Visual Representation Learning for Preference-Aware Path Planning

Autonomous mobile robots deployed in outdoor environments must reason about different types of terrain for both safety (e. g. , prefer dirt over mud) and deployer preferences (e. g. , prefer dirt path over flower beds). Most existing solutions to this preference-aware path planning problem use semantic segmentation to classify terrain types from camera images, and then ascribe costs to each type. Unfortunately, there are three key limitations of such approaches - they 1) require preenumeration of the discrete terrain types, 2) are unable to handle hybrid terrain types (e. g. , grassy dirt), and 3) require expensive labelled data to train visual semantic segmentation. We introduce Visual Representation Learning for Preference-Aware Path Planning (VRL-PAP), an alternative approach that overcomes all three limitations: VRL-PAP leverages un-labelled human demonstrations of navigation to autonomously generate triplets for learning visual representations of terrain that are viewpoint invariant and encode terrain types in a continuous representation space. The learned representations are then used along with the same unlabelled human navigation demonstrations to learn a mapping from the representation space to terrain costs. At run time, VRL-PAP maps from images to representations and then representations to costs to perform preference-aware path planning. We present empirical results from challenging outdoor settings that demonstrate VRL-PAP 1) is successfully able to pick paths that reflect demonstrated preferences, 2) is comparable in execution to geometric navigation with a highly detailed manually annotated map (without requiring such annotations), 3) is able to generalize to novel terrain types with minimal additional unlabeled demonstrations.

Authors

• Kavan Singh Sikand
• Sadegh Rabiee
• Adam Uccello
• Xuesu Xiao
• Garrett Warnell
• Joydeep Biswas

Keywords

• Representation learning
• Visualization
• Image segmentation
• Costs
• Navigation
• Annotations
• Semantics
• Visual Representation
• Path Planning
• Visual Learning
• Visual Representation Learning
• Semantic Segmentation
• Representation Of Space
• Manual Annotation
• Mobile Robot
• Terrain Types
• Automated Guided Vehicles
• Raised Beds
• Loss Function
• Environmental Variables
• Training Dataset
• Cost Function
• Visual Information
• Visual Function
• Generative Adversarial Networks
• Learning Problem
• Number Of Demonstrations
• Image Patches
• Intermediate Representation
• Inverse Reinforcement Learning
• Reference Trajectory
• Patch Extraction
• Tallgrass
• Machine Vision
• Latent Space
• Self-supervised Manner