Log In Sign Up

A Few Shot Adaptation of Visual Navigation Skills to New Observations using Meta-Learning

by   Qian Luo, et al.

Target-driven visual navigation is a challenging problem that requires a robot to find the goal using only visual inputs. Many researchers have demonstrated promising results using deep reinforcement learning (deep RL) on various robotic platforms, but typical end-to-end learning is known for its poor extrapolation capability to new scenarios. Therefore, learning a navigation policy for a new robot with a new sensor configuration or a new target still remains a challenging problem. In this paper, we introduce a learning algorithm that enables rapid adaptation to new sensor configurations or target objects with a few shots. We design a policy architecture with latent features between perception and inference networks and quickly adapt the perception network via meta-learning while freezing the inference network. Our experiments show that our algorithm adapts the learned navigation policy with only three shots for unseen situations with different sensor configurations or different target colors. We also analyze the proposed algorithm by investigating various hyperparameters.


page 1

page 5


Visual Perception Generalization for Vision-and-Language Navigation via Meta-Learning

Vision-and-language navigation (VLN) is a challenging task that requires...

Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms

Reinforcement learning methods can achieve significant performance but r...

Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation

Visual navigation is a task of training an embodied agent by intelligent...

MELD: Meta-Reinforcement Learning from Images via Latent State Models

Meta-reinforcement learning algorithms can enable autonomous agents, suc...

Learning Fast Adaptation with Meta Strategy Optimization

The ability to walk in new scenarios is a key milestone on the path towa...

Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning

Learning is an inherently continuous phenomenon. When humans learn a new...

Using Supervised Deep-Learning to Model Edge-FBG Shape Sensors

Continuum robots in robot-assisted minimally invasive surgeries provide ...