ARC-Calib: Autonomous Markerless Camera-to-Robot Calibration via Exploratory Robot Motions

2025-03-18

AI Summary

Traditional camera-to-robot hand-eye calibration relies on人工 markers or pre-trained tracking models, hindering edge deployment and limiting generalizability. ARC-Calib introduces the first purely model-driven, fully autonomous, markerless calibration framework: a robot autonomously generates exploratory motions to produce trackable visual trajectories; geometric constraints—derived from coplanarity and collinearity priors—are formulated and solved via direct geometric optimization to estimate extrinsic parameters. The method requires no manual markers, pre-trained models, additional data collection, or platform-specific fine-tuning, enabling zero-shot cross-robot generalization. Evaluated in simulation and on real robotic arms, it achieves rotation errors <1.2° and translation errors <1.8 mm, satisfying real-time execution requirements on edge devices.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Camera-to-robot (also known as eye-to-hand) calibration is a critical component of vision-based robot manipulation. Traditional marker-based methods often require human intervention for system setup. Furthermore, existing autonomous markerless calibration methods typically rely on pre-trained robot tracking models that impede their application on edge devices and require fine-tuning for novel robot embodiments. To address these limitations, this paper proposes a model-based markerless camera-to-robot calibration framework, ARC-Calib, that is fully autonomous and generalizable across diverse robots and scenarios without requiring extensive data collection or learning. First, exploratory robot motions are introduced to generate easily trackable trajectory-based visual patterns in the camera's image frames. Then, a geometric optimization framework is proposed to exploit the coplanarity and collinearity constraints from the observed motions to iteratively refine the estimated calibration result. Our approach eliminates the need for extra effort in either environmental marker setup or data collection and model training, rendering it highly adaptable across a wide range of real-world autonomous systems. Extensive experiments are conducted in both simulation and the real world to validate its robustness and generalizability.

Problem

• Autonomous camera-to-robot calibration without markers
• Eliminates need for pre-trained robot tracking models
• Generalizable across diverse robots and scenarios

Innovation

• Autonomous markerless calibration via exploratory robot motions
• Geometric optimization using coplanarity and collinearity constraints
• No need for markers, data collection, or model training