lauriasuo's picture
Update README.md
34f780c verified
metadata
tags:
  - model_hub_mixin
  - pytorch_model_hub_mixin
pipeline_tag: robotics

PointGoal navigation policy trained with the FrodoBots8K dataset.

Presented in the paper Data scaling for navigation in unknown environments

Project page | Code

Details

Architecture:

MLP-BC with Theia encoder + MLP action head

Dataset:

512H total, 8H from 64 distinct geographical locations

Usage

See the Github repo