3D Object Reconstruction Using Quadruped Robots with Fisheye Cameras and Neural Radiance Fields

Legged robots can navigate through narrow spaces with obstacles on the ground, making them ideal for indoor rescue tasks. In such scenarios, high-quality 3D reconstruction of suspicious items helps in decision-making with humans in the loop. For 3D reconstruction with binoc-ular fisheye cameras on a quadruped robot, we developed a pipeline with strategies for scanning an object on the ground and integrated it with a neural-radiance-fields-based approach for fast, realistic rendering. The pipeline allows the robot to maintain an optimal distance from an object specified by a user, capture images from multiple angles for comprehensive views, and reconstruct and render the object on a control-end server.