Adaptive motion planning framework by learning from demonstration

2019 ◽  
Vol 46 (4) ◽  
pp. 541-552 ◽  
Author(s):  
Xiao Li ◽  
Hongtai Cheng ◽  
Xiaoxiao Liang
Keyword(s):  
Motion Planning ◽  
Probabilistic Model ◽  
Training Data ◽  
Data Driven ◽  
Learning From Demonstration ◽  
Traditional Methods ◽  
Content Type ◽  
Adaptive Motion ◽  
Unstructured Environment ◽  
Planning Technique

Purpose Learning from demonstration (LfD) provides an intuitive way for non-expert persons to teach robots new skills. However, the learned motion is typically fixed for a given scenario, which brings serious adaptiveness problem for robots operating in the unstructured environment, such as avoiding an obstacle which is not presented during original demonstrations. Therefore, the robot should be able to learn and execute new behaviors to accommodate the changing environment. To achieve this goal, this paper aims to propose an improved LfD method which is enhanced by an adaptive motion planning technique. Design/methodology/approach The LfD is based on GMM/GMR method, which can transform original off-line demonstrations into a compressed probabilistic model and recover robot motion based on the distributions. The central idea of this paper is to reshape the probabilistic model according to on-line observation, which is realized by the process of re-sampling, data partition, data reorganization and motion re-planning. The re-planned motions are not unique. A criterion is proposed to evaluate the fitness of each motion and optimize among the candidates. Findings The proposed method is implemented in a robotic rope disentangling task. The results show that the robot is able to complete its task while avoiding randomly distributed obstacles and thereby verify the effectiveness of the proposed method. The main contributions of the proposed method are avoiding unforeseen obstacles in the unstructured environment and maintaining crucial aspects of the motion which guarantee to accomplish a skill/task successfully. Originality/value Traditional methods are intrinsically based on motion planning technique and treat the off-line training data as a priori probability. The paper proposes a novel data-driven solution to achieve motion planning for LfD. When the environment changes, the off-line training data are revised according to external constraints and reorganized to generate new motion. Compared to traditional methods, the novel data-driven solution is concise and efficient.

scholarly journals An Adaptive Motion Planning Technique for On-Road Autonomous Driving

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 2655-2664
Author(s):  
Xianjian Jin ◽  
Zeyuan Yan ◽  
Guodong Yin ◽  
Shaohua Li ◽  
Chongfeng Wei
Keyword(s):  
Motion Planning ◽  
Autonomous Driving ◽  
Adaptive Motion ◽  
Planning Technique

scholarly journals A Data-Driven Surrogate Approach for the Temporal Stability Forecasting of Vegetation Covered Dikes

Water ◽  
2021 ◽  
Vol 13 (1) ◽  
pp. 107
Author(s):  
Elahe Jamalinia ◽  
Faraz S. Tehrani ◽  
Susan C. Steele-Dunne ◽  
Philip J. Vardon
Keyword(s):  
Numerical Simulation ◽  
Water Flux ◽  
Temporal Stability ◽  
Synthetic Data ◽  
Climatic Conditions ◽  
Training Data ◽  
Data Driven ◽  
Data Set ◽  
Surface Cracking ◽  
Real Time Analysis

Climatic conditions and vegetation cover influence water flux in a dike, and potentially the dike stability. A comprehensive numerical simulation is computationally too expensive to be used for the near real-time analysis of a dike network. Therefore, this study investigates a random forest (RF) regressor to build a data-driven surrogate for a numerical model to forecast the temporal macro-stability of dikes. To that end, daily inputs and outputs of a ten-year coupled numerical simulation of an idealised dike (2009–2019) are used to create a synthetic data set, comprising features that can be observed from a dike surface, with the calculated factor of safety (FoS) as the target variable. The data set before 2018 is split into training and testing sets to build and train the RF. The predicted FoS is strongly correlated with the numerical FoS for data that belong to the test set (before 2018). However, the trained model shows lower performance for data in the evaluation set (after 2018) if further surface cracking occurs. This proof-of-concept shows that a data-driven surrogate can be used to determine dike stability for conditions similar to the training data, which could be used to identify vulnerable locations in a dike network for further examination.

