On Evaluation of Embodied Navigation Agents

by   Peter Anderson, et al.

Skillful mobile operation in three-dimensional environments is a primary topic of study in Artificial Intelligence. The past two years have seen a surge of creative work on navigation. This creative output has produced a plethora of sometimes incompatible task definitions and evaluation protocols. To coordinate ongoing and future research in this area, we have convened a working group to study empirical methodology in navigation research. The present document summarizes the consensus recommendations of this working group. We discuss different problem statements and the role of generalization, present evaluation measures, and provide standard scenarios that can be used for benchmarking.


page 1

page 2

page 3

page 4


ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects

We revisit the problem of Object-Goal Navigation (ObjectNav). In its sim...

SEAN: Social Environment for Autonomous Navigation

Social navigation research is performed on a variety of robotic platform...

The NVIDIA PilotNet Experiments

Four years ago, an experimental system known as PilotNet became the firs...

Rightsstatements.org White Paper: Requirements for the Technical Infrastructure for Standardized International Rights Statements

This document is part of the deliverables created by the International R...

Streamlining Cross-Document Coreference Resolution: Evaluation and Modeling

Recent evaluation protocols for Cross-document (CD) coreference resoluti...

Embodied Navigation at the Art Gallery

Embodied agents, trained to explore and navigate indoor photorealistic e...

WLCG Authorisation from X.509 to Tokens

The WLCG Authorisation Working Group was formed in July 2017 with the ob...