Monocular depth estimation technology has emerged as a critical component across a variety of outdoor applications like robotics, augmented reality, autonomous driving, and 3D reconstruction. Mainstream monocular depth estimation methods consistently face challenges in applications requiring real-time performances, as they exhibit considerable computational complexity, resulting in poor runtime performance. Here, we propose an innovative processing module named MDE-Lite. Based on that, we develop a lightweight yet effective depth estimation network named MBUDepthNet. Besides, we build a training scheme with multiple loss functions. Experimental validation on KITTI dataset demonstrates that our method not only rivals mainstream methods in terms of accuracy but also exhibits superior computational efficiency. Compared to the method using ResNet-18, our method achieves a 22% higher frame rate in terms of frames per second.
In response to the demand for small-size, high-precision, and real-time target distance measurement in platforms such as autonomous vehicles and drones, this paper investigates the multi-focal bionic compound eye (MFBCE) and its associated distance measurement algorithm. MFBCE was designed to integrate multiple lenses with different focal lengths and a CMOS array. Based on this system, a multi-eye distance measurement algorithm based on target detection was proposed. The algorithm derives the application of binocular distance measurement on cameras with different focal lengths, overcoming the limitation of traditional binocular algorithms that only work with identical cameras. By utilizing the multi-scale information obtained from multiple lenses with different focal lengths, the ranging accuracy of the MFBCE is improved. The telephoto lenses, with their narrow field of view, are beneficial for capturing detailed target information, while wide-angle lenses, with their larger field of view, are useful for acquiring information about the target’s environment. Experiments using the least squares method for ranging targets at 100 cm yielded a mean absolute error (MAE) of 1.05, approximately one-half of the binocular distance measurement algorithm. The proposed MFBCE demonstrates significant potential for applications in near-range obstacle avoidance, robotic grasping, and assisted driving.
Aiming at the shortcomings of the current automatic fruit sorting mechanism, based on the system architecture of the fruit automatic sorting robot, a fruit automatic sorting robot combining time delay estimation and smooth sliding mode impedance control method is proposed. The gripping mechanism control method uses the deviation between the expected gripping force and the actual contact gripping force as the input of the outer ring force impedance controller, the controller generates the correction amount for the reference trajectory of the inner ring position, and realizes the gripping force control through the position control.. This control method is easy to implement, but its control performance is directly related to the position control performance. The methods applicable to the position control of the clamping mechanism mainly include kinematic control and dynamic control. Compared with the kinematic control, the control based on the dynamic model considers the influence of the dynamic characteristics of the mechanism on the control performance, and its dynamic factors can be compensated by the controller, and theoretically, better control performance can be obtained. Focus on the research on the dynamics control of the clamping mechanism of the parallel robot.