Image Space Potential Fields: Constant Size Environment Representation for Vision-based Subsumption Control Architectures

TL;DR

This paper introduces a constant-size environment representation aligned with camera image space, facilitating real-time vision-based navigation and control without complex projections, suitable for subsumption control architectures.

Contribution

It proposes a novel environment representation that maintains constant size and aligns with image space, enabling efficient, sensor-space control in vision-based navigation.

Findings

Constant size environment representation enables real-time guarantees.

Representation aligns with camera image space for easier control.

Suitable for vision-based subsumption control architectures.

Abstract

This technical report presents an environment representation for use in vision-based navigation. The representation has two useful properties: 1) it has constant size, which can enable strong run-time guarantees to be made for control algorithms using it, and 2) it is structurally similar to a camera image space, which effectively allows control to operate in the sensor space rather than employing difficult, and often inaccurate, projections into a structurally different control space (e.g. Euclidean). The presented representation is intended to form the basis of a vision-based subsumption control architecture.