DeepAI AI Chat
Log In Sign Up

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

by   Jinwook Huh, et al.

This paper presents c2g-HOF networks which learn to generate cost-to-go functions for manipulator motion planning. The c2g-HOF architecture consists of a cost-to-go function over the configuration space represented as a neural network (c2g-network) as well as a Higher Order Function (HOF) network which outputs the weights of the c2g-network for a given input workspace. Both networks are trained end-to-end in a supervised fashion using costs computed from traditional motion planners. Once trained, c2g-HOF can generate a smooth and continuous cost-to-go function directly from workspace sensor inputs (represented as a point cloud in 3D or an image in 2D). At inference time, the weights of the c2g-network are computed very efficiently and near-optimal trajectories are generated by simply following the gradient of the cost-to-go function. We compare c2g-HOF with traditional planning algorithms for various robots and planning scenarios. The experimental results indicate that planning with c2g-HOF is significantly faster than other motion planning algorithms, resulting in orders of magnitude improvement when including collision checking. Furthermore, despite being trained from sparsely sampled trajectories in configuration space, c2g-HOF generalizes to generate smoother, and often lower cost, trajectories. We demonstrate cost-to-go based planning on a 7 DoF manipulator arm where motion planning in a complex workspace requires only 0.13 seconds for the entire trajectory.


page 1

page 4

page 5

page 6


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

Traditional motion planning is computationally burdensome for practical ...

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

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

Multimodal Trajectory Optimization for Motion Planning

Existing motion planning methods often have two drawbacks: 1) goal confi...

Learning To Find Shortest Collision-Free Paths From Images

Motion planning is a fundamental problem in robotics and machine percept...

TRON: A Fast Solver for Trajectory Optimization with Non-Smooth Cost Functions

Trajectory optimization is an important tool for control and planning of...

State Supervised Steering Function for Sampling-based Kinodynamic Planning

Sampling-based motion planners such as RRT* and BIT*, when applied to ki...

Safe Motion Planning for a Mobile Robot Navigating in Environments Shared with Humans

In this paper, a robot navigating an environment shared with humans is c...