Robots are increasingly expected to replace humans in many repetitive and high-precision tasks,of which surface scanning is a typical example.However,it is usually difficult for a robot to independently deal with a su...Robots are increasingly expected to replace humans in many repetitive and high-precision tasks,of which surface scanning is a typical example.However,it is usually difficult for a robot to independently deal with a surface scanning task with uncertainties in,for example the irregular surface shapes and surface properties.Moreover,it usually requires surface modelling with additional sensors,which might be time-consuming and costly.A human-robot collaboration-based approach that allows a human user and a robot to assist each other in scanning uncertain surfaces with uniform properties,such as scanning human skin in ultrasound examination is proposed.In this approach,teleoperation is used to obtain the operator's intent while allowing the operator to operate remotely.After external force perception and friction estimation,the orientation of the robot endeffector can be autonomously adjusted to keep as perpendicular to the surface as possible.Force control enables the robotic manipulator to maintain a constant contact force with the surface.And hybrid force/motion control ensures that force,position,and pose can be regulated without interfering with each other while reducing the operator's workload.The proposed method is validated using the Elite robot to perform a mock Bultrasound scanning experiment.展开更多
Conventional model transfer techniques,requiring the labelled source data,are not applicable in the privacy-protected medical fields.For the challenging scenarios,recent source data-free domain adaptation(SFDA)has bec...Conventional model transfer techniques,requiring the labelled source data,are not applicable in the privacy-protected medical fields.For the challenging scenarios,recent source data-free domain adaptation(SFDA)has become a mainstream solution but losing focus on the inter-sample class information.This paper proposes a new Credible Local Context Representation approach for SFDA.Our main idea is to exploit the credible local context for more discriminative representation.Specifically,we enhance the source model's discrimination by information regulating.To capture the context,a discovery method is developed that performs fixed steps walking in deep space and takes the credible features in this path as the context.In the epoch-wise adaptation,deep clustering-like training is conducted with two major updates.First,the context for all target data is constructed and then the context-fused pseudo-labels providing semantic guidance are generated.Second,for each target data,a weighting fusion on its context forms the anchored neighbourhood structure;thus,the deep clustering is switched from individual-based to coarse-grained.Also,a new regularisation building is developed on the anchored neighbourhood to drive the deep coarse-grained learning.Experiments on three benchmarks indicate that the proposed method can achieve stateof-the-art results.展开更多
In-hand manipulation is a fundamental ability for multi-fingered robotic hands that interact with their environments.Owing to the high dimensionality of robotic hands and intermittent contact dynamics,effectively prog...In-hand manipulation is a fundamental ability for multi-fingered robotic hands that interact with their environments.Owing to the high dimensionality of robotic hands and intermittent contact dynamics,effectively programming a robotic hand for in-hand manipulations is still a challenging problem.To address this challenge,this work employs deep reinforcement learning(DRL)algorithm to learn in-hand manipulations for multi-fingered robotic hands.A reward-shaping method is proposed to assist the learning of in-hand manipulation.The synergy of robotic hand postures is analysed to build a low-dimensional hand posture space.Two additional rewards are designed based on both the analysis of hand synergies and its learning history.The two additional rewards cooperating with an extrinsic reward are used to assist the in-hand manipulation learning.Three value functions are trained jointly with respect to their reward functions.Then they cooperate to optimise a control policy for in-hand manipulation.The reward shaping not only improves the exploration efficiency of the DRL algorithm but also provides a way to incorporate domain knowledge.The performance of the proposed learning method is evaluated with object rotation tasks.Experimental results demonstrated that the proposed learning method enables multi-fingered robotic hands to learn in-hand manipulation effectively.展开更多
Robotic assembly is widely utilized in large-scale manufacturing due to its high production efficiency,and the peg-in-hole assembly is a typical operation.While single peg-in-hole tasks have achieved great performance...Robotic assembly is widely utilized in large-scale manufacturing due to its high production efficiency,and the peg-in-hole assembly is a typical operation.While single peg-in-hole tasks have achieved great performance through reinforcement learning(RL)methods,multiple peg-in-hole assembly remains challenging due to complex geometry and physical constraints.To address this,we introduce a control policy workflow for multiple peg-in-hole assembly,dividing the task into three primitive sub-tasks:picking,alignment,and insertion to modularize the long-term task and improve sample efficiency.Sequential control policy(SeqPolicy),containing three control policies,is used to implement all the sub-tasks step-by-step.This approach introduces human knowledge to manage intermediate states,such as lifting height and aligning direction,thereby enabling flexible deployment across various scenarios.SeqPolicy demonstrated higher training efficiency with faster convergence and a higher success rate compared to the single control policy.Its adaptability is confirmed through generalization experiments involving objects with varying geometries.Recognizing the importance of object pose for control policies,a low-cost and adaptable method using visual representation containing objects’pose information from RGB images is proposed to estimate objects’pose in robot base frame directly in working scenarios.The representation is extracted by a Siamese-CNN network trained with self-supervised contrastive learning.Utilizing it,the alignment sub-task is successfully executed.These experiments validate the solution’s reusability and adaptability in multiple peg-in-hole scenarios.展开更多
基金Engineering and Physical Sciences Research Council(EPSRC),Grant/Award Number:EP/S001913。
文摘Robots are increasingly expected to replace humans in many repetitive and high-precision tasks,of which surface scanning is a typical example.However,it is usually difficult for a robot to independently deal with a surface scanning task with uncertainties in,for example the irregular surface shapes and surface properties.Moreover,it usually requires surface modelling with additional sensors,which might be time-consuming and costly.A human-robot collaboration-based approach that allows a human user and a robot to assist each other in scanning uncertain surfaces with uniform properties,such as scanning human skin in ultrasound examination is proposed.In this approach,teleoperation is used to obtain the operator's intent while allowing the operator to operate remotely.After external force perception and friction estimation,the orientation of the robot endeffector can be autonomously adjusted to keep as perpendicular to the surface as possible.Force control enables the robotic manipulator to maintain a constant contact force with the surface.And hybrid force/motion control ensures that force,position,and pose can be regulated without interfering with each other while reducing the operator's workload.The proposed method is validated using the Elite robot to perform a mock Bultrasound scanning experiment.
