Interactive Robot-Environment Self-Calibration via Compliant Exploratory Actions

Abstract-- Calibrating robots into their workspaces is crucial for manipulation tasks. Existing calibration techniques often rely on sensors external to the robot (cameras, laser scanners, etc.) or specialized tools. This reliance complicates the calibration process and increases the costs and time requirements. Furthermore, the associated setup and measurement procedures require significant human intervention, which makes them more challenging to operate. Figure 1: Our self-calibration framework estimates the robotenvironment spatial relationship via compliant exploratory actions. Visualized in green is the environment's pose as currently estimated Often, such robot applications require probing points in the environment, manual operations are still an accurate pose of the robot frame relative to a frame of the often required since existing simulation-based interaction and workspace to be provided by a calibration procedure before outcome prediction [11]-[13] have not shown to generalize task execution.