Benchmark aids robotic vision in finding and grasping small objects

BRAVE-6D: Benchmark for Robotic Active Vision in 6DOF Pose Estimation

Robotics

Summary

Robots have a hard time detecting and picking up tiny objects. To help with this, the authors created BRAVE-6D, a special test setup that lets robots move around and see objects better to guess their exact position and orientation. They use computer-generated scenes to test these robot vision methods so that everyone can compare fairly. The authors also show some example solutions where robots actively move and use vision to find and locate small objects precisely.

What this means in practice

Authors

Philipp Ausserlechner, Bernhard Neuberger, Alessandro Scherl, Michael Schebek, Stefan Thalhammer, Markus Vincze

Abstract

Detecting and grasping small objects remains a significant challenge in robotics. Active vision, where the robot moves closer to the object, is an intuitive solution, yet comparing approaches on common ground is difficult since identical physical scene setups are required. Hence, we introduce BRAVE-6D, a benchmark designed to evaluate robotic active vision systems for object pose estimation, a crucial first step in grasping objects. BRAVE-6D leverages view synthesis based on Gaussian Splats (3DGS) to provide scenes and tools for benchmarking active vision systems. We show baseline solutions performing visual servoing within the scene and accurately estimating the poses of small objects.