English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Safe robot motion generation is critical for practical applications frommanufacturing to homes. In this work, we proposed a stochasticoptimization-based motion generation method to generate collision-free andtime-optimal motion for the articulated robot represented by composite signeddistance field (SDF) networks. First, we propose composite SDF networks tolearn the SDF for articulated robots. The learned composite SDF networkscombined with the kinematics of the robot allow for quick and accurateestimates of the minimum distance between the robot and obstacles in a batchfashion. Then, a stochastic optimization-based trajectory planning algorithmgenerates a spatial-optimized and collision-free trajectory offline with thelearned composite SDF networks. This stochastic trajectory planner isformulated as a Bayesian Inference problem with a time-normalized Gaussianprocess prior and exponential likelihood function. The Gaussian process priorcan enforce initial and goal position constraints in Configuration Space.Besides, it can encode the correlation of waypoints in time series. Thelikelihood function aims at encoding task-related cost terms, such as collisionavoidance, trajectory length penalty, boundary avoidance, etc. The kernelupdating strategies combined with model-predictive path integral (MPPI) isproposed to solve the maximum a posteriori inference problems. Lastly, weintegrate the learned composite SDF networks into the trajectory planningalgorithm and apply it to a Franka Emika Panda robot. The simulation andexperiment results validate the effectiveness of the proposed method.

Collision-free Motion Generation Based on Stochastic Optimization and Composite Signed Distance Field Networks of Articulated Robot