Operating in inherently dynamic and unstructured environments, mobile robots must routinely navigate substantial uncertainties—particularly in crowded spaces or multi-door configurations. Yet mainstream navigation approaches often disregard such environmental unpredictability and underutilize historical task experience, leading to recurrent obstacle blockages that degrade both efficiency and safety. This work proposes an adaptive navigation method for uncertain environments using probabilistic topological mapping (PTM). We develop a Gaussian mixture model (GMM)-based PTM construction approach that extracts environmental feature nodes through path similarity and node density filtering, clusters nodes via GMM, and establishes topological connections to efficiently encode environmental characteristics. For adaptive navigation, we introduce: 1) a posterior heuristic algorithm for planning under uncertainty; 2) a topological edge analysis with re-planning and escape mechanisms for robustness; and 3) a dynamic particle filter for online probability updates. This framework enables robots to autonomously analyze environmental information and progressively optimize navigation strategies through probabilistic self-updating. Simulations and real-world experimental studies reveal that our method exhibits higher efficiency and safety compared to current mainstream navigation approaches.

To address the challenges posed by periodic gait-induced disturbances in legged robotic systems, we propose an enhanced visual SLAM framework that systematically incorporates gait-phase awareness into the mapping optimization process. Building upon the ORB-SLAM2 architecture, our methodology introduces two principal innovations: 1) a gait-synchronized pose prediction model that dynamically adjusts motion estimation parameters according to cyclic locomotion patterns and 2) an adaptive keyframe selection strategy that optimizes temporal sampling based on phase-dependent stability characteristics. By integrating real-time gait-phase detection with visual-inertial data fusion, our system demonstrates improved robustness against transient sensor perturbations and high-frequency vibrations inherent in dynamic locomotion. Quantitative evaluations reveal that this gait-adaptive optimization framework achieves superior tracking performance compared with conventional SLAM implementations, with lower absolute trajectory error, higher loop closure detection accuracy, and enhanced mapping consistency with less drift and overlap. The proposed architecture effectively decouples locomotion-induced sensor noise from true environmental observations, maintaining relatively high tracking precision even under severe gait disturbances (peak acceleration > 13m/s2). This advancement enables reliable long-term autonomous operation in unstructured environments where traditional vision-based SLAM systems typically suffer from error accumulation and mapping degradation.

Robotic endoluminal surgery has gained tremendous attention for its enhanced treatments in gastrointestinal intervention, where navigating surgeons with monocular camera-based metric depth estimation is a vital sector. However, existing methods either rely on external sensors or perform poorly in terms of visual navigation. In this work, we present our M$^{3}$-Degrees Net, a novel monocular vision-guided and graph learning-based network tailored for accurate metric marching depth (MD) estimation. We first leverage a generative model to output a scale-free depth map, providing a depth basis in a coarse granularity. To achieve an optimized and metric MD prediction, a relational graph convolutional network with multi-modal visual knowledge fusion is devised. It utilizes shared salient features between keyframes and encodes their pixel differences on the depth basis as the main node, while a projection length-based node that predicts the MD on a proportional relationship basis is introduced, aiming to enable the network with explicit depth awareness. Moreover, to compensate for rotation-induced MD estimation bias, we model the endoscope's orientation changes as image-level feature shifts, formulating an ego-motion correction node for MD optimization. Lastly, a multi-layer regression network for the metric MD estimation with finer granularity is devised. We validate our network on both public and in-house datasets, and the quantitative results reveal that it can limit the overall MD error under 27.3%, which vastly outperforms the existing methods. Besides, our M$^{3}$-Degrees Net is qualitatively tested on the in-house clinical gastrointestinal endoscopy data, demonstrating its satisfactory performance even under cavity mucus with varying reflections, indicating promising clinical potentials.

This paper focuses on developing modern, efficient, lightweight object detection a method for sweeping robots while trading off parameters, FLOPs and performance. In order to comply with the real-time requirements of sweeping robots, a method combining layer pruning and channel pruning is used to compress the initial model before optimization. First, a C2f module based on shunt gradient is introduced to lighten the network. Second, a$\mathrm{C}3_{-}\mathbf{DCN}$(Deformable convolutional networks) module is used to fit the shape and size of the object when sam-pling. Finally, a Convolutional Block Attention Module(CBAM) is added behind the backbone network to enhance the extraction of important features. In the experimental studies, we compare our method with state-of-the-art methods, and the results reveal that the new model accuracy can reach 88.5 % with only 2.27M parameters and 5.5G FLOPs. Furthermore, the experiment results show that our proposed method achieves a better balance between model size and accuracy.

