This paper proposes a secondary reactive collision avoidance system for microclass of robots based on a novel approach known as the furcated luminance-difference processing (FLDP) inspired by the lobula giant movement detector, a wide-field visual neuron located in the lobula layer of a locust nervous system. This paper addresses some of the major collision avoidance challenges: obstacle proximity and direction estimation, and operation in GPS-denied environment with irregular lighting. Additionally, it has proven effective in detecting edges independent of background color, size, and contour. The FLDP executes a series of image enhancement and edge detection algorithms to estimate collision threat-level which further determines whether the robot’s field of view must be dissected where each section’s response is compared against the others to generate a simple collision-free maneuver. Ultimately, the computation load and the performance of the model are assessed against an eclectic set of offline as well as real-time real-world collision scenarios validating the proposed model’s asserted capability to avoid obstacles at more than 670 mm prior to collision, moving at 1.2 ms−1 with a successful avoidance rate of 90% processing at 120 Hz on a simple single-core microcontroller, sufficient to conclude the system’s feasibility for real-time real-world applications that possess fail-safe collision avoidance system.

中文翻译：

---

一种用于自主微型机器人的分叉视觉防撞系统

本文提出了一种用于微类机器人的二次反应性碰撞避免系统，该系统基于一种称为分叉亮度差处理 (FLDP) 的新方法，其灵感来自小叶巨型运动检测器，这是一种位于小叶层的宽视野视觉神经元。蝗虫神经系统。本文解决了一些主要的防撞挑战：障碍物接近度和方向估计，以及在不规则照明的 GPS 拒绝环境中的操作。此外，它已被证明可以有效地检测与背景颜色、大小和轮廓无关的边缘。FLDP 执行一系列图像增强和边缘检测算法来估计碰撞威胁级别，这进一步确定是否必须解剖机器人的视野，其中每个部分的响应与其他部分的响应进行比较以生成简单的无碰撞机动。最终，模型的计算负载和性能根据一组折衷的离线和实时真实世界碰撞场景进行评估，验证了所提出的模型在碰撞前避开超过 670 毫米的障碍物的断言能力，在1.2 ms-1 在简单的单核微控制器上以 120 Hz 的频率处理 90% 的成功避免率，足以得出系统在具有故障安全防撞系统的实时实际应用中的可行性。