Simultaneous Mapping and Target Driven Navigation

By Georgios Georgakis, Yimeng Li, Jana Kosecka. 2019

17 citations recorded by the source corpus.

This work presents a modular architecture for simultaneous mapping and target driven navigation in indoors environments. The semantic and appearance stored in 2.5D map is distilled from RGB images, semantic segmentation and outputs of object detectors by convolutional neural networks. Given this representation, the mapping module learns to localize the agent and register consecutive observations in the map. The navigation task is then formulated as a problem of learning a policy for reaching semantic targets using current observations and the up-to-date map. We demonstrate that the use of semantic information improves localization accuracy and the ability of storing spatial semantic map aids the target driven navigation policy. The two modules are evaluated separately and jointly on Active Vision Dataset and Matterport3D environments, demonstrating improved performance on both localization and navigation tasks.

Subfields: Aerospace Engineering, 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 Aerospace Engineering

1. Cheston Tan
2. Jiafei Duan
3. Samson Yu
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): “There are also other evaluation metrics [17, 44, 58, 80] in addition to the two mentioned.”