Extracting overlapping regions is crucial for point cloud registration. Recently, coarse-to-fine approaches have gained popularity. These methods rely on highly accurate superpoint correspondences, which are then propagated to denser points. However, these correspondences inevitably introduce non-overlapping region superpoints, leading to a decrease in superpoint matching accuracy. To tackle this challenge, we introduce the Overlapping Region Estimation-Based (ORE-Based) Point Cloud Registration method, a novel approach designed to enhance matching accuracy by reducing the influence of non-overlapping points. Our method utilizes a learning model to predict whether each superpoint is situated within overlapping regions. By excluding superpoints outside these regions during correspondence extraction, we achieve improved matching accuracy. This approach ensures high registration precision regardless of the overlap ratio between the point clouds being registered. By specifically targeting overlapping regions, our method significantly enhances the robustness and reliability of point cloud registration across diverse scenarios. Although simple, our approach achieves state-of-the-art performance on the challenging ModelLoNet benchmark, reducing Relative Rotation Error by 12.87 % and Relative Translation Error by 14.47 % under conditions of larger initial rotation error.

Designing a safe and effective collision avoidance policy for multiple robots is essential in decentralized scenarios, where each robot is responsible for generating its own paths, to ensure their safe operation. Recently, the utilization of reinforcement learning to develop decentralized policies that enable multiple robots to move cooperatively and accomplish tasks has yielded positive outcomes. However, the presence of exploration unsafe actions during the reinforcement learning training process results in inadequate safety. We seek to enhance the safety of distributed multi-robot navigation policies and propose a new imitation learning framework based on the variational Bayesian model, which enables robots to learn safe actions by anticipating the subsequent state they are expected to reach. In addition, a new policy neural network structure for multi-robot navigation is proposed by introducing the transformer structure, which encodes the significance of nearby robots in relation to their forthcoming conditions. Experiments demonstrated that our policy can more safely guide robots to navigate in multi-robot environments under conditions of limited information, outperforming the state-of-the-art RL-RVO method in terms of success rate. Note to Practitioners —The motivation of this paper is to address the problem of collision avoidance in a multi-robot environment under limited information, which can also be applied to autonomous driving, crowd simulation, and other related fields. Positive outcomes have been observed in the utilization of reinforcement learning to create decentralized policies that enable multiple robots to move cooperatively and complete tasks. However, inadequate safety remains a challenging task due to the possibility of exploring hazardous actions during training. This article aims to enhance the safety of distributed policies guiding robots to accomplish navigation tasks in dynamic multi-robot environments. To begin with, we introduce a novel framework for imitation learning that is based on the variational Bayesian model. This framework facilitates the learning of safe actions by the policy to improve its performance and guide the robot in navigating and avoiding obstacles more securely. A loss function is proposed that enables the anticipation of the future state expected to be reached by the robot. By incorporating the transformer structure, a new neural network structure is designed for multi-robot navigation that encodes the significance of nearby robots concerning their upcoming conditions. This network structure employs a BiGRUs to facilitate the assimilation of observations from multiple agents by the policy. Compared to existing works such as GA3C-CADRL, SARL, and RL-RVO, our proposed method achieves a higher success rate. In our future research, we will investigate methods to enhance the policy’s performance in guiding robots to complete tasks by focusing on improving travel time and average speed, while also strictly ensuring safe navigation. Furthermore, we plan to extend this approach by addressing navigation challenges in more densely populated multi-robot environments.

Homography estimation is a common image alignment method. Unsupervised learning, which uses unlabeled training and exhibits excellent performance, has attracted much attention in this field. When there are multiple planes in the scene, using features over the entire image for matching will lead to compromised results. However, existing methods for learning focused principal plane masks through deep neural networks lack explicit guidance. In this paper, we propose a novel unsupervised method to explicitly model anomaly descriptor removal and mask generation. Specifically, reliable feature descriptors are selected from a novel perspective, and regard the features that are not responsible for alignment as outliers. The pixel-level support vector data description (PL-SVDD) module is designed. This module learns the feature representation of image pixels and fits a hypersphere to exclude the feature redundancy information that is not responsible for alignment from the hypersphere, thereby optimizing the feature descriptor. Based on the optimized image features, a correlation learning (CL) module is designed. This module displays a generated mask through mathematical modeling to select reliable areas for homography estimation. Specifically, the feature descriptor of one unaligned images is modeled as a multivariate Gaussian distribution by Gaussian density estimation (GDE). Then, The Mahalanobis distance is combined with the multivariate Gaussian distribution of the model and the feature descriptor of another image to generate the mask. Experiments show that our method achieves good performance compared with previous methods.

