Real-time Optimal Navigation Planning Using Learned Motion Costs

Navigation on challenging terrain topographies requires the understanding of robots' locomotion capabilities to produce optimal solutions. We present an integrated framework for real-time autonomous navigation of mobile robots based on elevation maps. The framework performs rapid global path pl...

Full description

Saved in:
Bibliographic Details
Main Authors: Yang, Bowen, Wellhausen, Lorenz, Miki, Takahiro, Liu, Ming, Hutter, Marco
Format: Conference Proceeding
Language:English
Subjects:
Computational modeling
Costs
Navigation
Real-time systems
Sampling methods
Surfaces
Training data
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Navigation on challenging terrain topographies requires the understanding of robots' locomotion capabilities to produce optimal solutions. We present an integrated framework for real-time autonomous navigation of mobile robots based on elevation maps. The framework performs rapid global path planning and optimization that is aware of the locomotion capabilities of the robot. A GPU-aided, sampling-based path planner combined with a gradient-based path optimizer provides optimal paths by using a neural network-based locomotion cost predictor which is trained in simulation. We show that our approach is capable of planning and optimizing paths three orders of magnitude faster than RRT* on GPU-enabled hardware, enabling real-time deployment on mobile platforms. We successfully evaluate the framework on the ANYmal C quadrupedal robot in both simulations and real-world environments for path planning tasks on multiple complex terrains.
ISSN:2577-087X
DOI:10.1109/ICRA48506.2021.9561861