scholarly journals Data-driven deep density estimation

2021 ◽  
Author(s):  
Patrik Puchert ◽  
Pedro Hermosilla ◽  
Tobias Ritschel ◽  
Timo Ropinski
Keyword(s):  
Data Analysis ◽  
Density Estimation ◽  
Population Data ◽  
Training Data ◽  
Data Driven ◽  
Discrete Observations ◽  
Efficient Manner ◽  
Continuous Models ◽  
3D Scans ◽  
Spatial Locations

AbstractDensity estimation plays a crucial role in many data analysis tasks, as it infers a continuous probability density function (PDF) from discrete samples. Thus, it is used in tasks as diverse as analyzing population data, spatial locations in 2D sensor readings, or reconstructing scenes from 3D scans. In this paper, we introduce a learned, data-driven deep density estimation (DDE) to infer PDFs in an accurate and efficient manner, while being independent of domain dimensionality or sample size. Furthermore, we do not require access to the original PDF during estimation, neither in parametric form, nor as priors, or in the form of many samples. This is enabled by training an unstructured convolutional neural network on an infinite stream of synthetic PDFs, as unbound amounts of synthetic training data generalize better across a deck of natural PDFs than any natural finite training data will do. Thus, we hope that our publicly available DDE method will be beneficial in many areas of data analysis, where continuous models are to be estimated from discrete observations.

Human skill integrated motion planning of assembly manipulation for 6R industrial robot

2019 ◽  
Vol 46 (1) ◽  
pp. 171-180
Author(s):  
Yi Liu ◽  
Ming Cong ◽  
Hang Dong ◽  
Dong Liu
Keyword(s):  
Deep Learning ◽  
Motion Planning ◽  
Industrial Robot ◽  
Robotic Assembly ◽  
3D Vision ◽  
Content Type ◽  
Human Skill ◽  
Depth Images ◽  
Positioning Method ◽  
Assembly Technology

Purpose The purpose of this paper is to propose a new method based on three-dimensional (3D) vision technologies and human skill integrated deep learning to solve assembly positioning task such as peg-in-hole. Design/methodology/approach Hybrid camera configuration was used to provide the global and local views. Eye-in-hand mode guided the peg to be in contact with the hole plate using 3D vision in global view. When the peg was in contact with the workpiece surface, eye-to-hand mode provided the local view to accomplish peg-hole positioning based on trained CNN. Findings The results of assembly positioning experiments proved that the proposed method successfully distinguished the target hole from the other same size holes according to the CNN. The robot planned the motion according to the depth images and human skill guide line. The final positioning precision was good enough for the robot to carry out force controlled assembly. Practical implications The developed framework can have an important impact on robotic assembly positioning process, which combine with the existing force-guidance assembly technology as to build a whole set of autonomous assembly technology. Originality/value This paper proposed a new approach to the robotic assembly positioning based on 3D visual technologies and human skill integrated deep learning. Dual cameras swapping mode was used to provide visual feedback for the entire assembly motion planning process. The proposed workpiece positioning method provided an effective disturbance rejection, autonomous motion planning and increased overall performance with depth images feedback. The proposed peg-hole positioning method with human skill integrated provided the capability of target perceptual aliasing avoiding and successive motion decision for the robotic assembly manipulation.

A Copula-Based Sampling Method for Data-Driven Prognostics and Health Management

2013 ◽  
Author(s):  
Zhimin Xi ◽  
Rong Jing ◽  
Pingfeng Wang ◽  
Chao Hu
Keyword(s):  
Sampling Method ◽  
Failure Time ◽  
Health Management ◽  
Remaining Useful Life ◽  
Training Data ◽  
Data Driven ◽  
Prognostics And Health Management ◽  
Statistical Relationship ◽  
Cooling Fans ◽  
On Line

This paper develops a Copula-based sampling method for data-driven prognostics and health management (PHM). The principal idea is to first build statistical relationship between failure time and the time realizations at specified degradation levels on the basis of off-line training data sets, then identify possible failure times for on-line testing units based on the constructed statistical model and available on-line testing data. Specifically, three technical components are proposed to implement the methodology. First of all, a generic health index system is proposed to represent the health degradation of engineering systems. Next, a Copula-based modeling is proposed to build statistical relationship between failure time and the time realizations at specified degradation levels. Finally, a sampling approach is proposed to estimate the failure time and remaining useful life (RUL) of on-line testing units. Two case studies, including a bearing system in electric cooling fans and a 2008 IEEE PHM challenge problem, are employed to demonstrate the effectiveness of the proposed methodology.

