Abstract 3D object detection technology from point clouds has been widely applied in the field of automatic driving in recent years. In practical applications, the shape point clouds of some objects are incomplete due to occlusion or far distance, which means they suffer from insufficient structural information. This greatly affects the detection performance. To address this challenge, the authors design a Structural Information Augment (SIA) Network for 3D object detection, named SIANet. Specifically, the authors design a SIA module to reconstruct the complete shapes of objects within proposals for enhancing their geometric features, which are further fused into the spatial feature of the object for box refinement to predict accurate detection boxes. Besides, the authors construct a novel Unet‐liked Context‐enhanced Transformer backbone network, which stacks Context‐enhanced Transformer modules and an upsampling branch to capture contextual information efficiently and generate high‐quality proposals for the SIA module. Extensive experiments show that the authors’ well‐designed SIANet can effectively improve detection performance, especially surpassing the baseline network by 1.04% mean Average Precision (mAP) gain in the KITTI dataset and 0.75% LEVEL_2 mAP gain in the Waymo dataset.

Small target detection in infrared (IR) images has been widely applied for both military and civilian purposes. In this study, because IR images contain sparse and low-rank features in most scenarios, we propose an optimal IR patch-image (OIPI) model-based detection method to detect small targets in heavily cluttered IR images. First, the OIPI model was generated based on a conventional IR image model using a novel optimal patch size and sliding step adaptive selection algorithm. Secondly, the sparse and low-rank features of IR images were extracted and fused to generate an adaptive weighted parameter. Thirdly, the adaptive inexact augmented Lagrange multiplier (AIALM) algorithm was applied in the OIPI model to solve the robust principal component analysis (RPCA) optimization problem. Finally, an adaptive threshold method is proposed to segment and calibrate targets. Experimental results indicate that the proposed algorithm is capable of detecting small targets more stably and accurately, compared with state-of-the-art methods.

To overcome the drawbacks of conventional methods to detect infrared (IR) small targets, including high false alarm probability and low detection rate, a novel approach to detect IR small targets based on local gradient field feature contrast measure (LGFFCM) is presented in this letter. First, the distinctive characters of the target, background, and clutter in the infrared gradient vector field (IGVF) are investigated. Next, a local contrast measure based on IGVF features was proposed. Then, an adaptive threshold method to obtain coarse detection results is proposed. Finally, a flux across the plane curve in the IGVF, which can eliminate clutter and enhance target, is defined. The experimental results indicate that the proposed approach shows superiority to other advanced approaches and can effectively and stably reduce false alarm probability and enhance detection rate.

This study presents a novel hybrid approach for mobile robot aiming to efficiently plan smooth paths in an unknown dynamic environment. The single robot is treated as a multi-agent system, and the corresponding architecture combined with cooperative control is constructed. Then, a new method of information fusion, i.e. Dezert–Smarandache Theory (DSmT) is introduced to build the map of the unknown dynamic environment. Considering the characteristics of sonar sensors, the grid map method is adopted and a sonar sensor mathematical model is constructed based on DSmT. Meanwhile, a few general basic belief assignment functions are constructed to deal with the uncertain, imprecise and sometimes even highly conflicting information obtained by the sonar. Safety guard district search method and an optimising approach for searched paths are proposed. Also, the parameters of internal proportional-integral-derivative controller in the goto agent are adjusted through practical experiments to smooth the path. Finally, two experiments are carried out with mobile robot: one uses the hybrid method, while the other the artificial potential field. The experimental results testify the validity of hybrid DSm model for fusing imprecise information, and also reveal the validity and superiority of the hybrid method for path planning in unknown dynamic environment.

As we know, the dynamic visual-tracking control, which is based on the depth-independent interaction matrix, has been proposed to cope with the general 3-D motion of robot manipulators. To deal with the unknown camera parameters, an adaptive law has been designed. It is noted, however, that the designed adaptive law uses a vector signal defined by the true depths of feature points, which are unavailable when the camera parameters are unknown. Nevertheless, such an adaptive law can still be implemented by replacing the exact depths with the estimated depths, since the estimated depths can be readily calculated by using the estimated values of the camera parameters. In this case, however, we cannot definitely say whether or not the robot system can be guaranteed to achieve asymptotical stability or even stable behavior. To overcome this problem, in this paper, we redefine the mentioned vector signal using the estimated depths and show that the design based on the new vector signal can make the robot system asymptotically stable. Additionally, the existing tracking control design based on the concept of depth-independent interaction matrix is initial-state dependent. Thus, in this paper, we also modify the existing design to obtain an initial-state-independent result. To show the performance of the proposed designs, simulation results based on a two-link planar manipulator are presented. In addition, preliminary experimental results using an industrial manipulator are also given.

