ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects

Abstract

We revisit the problem of Object-Goal Navigation (ObjectNav). In its simplest form, ObjectNav is defined as the task of navigating to an object, specified by its label, in an unexplored environment. In particular, the agent is initialized at a random location and pose in an environment and asked to find an instance of an object category, e.g., find a chair, by navigating to it. As the community begins to show increased interest in semantic goal specification for navigation tasks, a number of different often-inconsistent interpretations of this task are emerging. This document summarizes the consensus recommendations of this working group on ObjectNav. In particular, we make recommendations on subtle but important details of evaluation criteria (for measuring success when navigating towards a target object), the agent's embodiment parameters, and the characteristics of the environments within which the task is carried out. Finally, we provide a detailed description of the instantiation of these recommendations in challenges organized at the Embodied AI workshop at CVPR 2020 http://embodied-ai.org .

References in corpus (3)

• On Evaluation of Embodied Navigation Agents
• MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments
• ViZDoom Competitions: Playing Doom from Pixels

Cited by in corpus (18)

• Can an Embodied Agent Find Your "Cat-shaped Mug"? LLM-Guided Exploration for Zero-Shot Object Navigation
• Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI
• A Survey of Embodied AI: From Simulators to Research Tasks
• Habitat 2.0: Training Home Assistants to Rearrange their Habitat
• From Seeing to Moving: A Survey on Learning for Visual Indoor Navigation (VIN)
• No RL, No Simulation: Learning to Navigate without Navigating
• Unsupervised Active Visual Search with Monte Carlo planning under Uncertain Detections
• Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion
• Learning to Map for Active Semantic Goal Navigation
• SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigation
• Landmark Policy Optimization for Object Navigation Task
• Dialogue Object Search
• PanGEA: The Panoramic Graph Environment Annotation Toolkit
• Semantic Audio-Visual Navigation
• Building Intelligent Autonomous Navigation Agents
• Pushing it out of the Way: Interactive Visual Navigation
• Hierarchical and Partially Observable Goal-driven Policy Learning with Goals Relational Graph
• Realistic PointGoal Navigation via Auxiliary Losses and Information Bottleneck