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

TL;DR

This paper introduces a neural field-based method for robots to self-model their kinematics using only 2D images, enabling autonomous motion planning without traditional geometric models.

Contribution

It presents a novel neural density field architecture for high-DOF robot self-modeling from images, improving applicability over existing methods dependent on depth or geometry.

Findings

Achieved a 2% Chamfer-L2 distance in a 7-DOF robot setup.

Enabled robot self-modeling solely from 2D images and camera poses.

Demonstrated successful motion planning using the learned self-model.

Abstract

A robot self-model is a task-agnostic representation of the robot's physical morphology that can be used for motion planning tasks in the absence of a classical geometric kinematic model. In particular, when the latter is hard to engineer or the robot's kinematics change unexpectedly, human-free self-modeling is a necessary feature of truly autonomous agents. In this work, we leverage neural fields to allow a robot to self-model its kinematics as a neural-implicit query model learned only from 2D images annotated with camera poses and configurations. This enables significantly greater applicability than existing approaches which have been dependent on depth images or geometry knowledge. To this end, alongside a curricular data sampling strategy, we propose a new encoder-based neural density field architecture for dynamic object-centric scenes conditioned on high numbers of degrees of freedom (DOFs). In a 7-DOF robot test setup, the learned self-model achieves a Chamfer-L2 distance of 2% of the robot's workspace dimension. We demonstrate the capabilities of this model on motion planning tasks as an exemplary downstream application.