Abstract—This paper presents a biologically-inspired object detection system to facilitate autonomous grasping, based on the Furcated Luminance-Difference Processing (FLDP) concept. It is inspired by the Lobula Giant Movement Detector, a wide-field visual neuron found in the lobula layer of a locust’s nervous system. This computational model effectively addresses key challenges in object detection, such as estimating object proximity and dealing with irregular lighting conditions, without relying on computation-intensive processes. It also excels at detecting edges, regardless of background colour, size, or contour. The proposed system applies a series of image enhancement and edge detection algorithms to estimate the object’s position relative to the gripper. The model’s computational load and performance were tested in various offline and real-time autonomous object grasping scenarios. Results demonstrated the system’s ability to detect objects over 300 mm away approaching at 0.8 ms^-1 and a detection success rate of over 80%, processing at 120 Hz. These findings confirm the system’s feasibility for real-time, real-world applications that require low-computation, fail-safe object detection.
 
Keywords—autonomous robotic manipulation, bioinspired object detection, luminance-difference processing, direction and proximity estimation


Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).