cortical and subcortical circuits involved in grasping and manipulation might be promising to provide new insights about motor learning and brain plasticity in patients with motor disorders.…”

Section: Related Workmentioning

confidence: 99%

The System Design and Robotic Manipulation Skills of Dualarm Autonomous Mobile Robot for Bomb Removing

Zhao

Sun

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Bomb removing is a very challenging but valuable task in urban anti-terrorist or military applications. With the rapid development of technologies of intelligent robots in these years, the intelligence and security level of bomb removing process can be largely improved by using the autonomous mobile robotic systems. In this paper, a dual-arm autonomous mobile robot for bomb removing is proposed which is designed by Tsinghua University. The system design is introduced which mainly consists of the structure and multimodal perception module of the designed system. Besides, manipulation performance is one of the most important functional attributes in bomb removing. Therefore, the manipulation skills for the bomb removing applications are analyzed which adopt the idea of primitives, and skill decomposition and synthesis. Moreover, a knowledge graph for bomb removing is established in the paper and a knowledge based method for the manipulation skills learning is presented. Finally, simulations and experiments have been carried out in the platform to validate the proposed method in the paper and designed bomb removing mobile robot.

show abstract

Section: Related Workmentioning

confidence: 99%

The System Design and Robotic Manipulation Skills of Dualarm Autonomous Mobile Robot for Bomb Removing

Zhao

Sun

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…Liu et al [66] designed a system to complete several robotic pick-and-place tasks, including stacking, sorting, and pin-in-hole placement. A major contribution of this paper was the work around reward shaping to solve complex problems.…”

Section: State Of Research-complete Pick-and-place Taskmentioning

confidence: 99%

Reinforcement Learning for Pick and Place Operations in Robotics: A Survey

2021

View full text Add to dashboard Cite

The field of robotics has been rapidly developing in recent years, and the work related to training robotic agents with reinforcement learning has been a major focus of research. This survey reviews the application of reinforcement learning for pick-and-place operations, a task that a logistics robot can be trained to complete without support from a robotics engineer. To introduce this topic, we first review the fundamentals of reinforcement learning and various methods of policy optimization, such as value iteration and policy search. Next, factors which have an impact on the pick-and-place task, such as reward shaping, imitation learning, pose estimation, and simulation environment are examined. Following the review of the fundamentals and key factors for reinforcement learning, we present an extensive review of all methods implemented by researchers in the field to date. The strengths and weaknesses of each method from literature are discussed, and details about the contribution of each manuscript to the field are reviewed. The concluding critical discussion of the available literature, and the summary of open problems indicates that experiment validation, model generalization, and grasp pose selection are topics that require additional research.

show abstract

“…Many approaches on the prediction of physical interactions have been applied from video prediction [15] to robotic manipulation tasks [16]. Some methods build the system dynamics by explicitly modeling the state transitions, leveraging ground-truth poses [17], [18] or known physical properties [19]. However, access to the ground-truth states and physical properties may be difficult for most real-world applications.…”

Section: Related Workmentioning

confidence: 99%

Dynamics Learning With Object-Centric Interaction Networks for Robot Manipulation

Wang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Understanding the physical interactions of objects with environments is critical for multiobject robotic manipulation tasks. A predictive dynamics model can predict the future states of manipulated objects, which is used to plan plausible actions that enable the objects to achieve desired goal states. However, most current approaches on dynamics learning from high-dimensional visual observations have limitations. These methods either rely on a large amount of real-world data or build a model with a fixed number of objects, which makes them difficult to generalize to unseen objects. This paper proposes a Deep Object-centric Interaction Network (DOIN) which encodes object-centric representations for multiple objects from raw RGB images and reasons about the future trajectory for each object in latent space. The proposed model is trained only on large amounts of random interaction data collected in simulation. The learned model combined with a model predictive control framework enables a robot to search action sequences that manipulate objects to the desired configurations. The proposed method is evaluated both in simulation and real-world experiments on multi-object pushing tasks. Extensive simulation experiments show that DOIN can achieve high prediction accuracy in different scenes with different numbers of objects and outperform state-of-the-art baselines in the manipulation tasks. Real-world experiments demonstrate that the model trained on simulated data can be transferred to the real robot and can successfully perform multi-object pushing tasks for previously-unseen objects with significant variations in shape and size. INDEX TERMSDeep Learning in robotic manipulation, model learning, representation learning, visual Learning. Recently, video prediction models have been successfully applied to perform various manipulation tasks [9]-[11],

show abstract

A Reinforcement Learning-Based Framework for Robot Manipulation Skill Acquisition

Cited by 15 publications

References 39 publications

The System Design and Robotic Manipulation Skills of Dualarm Autonomous Mobile Robot for Bomb Removing

The System Design and Robotic Manipulation Skills of Dualarm Autonomous Mobile Robot for Bomb Removing

Reinforcement Learning for Pick and Place Operations in Robotics: A Survey

Dynamics Learning With Object-Centric Interaction Networks for Robot Manipulation

Contact Info

Product

Resources

About