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

We present TrueRMA, a data-efficient, model-free method to learncost-optimized robot trajectories over a wide range of starting points andendpoints. The key idea is to calculate trajectory waypoints in Cartesian spaceby recursively predicting orthogonal adaptations relative to the midpoints ofstraight lines. We generate a differentiable path by adding circular blendsaround the waypoints, calculate the corresponding joint positions with aninverse kinematics solver and calculate a time-optimal parameterizationconsidering velocity and acceleration limits. During training, the trajectoryis executed in a physics simulator and costs are assigned according to auser-specified cost function which is not required to be differentiable. Givena starting point and an endpoint as input, a neural network is trained topredict midpoint adaptations that minimize the cost of the resulting trajectoryvia reinforcement learning. We successfully train a KUKA iiwa robot to keep aball on a plate while moving between specified points and compare theperformance of TrueRMA against two baselines. The results show that our methodrequires less training data to learn the task while generating shorter andfaster trajectories.

TrueRMA: Learning Fast and Smooth Robot Trajectories with Recursive Midpoint Adaptations in Cartesian Space