Learning to Visually Navigate in Photorealistic Environments Without any Supervision

By Lina Mezghani, Sainbayar Sukhbaatar, Arthur Szlam, Armand Joulin, Piotr Bojanowski. 2020

12 citations recorded by the source corpus.

Learning to navigate in a realistic setting where an agent must rely solely on visual inputs is a challenging task, in part because the lack of position information makes it difficult to provide supervision during training. In this paper, we introduce a novel approach for learning to navigate from image inputs without external supervision or reward. Our approach consists of three stages: learning a good representation of first-person views, then learning to explore using memory, and finally learning to navigate by setting its own goals. The model is trained with intrinsic rewards only so that it can be applied to any environment with image observations. We show the benefits of our approach by training an agent to navigate challenging photo-realistic environments from the Gibson dataset with RGB inputs only.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jiafei Duan
2. Samson Yu
3. Cheston Tan
4. Tangyao Li
5. Huaiyu Zhu

In Computer Vision and Pattern Recognition

1. Jiafei Duan
2. Samson Yu
3. Cheston Tan
4. Tangyao Li
5. Huaiyu Zhu

Citations in the corpus

• A Survey of Embodied AI: From Simulators to Research Tasks (2021, background): “In the latter case, the agent builds the map as it navigates an unseen test environment [57, 58, 44], which”