Technology Category
Planning, Routing, and Scheduling: Optimization of Spatio-temporal SystemsIntelligent Robots: Localization, Mapping, and NavigationComputer Vision: Representation Learning for Vision
Predicting Dynamic Map States from Limited Field-of-View Sensor Data
Technology Category
Application Category
📝 Abstract
When autonomous systems are deployed in real-world scenarios, sensors are often subject to limited field-of-view (FOV) constraints, either naturally through system design, or through unexpected occlusions or sensor failures. In conditions where a large FOV is unavailable, it is important to be able to infer information about the environment and predict the state of nearby surroundings based on available data to maintain safe and accurate operation. In this work, we explore the effectiveness of deep learning for dynamic map state prediction based on limited FOV time series data. We show that by representing dynamic sensor data in a simple single-image format that captures both spatial and temporal information, we can effectively use a wide variety of existing image-to-image learning models to predict map states with high accuracy in a diverse set of sensing scenarios.
Problem
Research questions and friction points this paper is trying to address.
field-of-view
dynamic map prediction
sensor limitation
environment perception
autonomous systems
Innovation
Methods, ideas, or system contributions that make the work stand out.
limited field-of-view
dynamic map prediction
spatio-temporal representation
image-to-image learning
deep learning
🔎 Similar Papers
No similar papers found.
