Talks

MS Defense: TERRAIN SEGMENTATION AND TRAVERSABILITY ANALYSIS IN UNSTRUCTURED OUTDOOR ENVIRONMENTS

Tianrui Guan

5105 Brendan Iribe Center for Computer Science and Engineering (IRB)

Monday, November 22, 2021, 1:00-3:00 pm

You are subscribed to this talk through .
You are watching this talk through .
You are subscribed to this talk. (unsubscribe, watch)
You are watching this talk. (unwatch, subscribe)
You are not subscribed to this talk. (watch, subscribe)

Abstract

We present a new learning-based method for identifying safe and navigable regions in off-road terrains and unstructured environments from RGB images. Our approach consists of classifying groups of terrains based on their navigability levels using coarse-grained semantic segmentation. We propose a transformer-based deep neural network architecture that uses a novel group-wise attention mechanism to distinguish between navigability levels of different terrains. Our group-wise attention heads enable the network to explicitly focus on the different groups and improve the accuracy. We show through extensive evaluations on the RUGD and RELLIS-3D datasets that our learning algorithm improves visual perception accuracy in off-road terrains for navigation. We compare our approach with prior work on these datasets and achieve an improvement over the state-of-the-art mIoU by 6.74-39.1% on RUGD and 3.82-10.64% on RELLIS-3D. In addition, we deploy our method on a Clearpath Jackal robot. Our approach improves the performance of the navigation algorithm in terms of average progress towards the goal by 54.73% and the false positives in terms of forbidden region by 29.96%.

Examining Committee:

Chair:
Members:

Dr. Ming Lin
Dr. Sahil Shah
Dr. Dinesh Manocha
Dr. Aniket Bera

Bio

Tianrui is a second year Master student and an incoming PhD student at UMD. His primary work is on computer vision, robotic perception and terrain traversability analysis for mobile robot.

This talk is organized by Tom Hurst