Cross-entropy based stochastic optimization of robot trajectories using heteroscedastic continuous-time Gaussian processes

Petrović, Luka; Peršić, Juraj; Seder, Marija; Marković, Ivan

doi:10.1016/j.robot.2020.103618

Cited by 16 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As an avenue for future work, we note that the method presented herein can easily be integrated into existing control and planning pipelines-it would be interesting to benchmark their performance. We have previously integrated a manipulability maximization term in the trajectory optimization formulation of [29]; we plan to integrate the proposed index in a similar formulation that is better suited for nonlinear objectives [33].…”

Section: Discussionmentioning

confidence: 99%

A Riemannian Metric for Geometry-Aware Singularity Avoidance by Articulated Robots

Marić,

Petrović,

Guberina

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Articulated robots such as manipulators increasingly must operate in uncertain and dynamic environments where interaction (with human coworkers, for example) is necessary. In these situations, the capacity to quickly adapt to unexpected changes in operational space constraints is essential. At certain points in a manipulator's configuration space, termed singularities, the robot loses one or more degrees of freedom (DoF) and is unable to move in specific operational space directions. The inability to move in arbitrary directions in operational space compromises adaptivity and, potentially, safety. We introduce a geometry-aware singularity index, defined using a Riemannian metric on the manifold of symmetric positive definite matrices, to provide a measure of proximity to singular configurations. We demonstrate that our index avoids some of the failure modes and difficulties inherent to other common indices. Further, we show that this index can be differentiated easily, making it compatible with local optimization approaches used for operational space control. Our experimental results establish that, for reaching and path following tasks, optimization based on our index outperforms a common manipulability maximization technique, ensuring singularity-robust motions.

show abstract

Section: Discussionmentioning

confidence: 99%

A Riemannian Metric for Geometry-Aware Singularity Avoidance by Articulated Robots

Marić,

Petrović,

Guberina

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Zheng et al proposed a laser-based person detection and obstacle avoidance algorithm for differential drive robots applied to a handling robot to transport materials along a reference path in the hospital field ( Zheng et al, 2021 ). Luka Petrović et al proposed a new trajectory planning algorithm using stochastic optimization in order to find a continuous-time Gaussian process for collision-free trajectory generation ( Petrović et al, 2020 ). Deng et al proposed a multi-obstacle path planning and optimization method that uses convex packages to optimize the base obstacles and obtain the corresponding set of base obstacle points, and uses cubic bezier curves to smooth the path to fit the kinematic model of the robot ( Deng et al, 2021 ).…”

Section: Related Workmentioning

confidence: 99%

Genetic Algorithm-Based Trajectory Optimization for Digital Twin Robots

Liu

Tao

et al. 2022

Front. Bioeng. Biotechnol.

102

View full text Add to dashboard Cite

Mobile robots have an important role in material handling in manufacturing and can be used for a variety of automated tasks. The accuracy of the robot’s moving trajectory has become a key issue affecting its work efficiency. This paper presents a method for optimizing the trajectory of the mobile robot based on the digital twin of the robot. The digital twin of the mobile robot is created by Unity, and the trajectory of the mobile robot is trained in the virtual environment and applied to the physical space. The simulation training in the virtual environment provides schemes for the actual movement of the robot. Based on the actual movement data returned by the physical robot, the preset trajectory of the virtual robot is dynamically adjusted, which in turn enables the correction of the movement trajectory of the physical robot. The contribution of this work is the use of genetic algorithms for path planning of robots, which enables trajectory optimization of mobile robots by reducing the error in the movement trajectory of physical robots through the interaction of virtual and real data. It provides a method to map learning in the virtual domain to the physical robot.

show abstract

“…Specifically, path optimisation is the process of designing a path that can minimise/maximise some measure of performance while satisfying a series of constraints [26]. Compared with the other methods mentioned above, path optimisation methods provide several benefits including: 1) the capability of smoothing and shortening the path in a coupled way during the planning process and 2) superiority in computational speed making it suitable for online planning in environments with rapidly changing factors [27].…”

Section: Related Workmentioning

confidence: 99%

Anisotropic GPMP2: A Fast Continuous-Time Gaussian Processes Based Motion Planner for Unmanned Surface Vehicles in Environments With Ocean Currents

Meng

Liu

Bucknall

et al. 2022

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

show abstract

Cross-entropy based stochastic optimization of robot trajectories using heteroscedastic continuous-time Gaussian processes

Cited by 16 publications

References 16 publications

A Riemannian Metric for Geometry-Aware Singularity Avoidance by Articulated Robots

A Riemannian Metric for Geometry-Aware Singularity Avoidance by Articulated Robots

Genetic Algorithm-Based Trajectory Optimization for Digital Twin Robots

Anisotropic GPMP2: A Fast Continuous-Time Gaussian Processes Based Motion Planner for Unmanned Surface Vehicles in Environments With Ocean Currents

Contact Info

Product

Resources

About