Object Goal Navigation using Goal-Oriented Semantic Exploration

Abstract

This work studies the problem of object goal navigation which involves navigating to an instance of the given object category in unseen environments. End-to-end learning-based navigation methods struggle at this task as they are ineffective at exploration and long-term planning. We propose a modular system called, `Goal-Oriented Semantic Exploration' which builds an episodic semantic map and uses it to explore the environment efficiently based on the goal object category. Empirical results in visually realistic simulation environments show that the proposed model outperforms a wide range of baselines including end-to-end learning-based methods as well as modular map-based methods and led to the winning entry of the CVPR-2020 Habitat ObjectNav Challenge. Ablation analysis indicates that the proposed model learns semantic priors of the relative arrangement of objects in a scene, and uses them to explore efficiently. Domain-agnostic module design allow us to transfer our model to a mobile robot platform and achieve similar performance for object goal navigation in the real-world.

Winner of the CVPR 2020 AI-Habitat Object Goal Navigation Challenge. See the project webpage at https://devendrachaplot.github.io/projects/semantic-exploration.html

References in corpus (14)

• Rethinking Atrous Convolution for Semantic Image Segmentation
• On Evaluation of Embodied Navigation Agents
• Learning to Navigate in Complex Environments
• Matterport3D: Learning from RGB-D Data in Indoor Environments
• Learning to Explore using Active Neural SLAM
• MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments
• Grounded Language Learning in a Simulated 3D World
• Playing FPS Games with Deep Reinforcement Learning
• Neural Map: Structured Memory for Deep Reinforcement Learning
• Gated-Attention Architectures for Task-Oriented Language Grounding
• PyRobot: An Open-source Robotics Framework for Research and Benchmarking
• Visual Semantic Navigation using Scene Priors
• DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames
• Learning and Planning with a Semantic Model

Cited by in corpus (19)

• L3MVN: Leveraging Large Language Models for Visual Target Navigation
• Frontier Semantic Exploration for Visual Target Navigation
• A Survey of Embodied AI: From Simulators to Research Tasks
• Finding Things in the Unknown: Semantic Object-Centric Exploration with an MAV
• Benchmarking Neural Radiance Fields for Autonomous Robots: An Overview
• Consistent Attack: Universal Adversarial Perturbation on Embodied Vision Navigation
• Implicit Obstacle Map-driven Indoor Navigation Model for Robust Obstacle Avoidance
• Leveraging Large Language Model-based Room-Object Relationships Knowledge for Enhancing Multimodal-Input Object Goal Navigation
• SOON: Scenario Oriented Object Navigation with Graph-based Exploration
• Semantic Environment Atlas for Object-Goal Navigation
• SGoLAM: Simultaneous Goal Localization and Mapping for Multi-Object Goal Navigation
• Learning to Map for Active Semantic Goal Navigation
• Reinforcement Learning-based Visual Navigation with Information-Theoretic Regularization
• Spot the Difference: A Novel Task for Embodied Agents in Changing Environments
• MaAST: Map Attention with Semantic Transformersfor Efficient Visual Navigation
• Landmark Policy Optimization for Object Navigation Task
• CI-Net: Contextual Information for Joint Semantic Segmentation and Depth Estimation
• Multi-Agent Embodied Visual Semantic Navigation with Scene Prior Knowledge
• Multitask Adaptation by Retrospective Exploration with Learned World Models