Navigating robots through dynamic multi-robot environments, avoiding collisions with both other robots and obstacles, has emerged as a central challenge in robotics. The existing approaches fall short in allowing the policy network to effectively capture spatial-temporal reciprocal collision avoidance in multi-robot environments, comprising both static and dynamic obstacles, resulting in inadequate safety and efficiency in directing robot movement. In this study, we introduce a novel policy neural network called Spatial-Temporal RetNet (STR), designed to encode reciprocal collision avoidance states between robots in spatial and temporal dimensions. The goal is to improve the safety and efficacy of the policy neural network in directing robots to complete assigned tasks. The spatial state encoder module is built upon a parallel RetNet structure, which strengthens the neural network's capacity in extracting reciprocal collision avoidance states between robots in spatial dimensions. This module addresses the limitations of position encoding in transformer-based multi-robot navigation policy neural networks. We design a temporal state encoder utilizing a recurrent RetNet structure. This innovation bolsters the multi-robot navigation policy neural network's capability to capture features in the temporal dimension of multi-robot movements. It addresses the limitations of transformer-based multi-robot navigation policy neural networks, particularly in recurrently inferring information across time dimensions. Simulation experiments were conducted to showcase the superior safety and effectiveness of our proposed method compared to previous state-of-the-art approaches in guiding robots to accomplish tasks.

Generalizing visual reinforcement learning is fundamental to robot visual navigation, involving the acquisition of a policy from interactions with source environments to facilitate adaptation to analogous, yet unfamiliar target environments. Recent advancements capitalize on data augmentation techniques, self-supervised learning methods, and the generative adversarial network framework to train policy neural networks with enhanced generalizability. However, current methods, upon extracting domain-general latent features, further utilize these features to train the reinforcement learning policy, resulting in a decline in the performance of the learned policy guiding the agent to accomplish tasks. To tackle these challenges, a framework of self-expert imitation with purifying latent features was devised, empowering the policy to achieve robust and stable zero-shot generalization performance in visually similar domains previously unseen, without diminishing the performance of guiding the agent to accomplish tasks. The extraction method of domain-general latent features is proposed to enhance their quality based on the variational autoencoder. Extensive experiments have shown that our policy, compared with state-of-the-art counterparts, does not diminish the performance of the policy guiding the agent to accomplish tasks after generalization.

The core of multirobot collision avoidance lies in developing a decentralized policy that can guide robots from their initial positions to target locations based on the environment states perceived by the robots and ensure collision avoidance. However, the current multirobot collision avoidance policy network is challenging to simultaneously extract the global spatial state, temporal state, and reciprocity among robots, which limits its performance. In this work, we have developed a novel reciprocal velocity obstacle (RVO) spatial-temporal network and employed the proximal policy optimization algorithm to train the network parameters during interactions with amultirobot simulation environment. Specifically, a temporal state encoder module, utilized to represent the temporal characteristics of observation sequence data, is designed and achieved through the combination of the graph attention mechanism and the transformer encoding module. Furthermore, we design a reciprocal spatial state encoder module achieved through the use of a transformer encoding module to merge feature data from long short-term memory (LSTM), GRU, and bidirectional gated recurrent units (BiGRUs) branches, serving the purpose of representing spatial characteristics in RVO sequence data. Extensive simulation experiments demonstrate that our proposed method outperforms the state-of-the-art distributed policy reinforcement learning (RL)-RVO. We further conducted physical experiments using three Crazyflie quadcopter drones, illustrating its ability to effectively guide agents’ movements and avoid collisions.

Homography estimation has widespread applications in visual computing and image analysis. Current state-of-the-art Transformer-based image matching methods require computing all possible key-value combinations to obtain global information, resulting in high computational costs and slow inference speeds. This paper presents an enhanced Transformer-based approach for image matching, integrating a spatial decay matrix derived from Manhattan distance and leveraging attention decomposition. We introduce Manhattan Self-Attention (MaSA) to enhance the LoFTR framework. This approach maintains the integrity of the spatial decay matrix while reducing the computational burden of modeling global information. Through the incorporation of a spatial decay matrix and attention decomposition, explicit spatial priors can be seamlessly integrated into the visual backbone network, enabling the achievement of linear computational complexity. Thus, it improves decoding throughput, latency, and GPU memory usage without sacrificing performance. Experimental evaluations indicate that the proposed method substantially enhances matching accuracy while effectively reducing inference time and memory overhead, outperforming state-of-the-art approaches under consistent evaluation metrics.

Trajectory tracking is a basic problem in quadrotor control. To achieve a better control effect, MPC is introduced in the control of quadrotors. In this paper, we introduce the error-state dynamic model of a quadrotor firstly. Then, we develop an MPC method via the Lie group of special euclidean group based on the error-state dynamic model of a quadrotor. The proposed method is established on a manifold, thus the smoothness of the quadrotor trackjectory can be guaranteed. Our scheme is developed in error-state, which means that we take the velocity of the target trajectory into consideration for the dynamic model building. Therefore the cost function of our proposed approach is convex while the traditional MPC method is not when tracking a nonlinear trajectory. At the end of this paper, we compare our proposed MPC method with the traditional MPC method in one hundred sets of simulations. In our proposed method, the errors of position and orientation converge faster than the errors in the traditional method. The simulation results show that our proposed method is superior to traditional MPC scheme while tracking a nonlinear trajectory with a random initial position and verity the correctness of our MPC method.

