Gated Path Planning Networks

06/17/2018
by   Lisa Lee, et al.
2

Value Iteration Networks (VINs) are effective differentiable path planning modules that can be used by agents to perform navigation while still maintaining end-to-end differentiability of the entire architecture. Despite their effectiveness, they suffer from several disadvantages including training instability, random seed sensitivity, and other optimization problems. In this work, we reframe VINs as recurrent-convolutional networks which demonstrates that VINs couple recurrent convolutions with an unconventional max-pooling activation. From this perspective, we argue that standard gated recurrent update equations could potentially alleviate the optimization issues plaguing VIN. The resulting architecture, which we call the Gated Path Planning Network, is shown to empirically outperform VIN on a variety of metrics such as learning speed, hyperparameter sensitivity, iteration count, and even generalization. Furthermore, we show that this performance gap is consistent across different maze transition types, maze sizes and even show success on a challenging 3D environment, where the planner is only provided with first-person RGB images.

READ FULL TEXT

page 3

page 10

research
06/08/2022

Integrating Symmetry into Differentiable Planning

We study how group symmetry helps improve data efficiency and generaliza...
research
04/29/2021

Capability Iteration Network for Robot Path Planning

Path planning is an important topic in robotics. Recently, value iterati...
research
05/04/2021

PathBench: A Benchmarking Platform for Classical and Learned Path Planning Algorithms

Path planning is a key component in mobile robotics. A wide range of pat...
research
05/11/2023

Value Iteration Networks with Gated Summarization Module

In this paper, we address the challenges faced by Value Iteration Networ...
research
04/01/2020

Generation of Paths in a Maze using a Deep Network without Learning

Trajectory- or path-planning is a fundamental issue in a wide variety of...
research
04/05/2019

Planning under risk and uncertainty based on Prospect-theoretic models

In this work, we develop a novel sampling-based motion planing approach ...

Please sign up or login with your details

Forgot password? Click here to reset