scholarly journals Translational and rotational slip detection and control in robotic manipulation

1999 ◽  
Vol 32 (2) ◽  
pp. 647-652 ◽  
Author(s):  
Claudio Melchiorri
Keyword(s):  
Robotic Manipulation ◽  
And Control ◽  
Rotational Slip ◽  
Slip Detection

scholarly journals Parareal with a learned coarse model for robotic manipulation

2020 ◽  
Vol 23 (1-4) ◽  
Author(s):  
Wisdom Agboh ◽  
Oliver Grainger ◽  
Daniel Ruprecht ◽  
Mehmet Dogar
Keyword(s):  
Time Integration ◽  
Robotic Manipulation ◽  
Multiple Objects ◽  
Initial State ◽  
Link Type ◽  
Planning And Control ◽  
Physics Model ◽  
Coarse Model ◽  
Computational Bottleneck ◽  
And Control

AbstractA key component of many robotics model-based planning and control algorithms is physics predictions, that is, forecasting a sequence of states given an initial state and a sequence of controls. This process is slow and a major computational bottleneck for robotics planning algorithms. Parallel-in-time integration methods can help to leverage parallel computing to accelerate physics predictions and thus planning. The Parareal algorithm iterates between a coarse serial integrator and a fine parallel integrator. A key challenge is to devise a coarse model that is computationally cheap but accurate enough for Parareal to converge quickly. Here, we investigate the use of a deep neural network physics model as a coarse model for Parareal in the context of robotic manipulation. In simulated experiments using the physics engine Mujoco as fine propagator we show that the learned coarse model leads to faster Parareal convergence than a coarse physics-based model. We further show that the learned coarse model allows to apply Parareal to scenarios with multiple objects, where the physics-based coarse model is not applicable. Finally, we conduct experiments on a real robot and show that Parareal predictions are close to real-world physics predictions for robotic pushing of multiple objects. Code (https://doi.org/10.5281/zenodo.3779085) and videos (https://youtu.be/wCh2o1rf-gA) are publicly available.

A Study on Slip Controller for Safety Improvement of Running Flat Road for Motorized Wheelchair

2015 ◽  
Vol 789-790 ◽  
pp. 906-912
Author(s):  
Bo Min Kim ◽  
Won Yung Lee ◽  
Eung Hyuk Lee
Keyword(s):  
Detection Algorithm ◽  
Control Variables ◽  
Slip Ratio ◽  
Safety Improvement ◽  
Left And Right ◽  
And Control ◽  
Slip Detection

A slip controller that can move against the off-track and control excursion caused by slips while driving a motorized wheelchair is proposed. Detecting slips in a motorized wheelchair is to detect states of the motorized wheelchair and its motors in a traveling condition. For carrying it, slip ratios are calculated using a slip detection algorithm based on the information obtained from the six-axis IMU sensor and the encoders, which are connected to both left and right motors. The calculated slip ratios are used as control variables for improving the safety in a motorized wheelchair. In the experiment of the slip controller proposed in this study, slips are verified in a proposed track. Also, it is verified that the maximum slip ratio section is determined while turning left or right.

Modeling and Control of Four-bar Mechanism with Series Elastic Actuators

2020 ◽  
Author(s):  
Felipe R. Lopes ◽  
Marco A. Meggiolaro
Keyword(s):  
Human Interaction ◽  
Robotic Manipulation ◽  
Modeling And Control ◽  
Lqr Control ◽  
In Series ◽  
Flexible Behavior ◽  
Series Elastic Actuators ◽  
New Generation ◽  
And Control ◽  
Series Elastic

A new generation of robots that work in cooperation with humans (called collaborative robots) needs some flexibility to adapt to the environment and activities with people. That is why the Series Elastic Actuator (SEA) has been a breakthrough in actuator technologies. The idea of inserting an elastic element in series with a motor allows a lower output impedance, consequently a flexible behavior in the manipulator, in addition to providing torque feedback to better compensate disturbances caused e.g. by friction losses. This article presents a four-bar mechanism with SEA for the purpose of robotic manipulation. Its kinematics and dynamicsare studied, as well as its regulation and trajectory control. The behavior of the decoupled four-bar mechanism and the characteristics of the SEA are also analyzed. Then the regulation control of the complete system is carried out using LQR control. Finally, a circular trajectory is controlled in a simulation to validate the proposed control strategy. The simulation results show the effectiveness of the proposed controller for the mechanism in the presence of SEAs estimating torque and providing the desired compliance for human interaction.

scholarly journals Deep Reinforcement Learning for the Control of Robotic Manipulation: A Focussed Mini-Review

Robotics ◽  
2021 ◽  
Vol 10 (1) ◽  
pp. 22
Author(s):  
Rongrong Liu ◽  
Florent Nageotte ◽  
Philippe Zanne ◽  
Michel de Mathelin ◽  
Birgitta Dresp-Langley
Keyword(s):  
Deep Learning ◽  
Reinforcement Learning ◽  
Robotic Manipulation ◽  
Significant Progress ◽  
Expert Performance ◽  
Optimal Behavior ◽  
Real World Applications ◽  
Critical Issues ◽  
And Control ◽  
Manipulation And Control

Deep learning has provided new ways of manipulating, processing and analyzing data. It sometimes may achieve results comparable to, or surpassing human expert performance, and has become a source of inspiration in the era of artificial intelligence. Another subfield of machine learning named reinforcement learning, tries to find an optimal behavior strategy through interactions with the environment. Combining deep learning and reinforcement learning permits resolving critical issues relative to the dimensionality and scalability of data in tasks with sparse reward signals, such as robotic manipulation and control tasks, that neither method permits resolving when applied on its own. In this paper, we present recent significant progress of deep reinforcement learning algorithms, which try to tackle the problems for the application in the domain of robotic manipulation control, such as sample efficiency and generalization. Despite these continuous improvements, currently, the challenges of learning robust and versatile manipulation skills for robots with deep reinforcement learning are still far from being resolved for real-world applications.

scholarly journals Multimodal grasp data set: A novel visual–tactile data set for robotic manipulation

2019 ◽  
Vol 16 (1) ◽  
pp. 172988141882157 ◽  
Author(s):  
Tao Wang ◽  
Chao Yang ◽  
Frank Kirchner ◽  
Peng Du ◽  
Fuchun Sun ◽  
...  
Keyword(s):  
Short Term Memory ◽  
Robotic Manipulation ◽  
Robot Hand ◽  
Quality Of Data ◽  
Short Term ◽  
Data Set ◽  
Term Memory ◽  
Generalization Ability ◽  
Long Short Term Memory ◽  
Slip Detection

This article introduces a visual–tactile multimodal grasp data set, aiming to further the research on robotic manipulation. The data set was built by the novel designed dexterous robot hand, the Intel’s Eagle Shoal robot hand (Intel Labs China, Beijing, China). The data set contains 2550 sets data, including tactile, joint, time label, image, and RGB and depth video. With the integration of visual and tactile data, researchers could be able to better understand the grasping process and analyze the deeper grasping issues. In this article, the building process of the data set was introduced, as well as the data set composition. In order to evaluate the quality of data set, the tactile data were analyzed by short-time Fourier transform. The tactile data–based slip detection was realized by long short-term memory and contrasted with visual data. The experiments compared the long short-term memory with the traditional classifiers, and generalization ability on different grasp directions and different objects is implemented. The results have proved that the data set’s value in promoting research on robotic manipulation area showed the effective slip detection and generalization ability of long short-term memory. Further work on visual and tactile data will be devoted to in the future.

Sign in / Sign up

Export Citation Format

Share Document