Monocular depth estimation has been actively studied in fields such as robot vision, autonomous driving, and 3D scene understanding. Given a sequence of color images, unsupervised learning methods based on the framework of Structure-From-Motion (SfM) simultaneously predict depth and camera relative pose. However, dynamically moving objects in the scene violate the static world assumption, resulting in inaccurate depths of dynamic objects. In this work, we propose a new method to address such dynamic object movements through monocular 3D object detection. Specifically, we first detect 3D objects in the images and build the per-pixel correspondence of the dynamic pixels with the detected object pose while leaving the static pixels corresponding to the rigid background to be modeled with camera motion. In this way, the depth of every pixel can be learned via a meaningful geometry model. Besides, objects are detected as cuboids with absolute scale, which is used to eliminate the scale ambiguity problem inherent in monocular vision. Experiments on the KITTI depth dataset show that our method achieves State-of-The-Art performance for depth estimation. Furthermore, joint training of depth, camera motion and object pose also improves monocular 3D object detection performance. To the best of our knowledge, this is the first work that allows a monocular 3D object detection network to be fine-tuned in a self-supervised manner.

In this article, based on the rapidly-exploring random tree (RRT), we propose a novel and efficient motion planning algorithm using bidirectional RRT search. First, a RRT extend function is used to organize the sampled states under kinodynamic constraints. Meanwhile, the bidirectional search strategy is implemented to grow a forward tree and backward tree simultaneously in the tree extension process. When these two trees meet each other, the backward tree will act as a heuristic to guide the forward tree to continuously grow toward the goal state, where the algorithm switches to unidirectional search mode. Therefore, the two-point boundary value problem (BVP) in the connection process is avoided, and the extension process gets much accelerated. We also prove that probabilistic completeness is guaranteed. Numerical simulations are conducted to demonstrate that the proposed algorithm performs much better than the state-of-the-art algorithms in different environments.Note to Practitioners—The motivation of this work is to develop an efficient sampling-based motion planning algorithm for mobile robots. Conventional sampling-based algorithms are time-consuming to find a feasible solution under differential constraints. When applying bidirectional search strategy to improve them, the complex 2-point BVP is required to solve. In this article, the backward free is regarded as a heuristic to guide the tree growth. On the one hand, the advantage of bidirectional search is retained. On the other hand, the 2-point BVP is avoided. Therefore, the bidirectional-unidirectional technique can achieve efficient robot motion planning. The proposed algorithm can be extended to other specified sampling-based algorithms to further improve their performance. Besides, it can be also applied to autonomous driving, service robot and medical robots to achieve efficient motion planning.

The sampling-based partial motion planning algorithm has come into widespread application in dynamic mobile robot navigation due to its low calculation costs and excellent performance in avoiding obstacles. However, when confronted with complicated scenarios, the motion planning algorithms are easily caught in traps. In order to solve this problem, this paper proposes a knowledge-based fast motion planning algorithm based on Risk-RRT, which guides motion planning by constructing a topological feature tree and generating a heuristic path from the tree. Firstly, an online topological feature learning method is proposed to simultaneously extract the features during the motion of the robot by means of the dual-channel scale filter and the secondary distance fusion. The learning process is completed until the feature points can represent arbitrary obstacle-free grid points of the whole map. Secondly, the topological feature tree is constructed with environmental feature points and the heuristic motion planning can be carried out on the feature tree. For one map, once the construction of the feature tree finishes, it can be reused as a prior knowledge in the following heuristic motion planning process, which will further improve the efficiency of searching feasible paths. The experimental results demonstrate that our proposed method can remarkably reduce the time taken to find a heuristic path and enhance the success rate of navigation in trapped environments.

In this article, a novel informative path planning (IPP) framework is proposed for efficient robotic object search. We innovatively reformulate the object search into an IPP problem, which takes account of the knowledge of possible target object locations. To model the target object distribution knowledge, the semantic information of the focused environment is utilized to obtain the probabilities of finding the target object at possible locations. Then, the probability distribution is modeled by Gaussian mixture model (GMM) to generate an information map. Based on the map, a sampling-based IPP method is proposed to minimize the object search cost. It is worth noting that the object search path is planned with a tree structure and evaluated by a utility function that concerns both search information gain and path cost. Moreover, to improve the quality of the search path, a novel informative sampling strategy and a rewire mechanism are conceived. The performance of the proposed object search framework is fully evaluated through both simulation experiments and real-world tests with a mobile robot platform. Results demonstrated that our method can find the target object efficiently and robustly with shorter path length than three comparative methods in the literature and the mobile robot shows human-like behavior when searching for the target object.

