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

A robot self-model is a task-agnostic representation of the robot's physicalmorphology that can be used for motion planning tasks in absence of classicalgeometric kinematic models. In particular, when the latter are hard to engineeror the robot's kinematics change unexpectedly, human-free self-modeling is anecessary feature of truly autonomous agents. In this work, we leverage neuralfields to allow a robot to self-model its kinematics as a neural-implicit querymodel learned only from 2D images annotated with camera poses andconfigurations. This enables significantly greater applicability than existingapproaches which have been dependent on depth images or geometry knowledge. Tothis end, alongside a curricular data sampling strategy, we propose a newencoder-based neural density field architecture for dynamic object-centricscenes conditioned on high numbers of degrees of freedom (DOFs). In a 7-DOFrobot test setup, the learned self-model achieves a Chamfer-L2 distance of 2%of the robot's workspace dimension. We demonstrate the capabilities of thismodel on a motion planning task as an exemplary downstream application.

High-Degrees-of-Freedom Dynamic Neural Fields for Robot Self-Modeling and Motion Planning