Learning to Navigate from Simulation via Spatial and Semantic Information Synthesis with Noise Model Embedding

10/13/2019
by   Gang Chen, et al.
0

While training an end-to-end navigation network in the real world is usually of high cost, simulation provides a safe and cheap environment in this training stage. However, training neural network models in simulation brings up the problem of how to effectively transfer the model from simulation to the real world (sim-to-real). In this work, we regard the environment representation as a crucial element in this transfer process and propose a visual information pyramid (VIP) model to systematically investigate a practical environment representation. A novel representation composed of spatial and semantic information synthesis is then established accordingly, where noise model embedding is particularly considered. To explore the effectiveness of this representation, we compared the performance with representations popularly used in the literature in both simulated and real-world scenarios. Results suggest that our environment representation stands out. Furthermore, an analysis on the feature map is implemented to investigate the effectiveness through inner reaction, which could be irradiative for future researches on end-to-end navigation.

READ FULL TEXT
research
10/13/2019

Learning to Navigate from Simulation via Spatial and Semantic Information Synthesis

While training an end-to-end navigation network in the real world is usu...
research
12/02/2022

Navigating to Objects in the Real World

Semantic navigation is necessary to deploy mobile robots in uncontrolled...
research
12/19/2018

Learning On-Road Visual Control for Self-Driving Vehicles with Auxiliary Tasks

A safe and robust on-road navigation system is a crucial component of ac...
research
04/08/2019

Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigation

There has been an increasing interest in 3D indoor navigation, where a r...
research
05/12/2021

Out of the Box: Embodied Navigation in the Real World

The research field of Embodied AI has witnessed substantial progress in ...
research
08/17/2020

The Best of Both Worlds: Hybrid Data-Driven and Model-Based Vehicular Network Simulation

The analysis of the end-to-end behavior of novel mobile communication me...
research
11/09/2022

Efficient Neural Mapping for Localisation of Unmanned Ground Vehicles

Global localisation from visual data is a challenging problem applicable...

Please sign up or login with your details

Forgot password? Click here to reset