This paper deals with enriched qualitative belief functions for reasoning under uncertainty and for combining information expressed in natural language through linguistic labels. In this work, two possible enrichments (quantitative and/or qualitative) of linguistic labels are considered and operators (addition, multiplication, division, etc) for dealing with them are proposed and explained. We denote them qe-operators, qe standing for “qualitative-enriched” operators. These operators can be seen as a direct extension of the classical qualitative operators (q-operators) proposed recently in the Dezert-Smarandache Theory of plausible and paradoxist reasoning (DSmT). q-operators are also justified in details in this paper. The quantitative enrichment of linguistic label is a numerical supporting degree in [0,∞), while the qualitative enrichment takes its values in a finite ordered set of linguistic values. Quantitative enrichment is less precise than qualitative enrichment, but it is expected more close with what human experts can easily provide when expressing linguistic labels with supporting degrees. Two simple examples are given to show how the fusion of qualitative-enriched belief assignments can be done, and a simulation application is given to show its advantage in rough navigation map building of mobile robot.

We consider in this work evidential sources of information and propose a very general evidence supporting measure of similarity (ESMS) for selecting the most coherent subset of sources to combine among all sources available at each instant. The methodology proposed here coupled with a DSmT-based fusion machine is tested in robotics for the automatic estimation of an unknown simulated environment with obstacles where an autonomous mobile Pioneer II robot with sonar sensors evolves. Our simulation results are based on the fusion of similar and equireliable sensors but same approach can also be used with dissimilar sources as well by using a discounting method taking into account the reliability of each sensor. Our results show clearly the benefit of the selection of the sources as prerequisite for improvement of information fusion

An image Jacobian estimate method for uncalibrated visual servoing is proposed in this paper. With less or no prior knowledge to robotic parameters and filtering statistics, the method employs a Kalman filter to provide an optimal estimate of the Jacobian elements and fuzzy logic controllers to adjust the Kalman noise covariance matrices Q and R adaptively. The adaptations are performed based on a matching technique of the filter residual mean value and covariance error. It greatly improves the Jacobian estimate adaptability to unknown dynamic imaging applications. A microscopic image Jacobian model has been developed for the 4 degree-of-freedom micromanipulator in our microassembly system. Its Jacobian estimate results demonstrate a good performance of the proposed method

A new robust neuro-fuzzy controller for autonomous and intelligent robot manipulators in dynamic and partially known environments containing moving obstacles is presented. The navigation is based on a fuzzy technique for the idea of artificial potential fields (APFs) using analytic harmonic functions. Unlike the fuzzy technique, the development of APFs is computationally intensive. A computationally efficient processing scheme for fuzzy navigation to reasoning about obstacle avoidance using APF is described, namely, the intelligent dynamic motion planning. An integration of a robust controller and a modified Elman neural networks (MENNs) approximation-based computed-torque controller is proposed to deal with unmodeled bounded disturbances and/or unstructured unmodeled dynamics of the robot arm. The MENN weights are tuned online, with no off-line learning phase required. The stability of the overall closed-loop system, composed by the nonlinear robot dynamics and the robust neuro-fuzzy controller, is guaranteed by the Lyapunov theory. The purpose of the robust neuro-fuzzy controller is to generate the commands for the servo-systems of the robot so it may choose its way to its goal autonomously, while reacting in real-time to unexpected events. The proposed scheme has been successfully tested. The controller also demonstrates remarkable performance in adaptation to changes in manipulator dynamics. Sensor-based motion control is an essential feature for dealing with model uncertainties and unexpected obstacles in real-time world systems.

An integration of a fuzzy controller and modified Elman neural networks (NN) approximation-based computed-torque controller is proposed for motion control of autonomous manipulators in dynamic and partially known environments containing moving obstacles. The navigation technique of robot control using artificial potential fields is based on the fuzzy controller. The NN controller can deal with unmodeled bounded disturbances and or unstructured unmodeled dynamics of the robot arm. The NN weights are tuned online, with no off-line learning phase required. The stability of the closed-loop system is guaranteed by the Lyapunov theory. The purpose of the controller, which is designed as a neuro-fuzzy controller, is to generate the commands for the servo-systems of the robot so it may choose its way to its goal autonomously, while reacting in real-time to unexpected events. The proposed scheme has been successfully tested. The controller also demonstrates remarkable performance in adaptation to changes in manipulator dynamics. Sensor-based motion control is an essential feature for dealing with model uncertainties and unexpected obstacles in real-time world systems.