Learning Ground Traversability From Simulations

By R. Omar Chavez-Garcia, Jérôme Guzzi, Luca Maria Gambardella, Alessandro Giusti. 2017

112 citations recorded by the source corpus.

Mobile ground robots operating on unstructured terrain must predict which areas of the environment they are able to pass in order to plan feasible paths. We address traversability estimation as a heightmap classification problem: we build a convolutional neural network that, given an image representing the heightmap of a terrain patch, predicts whether the robot will be able to traverse such patch from left to right. The classifier is trained for a specific robot model (wheeled, tracked, legged, snake-like) using simulation data on procedurally generated training terrains; the trained classifier can be applied to unseen large heightmaps to yield oriented traversability maps, and then plan traversable paths. We extensively evaluate the approach in simulation on six real-world elevation dataset, and run a real-robot validation in one indoor and one outdoor environment.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Robot Parkour Learning (2023, methodology): “Classical modular methods rely on decoupled visual perception and control pipelines, where the elevation maps [75, 76, 77, 78, 79, 80, 81], traversability maps [82, 83, 84, 85], or state estimators [86, 87, 88, 89, 90, 91, 92, 93, 94, 95] are constructed as intermediate representations for downstrea”
ANYmal parkour: Learning agile navigation for quadrupedal robots (2023, background): “Finally, after training in simulation, all the modules are deployed in the real world.”
Legged Locomotion in Challenging Terrains using Egocentric Vision (2022, methodology): “Other methods forgo explicit 247 foothold optimization and learn traversibility maps instead [66, 67, 68, 69].”