基金National Key R&D Program of China,Grant/Award Numbers:2018YFE0203900,2020YFB1313600German Research Foundation,Hamburg Landesforschungsförderungsprojekt Cross,Grant/Award Number:Sonderforschungsbereich Transregio 169+2 种基金Shanghai Artificial Intelligence Innovation Development Special Support Project,Grant/Award Number:3920365001Horizon2020 RISE project STEP2DYNA,Grant/Award Number:691154National Natural Science Foundation of China,Grant/Award Numbers:61773083,62206168,62276048,U1813202。
文摘Conventional model transfer techniques,requiring the labelled source data,are not applicable in the privacy-protected medical fields.For the challenging scenarios,recent source data-free domain adaptation(SFDA)has become a mainstream solution but losing focus on the inter-sample class information.This paper proposes a new Credible Local Context Representation approach for SFDA.Our main idea is to exploit the credible local context for more discriminative representation.Specifically,we enhance the source model's discrimination by information regulating.To capture the context,a discovery method is developed that performs fixed steps walking in deep space and takes the credible features in this path as the context.In the epoch-wise adaptation,deep clustering-like training is conducted with two major updates.First,the context for all target data is constructed and then the context-fused pseudo-labels providing semantic guidance are generated.Second,for each target data,a weighting fusion on its context forms the anchored neighbourhood structure;thus,the deep clustering is switched from individual-based to coarse-grained.Also,a new regularisation building is developed on the anchored neighbourhood to drive the deep coarse-grained learning.Experiments on three benchmarks indicate that the proposed method can achieve stateof-the-art results.
基金This work was funded by the German Science Foundation(DFG)and the National Science Foundation of China(NSFC)in project Crossmodal Learning under contract Sonderforschungsbereich Transregio 169.
文摘In-hand manipulation is a fundamental ability for multi-fingered robotic hands that interact with their environments.Owing to the high dimensionality of robotic hands and intermittent contact dynamics,effectively programming a robotic hand for in-hand manipulations is still a challenging problem.To address this challenge,this work employs deep reinforcement learning(DRL)algorithm to learn in-hand manipulations for multi-fingered robotic hands.A reward-shaping method is proposed to assist the learning of in-hand manipulation.The synergy of robotic hand postures is analysed to build a low-dimensional hand posture space.Two additional rewards are designed based on both the analysis of hand synergies and its learning history.The two additional rewards cooperating with an extrinsic reward are used to assist the in-hand manipulation learning.Three value functions are trained jointly with respect to their reward functions.Then they cooperate to optimise a control policy for in-hand manipulation.The reward shaping not only improves the exploration efficiency of the DRL algorithm but also provides a way to incorporate domain knowledge.The performance of the proposed learning method is evaluated with object rotation tasks.Experimental results demonstrated that the proposed learning method enables multi-fingered robotic hands to learn in-hand manipulation effectively.
基金supported by the UKRI Guarantee funding for Horizon Europe MSCA Postdoctoral Fellowships(No.EP/Z00117X/1).
文摘Robotic assembly is widely utilized in large-scale manufacturing due to its high production efficiency,and the peg-in-hole assembly is a typical operation.While single peg-in-hole tasks have achieved great performance through reinforcement learning(RL)methods,multiple peg-in-hole assembly remains challenging due to complex geometry and physical constraints.To address this,we introduce a control policy workflow for multiple peg-in-hole assembly,dividing the task into three primitive sub-tasks:picking,alignment,and insertion to modularize the long-term task and improve sample efficiency.Sequential control policy(SeqPolicy),containing three control policies,is used to implement all the sub-tasks step-by-step.This approach introduces human knowledge to manage intermediate states,such as lifting height and aligning direction,thereby enabling flexible deployment across various scenarios.SeqPolicy demonstrated higher training efficiency with faster convergence and a higher success rate compared to the single control policy.Its adaptability is confirmed through generalization experiments involving objects with varying geometries.Recognizing the importance of object pose for control policies,a low-cost and adaptable method using visual representation containing objects’pose information from RGB images is proposed to estimate objects’pose in robot base frame directly in working scenarios.The representation is extracted by a Siamese-CNN network trained with self-supervised contrastive learning.Utilizing it,the alignment sub-task is successfully executed.These experiments validate the solution’s reusability and adaptability in multiple peg-in-hole scenarios.