Rapidly random-exploring tree (RRT) and its variants are very popular due to their ability to quickly and efficiently explore the state space. However, they suffer sensitivity to the initial solution and slow convergence to the optimal solution, which means that they consume a lot of memory and time to find the optimal path. It is critical to quickly find a short path in many applications such as the autonomous vehicle with limited power/fuel. To overcome these limitations, we propose a novel optimal path planning algorithm based on the convolutional neural network (CNN), namely the neural RRT* (NRRT*). The NRRT* utilizes a nonuniform sampling distribution generated from a CNN model. The model is trained using quantities of successful path planning cases. In this article, we use the A* algorithm to generate the training data set consisting of the map information and the optimal path. For a given task, the proposed CNN model can predict the probability distribution of the optimal path on the map, which is used to guide the sampling process. The time cost and memory usage of the planned path are selected as the metric to demonstrate the effectiveness and efficiency of the NRRT*. The simulation results reveal that the NRRT* can achieve convincing performance compared with the state-of-the-art path planning algorithms. Note to Practitioners-The motivation of this article stems from the need to develop a fast and efficient path planning algorithm for practical applications such as autonomous driving, warehouse robot, and countless others. Sampling-based algorithms are widely used in these areas due to their good scalability and high efficiency. However, the quality of the initial path is not guaranteed and it takes much time to converge to the optimal path. To quickly obtain a high-quality initial path and accelerate the convergence speed, we propose the NRRT*. It utilizes a nonuniform sampling distribution and achieves better performance. The NRRT* can be also applied to other sampling-based algorithms for improved results in different applications.

In a human-robot coexisting environment, reaching the target place efficiently and safely is pivotal for a mobile service robot. In this paper, a Risk-based Dual-Tree Rapidly exploring Random Tree (Risk-DTRRT) algorithm is proposed for the robot motion planning in a dynamic environment, which provides a homotopy optimal trajectory on the basis of a heuristic trajectory. A dual-tree framework consisting of an RRT tree and a rewired tree is proposed for the trajectory searching. The RRT tree is a time-based tree, considering the future trajectory predictions of the pedestrians, and this tree is utilized to generate a heuristic trajectory. However, the heuristic trajectory is usually nonoptimal. Then, a line-of-sight (LoS) control checking algorithm is proposed to detect whether two time-based nodes can be rewired with the least cost. On the basis of the LoS control checking algorithm, a tree rewiring algorithm is proposed to optimize the heuristic trajectory. The tree generated in the tree rewiring process is called the rewired tree. The trajectory generated by the Risk-DTRRT algorithm proves to be optimal in the homotopy class of the heuristic trajectory. The navigation run time and the lengths of the planned trajectories are selected to demonstrate the effectiveness of the proposed algorithm. The experimental results in both simulation studies and real-world implementations reveal that our proposed method achieves convincing performance in both static and dynamic environments. Note to Practitioners-This paper is motivated by planning optimized trajectories for the mobile service robots in dynamic environments with pedestrians. In this area, the sampling-based motion planning algorithms have been widely used for their high efficiency and robustness. However, the real-time optimality of the motion planning cannot be guaranteed due to the challenges caused by the moving pedestrians. In this paper, we propose a dual-tree framework to solve this problem. First, a classic Rapidly exploring Random Tree (RRT) is constructed to generate a heuristic trajectory. Then, instead of reconnecting the nodes on the heuristic trajectory directly, a rewired tree is built to optimize the heuristic trajectory. This proposed dual-tree framework can fully exploit the information of the RRT tree and ensure the completeness of the motion planning. The proposed motion planning algorithm also considers the constraints of the nonholonomic mobile robots, and it can be applied in most mobile service robots to improve their motion planning quality.

In this paper, we propose a novel path planning framework for autonomous exploration in unknown environments using a mobile robot. A graph structure is incrementally constructed along with the exploration process. The structure is the road map that represents the topology of the explored environment. To construct the road map, we design a sampling strategy to get random points in the explored environment uniformly. A global path from the current location of the robot to the target area can be found on this road map efficiently. We utilize a lazy collision checking method that only checks the feasibility of the generated global path to improve the planning efficiency. The feasible global path is further optimized with our proposed trajectory optimization method considering the motion constraints of the robot. This mechanism can facilitate the path cost evaluation for the next best view selection. In order to select the next best target region, we propose a utility function that takes into account both the path cost and the information gain of a candidate target region. Moreover, we present a target reselection mechanism to evaluate the target region and reduce the extra path cost. The efficiency and effectiveness of our approach are demonstrated using a mobile robot in both simulation and real experimental studies.

In this paper, we propose a gait recognition method for service robots to conduct human following tasks. A walking sequence segmentation method is designed to extract the consecutive gait cycles from an arbitrary walking sequence. Based on the segmentation results, a novel hybrid gait feature is proposed to capture the static, dynamic, and trajectory features for each segmented key and supplementary gait cycles. A dataset of 25 human subjects is collected to evaluate the proposed method in three different walking paths with various walking directions. Experimental results show that the proposed method achieves satisfactory performance in terms of identification accuracy and Fcomb indexes on our dataset. Compared with five state-of-the-art gait recognition methods, the proposed method achieves the best performance on human gait recognition based on the walking sequences defined in our proposed dataset.