Learning to Map for Active Semantic Goal Navigation
arXiv:2106.15648
Abstract
We consider the problem of object goal navigation in unseen environments. Solving this problem requires learning of contextual semantic priors, a challenging endeavour given the spatial and semantic variability of indoor environments. Current methods learn to implicitly encode these priors through goal-oriented navigation policy functions operating on spatial representations that are limited to the agent's observable areas. In this work, we propose a novel framework that actively learns to generate semantic maps outside the field of view of the agent and leverages the uncertainty over the semantic classes in the unobserved areas to decide on long term goals. We demonstrate that through this spatial prediction strategy, we are able to learn semantic priors in scenes that can be leveraged in unknown environments. Additionally, we show how different objectives can be defined by balancing exploration with exploitation during searching for semantic targets. Our method is validated in the visually realistic environments of the Matterport3D dataset and show improved results on object goal navigation over competitive baselines.
References in corpus (20)
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
- A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
- Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
- On Evaluation of Embodied Navigation Agents
- Bayesian Active Learning for Classification and Preference Learning
- Matterport3D: Learning from RGB-D Data in Indoor Environments
- AI2-THOR: An Interactive 3D Environment for Visual AI
- Building Generalizable Agents with a Realistic and Rich 3D Environment
- Object Goal Navigation using Goal-Oriented Semantic Exploration
- Learning to Explore using Active Neural SLAM
- ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects
- Neural Map: Structured Memory for Deep Reinforcement Learning
- UCB Exploration via Q-Ensembles
- Exploration vs Exploitation vs Safety: Risk-averse Multi-Armed Bandits
- MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation
- Benchmarking Classic and Learned Navigation in Complex 3D Environments
- Learning Exploration Policies for Navigation
- Visual Semantic Navigation using Scene Priors
- Simultaneous Mapping and Target Driven Navigation
- Semantic Audio-Visual Navigation