Multiagent path finding (MAPF) is employed to find collision-free paths to guide agents traveling from an initial to a target position. The advanced decentralized approach utilizes communication between agents to improve their performance in environments with high-density obstacles. However, it dramatically reduces the robustness of multiagent systems. To overcome this difficulty, we propose a novel method for solving MAPF problems. In this method, expert data are transformed into supervised signals by proposing a hot supervised contrastive loss, which is combined with reinforcement learning to teach fully-decentralized policies. Agents reactively plan paths online in a partially observable world while exhibiting implicit coordination without communication with others. We introduce the self-attention mechanism in the policy network, which improves the ability of the policy network to extract collaborative information between agents from the observation data. By designing simulation experiments, we demonstrate that the learned policy achieved good performance without communication between agents. Furthermore, real-world application experiments demonstrate the effectiveness of our method in practical applications.

As the drone captures image targets at different flying altitudes, their scales may vary significantly, which can pose challenges for the object detection model to accurately detect them. Additionally, tiny objects in the image contain minimal information, making them difficult to distinguish from the background. To overcome these two challenges, we proposed a network architecture that aims to improve the accuracy of tiny object detection in drone images. Specially, we designed a tiny object detector(TOD) that can effectively extract features of tiny objects and distinguish between tiny object features and image background. Furthermore, this TOD module contains a Convolutional Visual Attention Network (CVAN) to better focus on the regions of tiny objects. Experimental results demonstrate that the proposed method achieves mAP@.5 accuracy of 53.9% on the VisDrone2021-test-dev dataset and improves by 2.8 % compared to YOLOv7.

Homography estimation is a crucial problem in computer vision, which aims to provide an optimal transformation matrix for aligning images captured from different viewpoints. Current methods extract shallow features from image pairs and introduce learnable mask modules to improve homography estimation performance. However, they struggle to capture long-term dependencies between features and comprehend the global structures of image features. A deep unsupervised homography learning framework is proposed in this paper, consisting of a weight-sharing feature extraction network and a homography estimation network based on the Transformer model. The former extracts the local features of images, while the latter learns the correlation between them and understands the global features of images, enabling the algorithm to better estimate the homography of unaligned images. Experimental results demonstrate that the proposed method outperforms the advanced methods for estimating homography matrices in the CA-Unsupervised dataset.

Multirobot path planning leads multiple robots from start positions to designated goal positions by generating efficient and collision-free paths. Multirobot systems realize coordination solutions and decentralized path planning, which is essential for large-scale systems. The state-of-the-art decentralized methods utilize imitation learning and reinforcement learning methods to teach fully decentralized policies, dramatically improving their performance. However, these methods cannot enable robots to perform tasks efficiently in relatively dense environments without communication between robots. We introduce the transformer structure into policy neural networks for the first time, dramatically enhancing the ability of policy neural networks to extract features that facilitate collaboration between robots. It mainly focuses on improving the performance of policies in relatively dense multirobot environments under conditions where robots do not communicate with each other. Furthermore, a novel imitation reinforcement learning framework is proposed by combining contrastive learning and double deep Q-network to solve the problem of difficulty training policy neural networks after introducing the transformer structure. We present results in the simulation environment and compare the resulting policy against advanced multirobot path-planning methods in terms of success rate. Simulation results show that our policy achieves state-of-the-art performance when there is no communication between robots. Finally, we experimented with a real-world case using a total of three robots in our robotic laboratory.

Multi-Agent Path Finding is a problem of finding the optimal set of paths for multiple agents from the starting position to the goal without conflict, which is essential to large-scale robotic systems. Imitation and reinforcement learning are applied to solve the MAPF problem and have achieved certain results, which provides a feasible solution for the path planning problem of large-scale robot systems. The current method improves the performance of distributed strategy-guided agent planning paths in complex environments by introducing the communication between graph neural networks and agents but dramatically reduces the system's robustness. This paper develops a novel imitation reinforcement learning framework by introducing Transformer, which enables algorithms to perform well in complex environments without relying on communication between agents. Compared with its counterparts, experiments show that the policy trained by our method guides the agent to drive from the initial position to the goal without collision and achieve better performance.

Due to the limitation of the fixed structures of neighborhood windows, the quality of spatial information obtained from the neighborhood pixels may be affected by noise. In order to compensate this drawback, a robust fuzzy c-means clustering with non-neighborhood spatial information (FCM_NNS) is presented. Through incorporating non-neighborhood spatial information, the robustness performance of the proposed FCM_NNS with respect to the noise can be significantly improved. The results indicate that FCM_NNS is very effective and robust to noisy aliasing images. Moreover, the comparison of other seven roughness indexes indicates that the proposed FCM_NNS-based F index can characterize the aliasing degree in the surface images and is highly correlated with surface roughness (R-2 = 0.9327 for thirty grinding samples).