Occlusion Avoidance for Robotic Manipulators Using Rigid Gaussian Splatting

Abstract

Abstract Monitoring robotic manipulators is essential in highly automated environments, where optical cameras can provide precise and dense information while suffering from line-of-sight occlusions. This paper introduces a lightweight, learning-based solution to address these occlusions in robot-camera systems. We employ a small MLP (Multilayer Perceptron) to learn occluded spaces and use its gradients for active occlusion avoidance. To generate training data, we use smooth random robot trajectories that uniformly sample the robot’s configuration space. Additionally, we reduce data acquisition time by modifying the state-of-the-art 3D Gaussian Splatting (3DGS) method to create a near-photorealistic model of the manipulator for generating extensive training datasets. Our experiments show that the proposed approach achieves a balanced accuracy of 94.7 %, which improves upon a previous method by 20 % while reducing the sampling time from 4.5 h to 5 min. We demonstrate the application of the proposed method in two real-world test cases and achieve continuous visibility. Through the use of rigid 3DGS, we significantly improved upon previous results. By reducing the data sampling duration from hours to minutes, the practicality and applicability of our approach in real-world scenarios have been substantially enhanced.