GA-Nav: Efficient Terrain Segmentation for Robot Navigation in Unstructured Outdoor Environments

  title={GA-Nav: Efficient Terrain Segmentation for Robot Navigation in Unstructured Outdoor Environments},
  author={Tianrui Guan and Divya Kothandaraman and Rohan Chandra and Adarsh Jagan Sathyamoorthy and K. M. K. Weerakoon and Dinesh Manocha},
  journal={IEEE Robotics and Automation Letters},
We propose GA-Nav, a novel group-wise attention mechanism to identify safe and navigable regions in unstructured environments from RGB images. Our group-wise attention method extracts multi-scale features from each type of terrain independently and classifies terrains based on their navigability levels using coarse-grained semantic segmentation. Our novel loss can be embedded within any backbone network to explicitly focus on the different groups’ features, at a low spatial resolution. Our… 

Overleaf Example

A novel hybrid architecture that utilizes an intermediate output from a fully trained attention DRL policy as a navigation cost map for outdoor navigation, which generates dynamically feasible velocities along stable, traversable regions to reach the robot’s goals.

Probabilistic Traversability Model for Risk-Aware Motion Planning in Off-Road Environments

—A key challenge in off-road navigation is that even visually similar or semantically identical terrain may have substantially different traction properties. Existing work typically assumes a nominal

VINet: Visual and Inertial-based Terrain Classification and Adaptive Navigation over Unknown Terrain

This work presents a visual and inertial-based terrain classification network (VINet) for robotic navigation over different traversable surfaces and uses a novel navigation-based labeling scheme and adaptive control framework to make predictions according to terrain navigation properties and lead to better performance on both terrain classing and navigation control on known and unknown surfaces.



A RUGD Dataset for Autonomous Navigation and Visual Perception in Unstructured Outdoor Environments

The Robot Unstructured Ground Driving (RUGD) dataset is introduced with video sequences captured from a small, unmanned mobile robot traversing in unstructured environments, which contains significantly more terrain types, irregular class boundaries, minimal structured markings, and presents challenging visual properties often experienced in off road navigation.

Learning terrain segmentation with classifier ensembles for autonomous robot navigation in unstructured environments

The most important being that the proposed near‐to‐far Best‐K Ensemble Algorithm, with appropriate parameter selection, outperforms the single‐model, nonensemble baseline approach in far‐field terrain classification.

RELLIS-3D Dataset: Data, Benchmarks and Analysis

RELLIS-3D is a multimodal dataset collected in an off-road environment, which contains annotations for 13,556 LiDAR scans and 6,235 images and evaluates the current state of the art deep learning semantic segmentation models on this dataset.

Obstacle Detection and Terrain Classification for Autonomous Off-Road Navigation

An obstacle detection technique that does not rely on typical structural assumption on the scene; a color-based classification system to label the detected obstacles according to a set of terrain classes; and an algorithm for the analysis of ladar data that allows one to discriminate between grass and obstacles, even when such obstacles are partially hidden in the grass are proposed.

CGNet: A Light-Weight Context Guided Network for Semantic Segmentation

This work proposes a novel Context Guided Network (CGNet), which is a light-weight and efficient network for semantic segmentation, and develops CGNet which captures contextual information in all stages of the network.

Traversable Region Estimation for Mobile Robots in an Outdoor Image

A novel method to estimate appropriate traversable regions from an outdoor scene image that reflects the common sense of people through the application of two score functions in region estimation process.

Off-Road Terrain Traversability Analysis and Hazard Avoidance for UGVs

Algorithms are presented that analyze the off-road terrain using a point cloud produced by a 3D laser range finder, determine potential hazards both above ground and those where the ground cover has a negative slope, then plan safe routes around those hazards.

PSANet: Point-wise Spatial Attention Network for Scene Parsing

The point-wise spatial attention network (PSANet) is proposed to relax the local neighborhood constraint and achieves top performance on various competitive scene parsing datasets, including ADE20K, PASCAL VOC 2012 and Cityscapes, demonstrating its effectiveness and generality.

Training a terrain traversability classifier for a planetary rover through simulation

A neural network classifier and its training algorithm are presented, and the results of its output as well as other popular classifiers show high accuracy on test data sets after training.

Multi-Modal Fusion Transformer for End-to-End Autonomous Driving

This work demonstrates that imitation learning policies based on existing sensor fusion methods under-perform in the presence of a high density of dynamic agents and complex scenarios, which require global contextual reasoning, and proposes TransFuser, a novel Multi-Modal Fusion Transformer to integrate image and LiDAR representations using attention.