Robot Arm Self-Calibration using RGB-D camera
Jiyong Lee, KangGeon Kim, BUM JAE YOU
AI summary
Problem
Traditional robot calibration relies on expensive external markers or fixed setups, making on-site recalibration impractical and limiting flexibility in textureless or range-constrained environments.
Approach
The method relocates the robot base to collect diverse RGB-D image data, uses SuperGlue for feature matching, and applies a local-to-global pose estimation scheme with SSIM-based filtering to simultaneously calibrate the robot arm and hand-eye transformation.
Key results
- Simultaneous kinematic and hand-eye calibration without external markers
- Base relocation strategy overcomes sensor range and textureless scene limitations
- Local-to-global pose estimation with 2D/3D error metrics improves noise robustness
- 7% higher calibration accuracy (lower RMSE) compared to laser tracker baseline
Why it matters
Enables accurate, low-cost, and flexible robot calibration for industrial automation and manipulation tasks without specialized equipment.
Abstract
Kinematic and hand-eye calibration of robotic arms is a critical research area in robotics, essential to ensuring the accuracy of manipulation tasks. The widely adopted methods for robotic arm calibration typically rely on specialized markers or external sensors to achieve precise measurements. However, these approaches are often expensive and require additional effort, such as the installation and maintenance of auxiliary equipment. Furthermore, many downstream tasks require separate hand-eye calibration steps because of differences between the sensors used for calibration and those used for task execution. Comprehensive calibration of both the robot arm and sensors plays a vital role in optimizing system performance. However, the robot’s posture could be constrained due to either the sensor’s limited range or textureless scenes when a camera is used. To address these limitations, this study proposes a cost-effective self-calibration method that simultaneously calibrates the robot arm and deter- mines the spatial relationship between the robot and an RGB-D camera, allowing for data collection at multiple locations. The proposed approach leverages recent advancements in machine learning to identify correspondences between images captured at different robot postures, facilitating automatic data selection. Furthermore, the removal of location constraints increases flex- ibility, enabling the collection of sufficient data as the robot’s location changes. The method is evaluated using a Franka Emika Panda robotic arm, and the experimental results demonstrate its effectiveness in achieving accurate calibration without the need for external devices or markers.