Manipulator-based Active Exploration Strategy for Unexplored Areas Utilizing 3D-2D Spherical Projection

The rapid aging of the agricultural workforce and the continued shrinkage of the rural population have heightened the need for affordable autonomous robotic solutions in agriculture. Visual simultaneous and localization mapping systems are widely used for environmental perception and localization, but their narrow field of view (FOV) limits their ability to map complex agricultural environments comprehensively. While multi-camera systems can address FOV limitations, their high costs and increased computational demands make them impractical for cost-sensitive applications. Herein, a low-cost and efficient methodology that employs active exploration using a robotic manipulator has been proposed to address these challenges This unique approach reduces computational complexity while retaining essential environmental details by converting 3D point cloud data into 2D depth images through spherical projection. Such a transformation allows the system to effectively identify unexplored regions within the depth images, guiding the manipulator to explore these areas autonomously. As a result, this method enables comprehensive environmental mapping with minimal sensor requirements, offering a practical solution for agricultural automation.