DeepAI AI Chat
Log In Sign Up

Learning to Generate Cost-to-Go Functions for Efficient Motion Planning

by   Jinwook Huh, et al.

Traditional motion planning is computationally burdensome for practical robots, involving extensive collision checking and considerable iterative propagation of cost values. We present a novel neural network architecture which can directly generate the cost-to-go (c2g) function for a given configuration space and a goal configuration. The output of the network is a continuous function whose gradient in configuration space can be directly used to generate trajectories in motion planning without the need for protracted iterations or extensive collision checking. This higher order function (i.e. a function generating another function) representation lies at the core of our motion planning architecture, c2g-HOF, which can take a workspace as input, and generate the cost-to-go function over the configuration space map (C-map). Simulation results for 2D and 3D environments show that c2g-HOF can be orders of magnitude faster at execution time than methods which explore the configuration space during execution. We also present an implementation of c2g-HOF which generates trajectories for robot manipulators directly from an overhead image of the workspace.


page 2

page 5


Cost-to-Go Function Generating Networks for High Dimensional Motion Planning

This paper presents c2g-HOF networks which learn to generate cost-to-go ...

Predicting Sample Collision with Neural Networks

Many state-of-art robotics applications require fast and efficient motio...

Learning Configuration Space Belief Model from Collision Checks for Motion Planning

For motion planning in high dimensional configuration spaces, a signific...

Estimating Configuration Space Belief from Collision Checks for Motion Planning

For motion planning in high dimensional configuration spaces, a signific...

Comparing SONN Types for Efficient Robot Motion Planning in the Configuration Space

Motion planning in the configuration space (C-space) induces benefits, s...

Object Gathering with a Tethered Robot Duo

We devise a cooperative planning framework to generate optimal trajector...

Learning Continuous Cost-to-Go Functions for Non-holonomic Systems

This paper presents a supervised learning method to generate continuous ...