Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey

Zhao, Wenshuai; Queralta, Jorge Peña; Westerlund, Tomi

doi:10.1109/ssci47803.2020.9308468

Cited by 477 publications

(241 citation statements)

References 32 publications

Supporting

Mentioning

237

Contrasting

Unclassified

Order By: Relevance

“…Caldera et al ( 2018 ), Kroemer et al ( 2019 ), Li and Qiao ( 2019 ), and Kleeberger et al ( 2020 ) focus on the overview of robot manipulation methods based on deep learning. Mohammed et al ( 2020 ) and Zhao W. et al ( 2020 ) introduce the techniques in robot learning on the basis of reinforcement learning. Billard and Kragic ( 2019 ) describes the trends and challenges in robot manipulation.…”

Section: Proposed Taxonomymentioning

confidence: 99%

See 1 more Smart Citation

Robotics Dexterous Grasping: The Methods Based on Point Cloud and Deep Learning

et al. 2021

View full text Add to dashboard Cite

Dexterous manipulation, especially dexterous grasping, is a primitive and crucial ability of robots that allows the implementation of performing human-like behaviors. Deploying the ability on robots enables them to assist and substitute human to accomplish more complex tasks in daily life and industrial production. A comprehensive review of the methods based on point cloud and deep learning for robotics dexterous grasping from three perspectives is given in this paper. As a new category schemes of the mainstream methods, the proposed generation-evaluation framework is the core concept of the classification. The other two classifications based on learning modes and applications are also briefly described afterwards. This review aims to afford a guideline for robotics dexterous grasping researchers and developers.

show abstract

Section: Proposed Taxonomymentioning

confidence: 99%

“…Simulation-based training provides data at low-cost, but involves inherent mismatches with real-world settings (Zhao W. et al, 2020 ). At present, domain randomization and domain adaptation are widely used in sim-to-real problems.…”

Section: Challenges and Future Directionsmentioning

confidence: 99%

Robotics Dexterous Grasping: The Methods Based on Point Cloud and Deep Learning

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Without such models, the deviation between simulated and actual manipulators would be a big obstacle for reinforcement learning's application. To handle these cases, Sim-to-Real transfer approaches (Zhao et al, 2020) such as domain randomization and domain adaptation may drive a new research focus in the recent future.…”

Section: Discussionmentioning

confidence: 99%

A Survey for Machine Learning-Based Control of Continuum Robots

Wang

Kwok

2021

Front. Robot. AI

View full text Add to dashboard Cite

Soft continuum robots have been accepted as a promising category of biomedical robots, accredited to the robots’ inherent compliance that makes them safely interact with their surroundings. In its application of minimally invasive surgery, such a continuum concept shares the same view of robotization for conventional endoscopy/laparoscopy. Different from rigid-link robots with accurate analytical kinematics/dynamics, soft robots encounter modeling uncertainties due to intrinsic and extrinsic factors, which would deteriorate the model-based control performances. However, the trade-off between flexibility and controllability of soft manipulators may not be readily optimized but would be demanded for specific kinds of modeling approaches. To this end, data-driven modeling strategies making use of machine learning algorithms would be an encouraging way out for the control of soft continuum robots. In this article, we attempt to overview the current state of kinematic/dynamic model-free control schemes for continuum manipulators, particularly by learning-based means, and discuss their similarities and differences. Perspectives and trends in the development of new control methods are also investigated through the review of existing limitations and challenges.

show abstract

“…Sensors are essential for the localization of source, and the means of sensing have a comprehensive scope [61][62][63]. e authors of [64,65] have used the multirobot systems to significantly increase the efficiency of SAR robot with a faster search of victims, providing the real-time monitoring and surveillance of SAR operations. e SAR operations include a variety of conditions and situations, and collaborative multirobot systems can provide the most benefits.…”

Section: Previous Studiesmentioning

confidence: 99%

A Comprehensive Review on Design of Autonomous Robotic Boat for Rescue Applications

Jain

Saini

Gupta

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

New technologies are advancing and emerging day by day to improve the safety of humans by making use of various autonomous technologies. The continuous utilization of autonomous vehicles/systems in search and rescue (SAR) operations is a challenging research area particularly for marine-based activities. A comprehensive systematic literature review (SLR) providing an overview of improvisations that have been done in the field of autonomous technologies for search and rescue operation over the last five years has been compiled in this paper. A methodology for using autonomous vehicles in water for SAR operations has been incorporated and demonstrated. The focus of this study is to look at the various techniques and address different challenges faced for human beings’ safety during rescue operation. The comparison of results achieved for various technologies and algorithms is highlighted in this paper. This literature survey proves to be a good source of information for fellow researchers to precisely analyze the study results.

show abstract

Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey

Cited by 477 publications

References 32 publications

Robotics Dexterous Grasping: The Methods Based on Point Cloud and Deep Learning

Robotics Dexterous Grasping: The Methods Based on Point Cloud and Deep Learning

A Survey for Machine Learning-Based Control of Continuum Robots

A Comprehensive Review on Design of Autonomous Robotic Boat for Rescue Applications

Contact Info

Product

Resources

About