iSDF: Real-Time Neural Signed Distance Fields for Robot Perception
Joseph D. Ortiz, Alexander Clegg, Jing Dong, Edgar Sucar, David Novotný, Michael Zollhoefer, Mustafa Mukadam
Abstract
Online optimisation / continual learning Latest frame (RGB unused) Fig. To train the network in real-time we develop a batch-based self-supervision method. This network can be queried online to obtain collision costs and gradients for use by downstream planners in domains from navigation to manipulation. The trajectory (red) of the camera (green) is visualised on top of the zero level set (top row) and SDF slice (middle row) generated by iSDF over time (left to right).
Topics & Concepts
Computer scienceRobotPerceptionArtificial intelligenceArtificial neural networkComputer visionPsychologyNeuroscienceInfrastructure Maintenance and MonitoringVideo Surveillance and Tracking MethodsRobotics and Sensor-Based Localization