Imitation of Demonstrations Using Bayesian Filtering With Nonparametric Data-Driven Models

2017 ◽  
Vol 140 (3) ◽  
Author(s):  
Nurali Virani ◽  
Devesh K. Jha ◽  
Zhenyuan Yuan ◽  
Ishana Shekhawat ◽  
Asok Ray
Keyword(s):  
Particle Filtering ◽  
Dynamic Models ◽  
Training Data ◽  
Data Driven ◽  
Conditional Density ◽  
Bayesian Filtering ◽  
State Dependent ◽  
State Evolution ◽  
And Control ◽  
Nonparametric Kernel

This paper addresses the problem of learning dynamic models of hybrid systems from demonstrations and then the problem of imitation of those demonstrations by using Bayesian filtering. A linear programming-based approach is used to develop nonparametric kernel-based conditional density estimation technique to infer accurate and concise dynamic models of system evolution from data. The training data for these models have been acquired from demonstrations by teleoperation. The trained data-driven models for mode-dependent state evolution and state-dependent mode evolution are then used online for imitation of demonstrated tasks via particle filtering. The results of simulation and experimental validation with a hexapod robot are reported to establish generalization of the proposed learning and control algorithms.

Adaptive motion selection for online hand–eye calibration

Robotica ◽  
2007 ◽  
Vol 25 (5) ◽  
pp. 529-536
Author(s):  
Jing Zhang ◽  
Fanhuai Shi ◽  
Yuncai Liu
Keyword(s):  
Motion Planning ◽  
Dynamic Threshold ◽  
Selection Algorithm ◽  
Robot System ◽  
End Effector ◽  
Threshold Determination ◽  
Robot Gripper ◽  
Adaptive Motion ◽  
Selection For ◽  
Relative Pose

SUMMARYWhile a robot moves, online hand–eye calibration to determine the relative pose between the robot gripper/end-effector and the sensors mounted on it is very important in a vision-guided robot system. During online hand–eye calibration, it is impossible to perform motion planning to avoid degenerate motions and small rotations, which may lead to unreliable calibration results. This paper proposes an adaptive motion selection algorithm for online hand–eye calibration, featured by dynamic threshold determination for motion selection and getting reliable hand–eye calibration results. Simulation and real experiments demonstrate the effectiveness of our method.

How to turn managers into data-driven decision makers

2019 ◽  
Vol 25 (3) ◽  
pp. 553-578 ◽  
Author(s):  
Kevin Daniel André Carillo ◽  
Nadine Galy ◽  
Cameron Guthrie ◽  
Anne Vanhems
Keyword(s):  
Measurement Instrument ◽  
Data Driven ◽  
Business Analytics ◽  
Business World ◽  
Content Type ◽  
Multi Stage ◽  
Attitudes Toward Statistics ◽  
Attitude Toward Business ◽  
Professional Contexts ◽  
The Way

Purpose The purpose of this paper is to emphasize the need to engender a positive attitude toward business analytics in order for firms to more effectively transform into data-driven businesses, and for business schools to better prepare future managers. Design/methodology/approach This paper develops and validates a measurement instrument that captures the attitude toward business statistics, the foundation of business analytics. A multi-stage approach is implemented and the validation is conducted with a sample of 311 students from a business school. Findings The instrument has strong psychometric properties. It is designed so that it can be easily extrapolated to professional contexts and extended to the entire domain of business analytics. Research limitations/implications As the advent of a data-driven business world will impact the way organizations function and the way individuals think, work, communicate and interact, it is crucial to engage a transdisciplinary dialogue among domains that have the expertise to help train and transform current and future professionals. Practical implications The contribution provides educators and organizations with a means to measure and monitor attitudes toward statistics, the most anxiogenic component of business analytics. This is a first step in monitoring and developing an analytics mindset in both managers and students. Originality/value By demonstrating how the advent of the data-driven business era is transforming the DNA and functioning of organizations, this paper highlights the key importance of changing managers’ and all employees’ (to a lesser extent) mindset and way of thinking.

Sign in / Sign up

Export Citation Format

Share Document