A framework of robot skill learning from complex and long-horizon tasks
Robot Learning from humans is a promising paradigm for directly transferring human skills
to robots. This learning allows robots to encapsulate task constraints and motion patterns …
to robots. This learning allows robots to encapsulate task constraints and motion patterns …
Learning robot anomaly recovery skills from multiple time-driven demonstrations
Robots are prone to making anomalies when performing manipulation tasks in unstructured
environments, it is often desirable to rapidly adapt the robotic behavior to avoid …
environments, it is often desirable to rapidly adapt the robotic behavior to avoid …
Fast Recognition of Snap-Fit for Industrial Robot Using a Recurrent Neural Network
T Cui, R Song, F Li, T Fu, C Wang… - IEEE Robotics and …, 2022 - ieeexplore.ieee.org
Snap-fit recognition is an essential capability for industrial robots in manufacturing. The goal
is to protect fragile parts by quickly detecting snap-fit signals in the assembly. In this letter …
is to protect fragile parts by quickly detecting snap-fit signals in the assembly. In this letter …
Learning skills to patch plans based on inaccurate models
A Lagrassa, S Lee, O Kroemer - 2020 IEEE/RSJ International …, 2020 - ieeexplore.ieee.org
Planners using accurate models can be effective for accomplishing manipulation tasks in the
real world, but are typically highly specialized and require significant fine-tuning to be …
real world, but are typically highly specialized and require significant fine-tuning to be …
What went wrong? Identification of everyday object manipulation anomalies
Enhancing the abilities of service robots is important for expanding what they can achieve in
everyday manipulation tasks. In addition, it is also essential to ensure that they can …
everyday manipulation tasks. In addition, it is also essential to ensure that they can …
Multimodal prediction-based robot abnormal movement identification under variable time-length experiences
Robots will eventually make part of our daily lives, helping us at home, taking care of the
elderly, and collaborating at work. In such Human-Robot Collaboration (HRC) scenarios …
elderly, and collaborating at work. In such Human-Robot Collaboration (HRC) scenarios …
[图书][B] AI based robot safe learning and control
This open access book mainly focuses on the safe control of robot manipulators. The control
schemes are mainly developed based on dynamic neural network, which is an important …
schemes are mainly developed based on dynamic neural network, which is an important …
Incremental learning robot task representation and identification
In this chapter, we present a novel method for incremental learning robot complex task
representation, identifying repeated skills, and generalizing to new environment by …
representation, identifying repeated skills, and generalizing to new environment by …
Recognition of micro force locking contact state based on one-dimensional residual network
D Guan, Y Lu, C Zhuang - 2022 28th International Conference …, 2022 - ieeexplore.ieee.org
The robot locking alignment has the characteristics of small tolerance, micro contact force,
and high similarity of contact force. Meanwhile, due to the uncertainty of vision and robot …
and high similarity of contact force. Meanwhile, due to the uncertainty of vision and robot …
Mode-dependent event-triggered fault detection for nonlinear semi-Markov jump systems with quantization: application to robotic manipulator
Y Ji, C Wang, W Wu - IEEE Access, 2021 - ieeexplore.ieee.org
This paper is studied with fault detection issue for nonlinear semi-Markov jump systems. In
particular, the mode-dependent mechanism of event-triggered transmission is developed for …
particular, the mode-dependent mechanism of event-triggered transmission is developed for …