Large reasoning models (LRMs) have shown significant progress in test-time scaling through chain-of-thought prompting. Current approaches like search-o1 integrate retrieval augmented generation (RAG) into multi-step reasoning processes but rely on a single, linear reasoning path while incorporating unstructured textual information in a flat, context-agnostic manner. As a result, these approaches can lead to error accumulation throughout the reasoning chain, which significantly limits its effectiveness in medical question-answering (QA) tasks where both accuracy and traceability are critical requirements. To address these challenges, we propose MIRAGE (Multi-path Inference with Retrieval-Augmented Graph Exploration), a novel test-time scalable reasoning framework that performs dynamic multi-path inference over structured medical knowledge graphs. Specifically, MIRAGE 1) decomposes complex queries into entity-grounded sub-questions, 2) executes parallel inference paths, 3) retrieves evidence adaptively via neighbor expansion and multi-hop traversal, and 4) integrates answers using cross-path verification to resolve contradictions. Experiments on three medical QA benchmarks (GenMedGPT-5k, CMCQA, and ExplainCPE) show that MIRAGE consistently outperforms GPT-4o, Tree-of-Thought variants, and other retrieval-augmented baselines in both automatic and human evaluations. Additionally, MIRAGE improves interpretability by generating explicit reasoning chains that trace each factual claim to concrete paths within the knowledge graph, making it especially suitable for complex medical reasoning scenarios.

Reversible data hiding in encrypted images (RDHEIs) has attracted considerable attention, as it can facilitate the management of massive encrypted images and can be employed for covert communication. Recent research has demonstrated that the RDHEI methods with pixel prediction can achieve a more significant embedding capacity than those that do not utilize pixel prediction. Moreover, the accuracy of predictors greatly impacts the embedding capacity. Nevertheless, current predictors have several limitations, including a lack of accuracy and insufficient flexibility. To address these issues, we propose a high-precision multidirectional gradient predictor (MDGP). Based on this predictor, a novel region-based RDHEI method is proposed. Pixel prediction, image compression, data embedding, data extraction, and image recovery are conducted independently within image regions. Extensive experiments have demonstrated that the proposed MDGP predictor outperforms the current predictors in several metrics, including the average absolute errors, information entropy, and embedding capacity. The proposed RDHEI method demonstrates superior embedding capacity on the test images, and the data sets BOSSBase and BOWS2 outperforming the several state-of-the-art methods. Furthermore, it exhibits robust resilience to a variety of attacks, including perceptual attacks, statistical analysis, and patch removal attacks.

To overcome the issue of poor absolute positioning accuracy owing to the low stiffness of serial robot arms, this study proposed a new dual-arm robot (DAR) through the optimisation of the configuration of traditional robots. The DAR adopts a novel kinematic structure comprising a pair of 3-degree of freedom (DOF) robots: the workpiece and tool arms. A kinematic modelling method based on a closed-loop virtual kinematic chain was proposed to solve the problem of synchronous control of both arms via one controller. The workspace of the DAR was calculated, and the singularity was analysed. Furthermore, the stiffness was evaluated through finite element analysis. The results demonstrate that the DAR exhibits significantly higher stiffness, thus enabling considerably better positioning accuracy. To verify the superiority of the proposed DAR, a machining platform was developed based on the DAR for grinding and polishing an aero-engine blade. Compared to a traditional serial 6-DOF robot, the proposed DAR significantly improved the contour accuracy, with a surface roughness Ra 0.3 v.s. 0.4$\mu $m. Furthermore, the profile deviation of the blade body and edge were$+$0.05 mm, -0.07 mm v.s.$+$0.075 mm, -0.07 mm, and$+$0.05 mm, -0.03 mm v.s.$+$0.05 mm, -0.05 mm, respectively.Note to Practitioners—This study aimed to enhance the machining accuracy of industrial robotic machining. A novel dual-arm robot with superior stiffness was designed and compared with a conventional serial 6-DOF robot. A prototyping DAR was developed as the foundation for a grinding platform’s subsequent design and construction. The platform was utilised in aero-engine blade grinding and polishing. The contour accuracy of the processed blade drastically improved compared with that of the traditional serial 6-DOF robot system. Experiments verified the proposed robot’s feasibility and superiority in improving the robotic machining accuracy. Furthermore, the proposed DAR exhibited good potential for application in other robotic machining scenarios, such as assembly, carving, etc.

As the core foundation of web mapping, each geographic object (geo-object), such as a traffic sign, plays a vital role in navigation and intelligent driving. Determining how to obtain the latest high-precision geo-object information is a classic topic in updating road databases. Benefiting from the cost-effective attribute and availability of the positioning equipment and camera, the vision-based update pattern is becoming increasingly popular in the industry. Generally speaking, the road database update mainly includes three phases: geo-object recognition, localization, and change detection. Previous change detection strategies are mainly performed by comparing the historical road information (i.e., geo-object type and position) with the new geographic data of geo-objects collected from the street-view imagery. However, limited by the localization precision of the positioning equipment and the discriminative power of the vanilla differential-based method, the accuracy, recall, and efficiency of previous systems for geo-object change detection are greatly impaired. In addition, the artificially prescribed production standards make the geo-object position in the map data deviate from its position in the real world, as well as some geo-objects do not need to be updated (e.g., temporary speed limit), which further yields many false-positive detections and significantly increases the labor costs of existing systems. To address these challenges, we propose a novel framework called DuARUS for automatic geo-object change detection with street-view imagery. In this paper, we mainly focus on automatic geo-object localization and change detection. Specifically, for geo-object localization, we propose a two-stage, integrated localization algorithm based on image matching and monocular depth estimation. Furthermore, to achieve automatic change detection, vision-based representation learning and scene understanding strategies are introduced to build a large-scale geo-object semantic map, which can provide sufficient multimodal information support for change detection. Based on such artful modeling, we recast the complicated, labor-based change detection problem as a vanilla binary classification task, which is a robust and efficient strategy that contributes to resolving this problem. By combining these operations, we construct an industrial-grade, fully automatic production system for road database updates. Extensive experiments conducted on large-scale, real-world datasets from Baidu Maps demonstrate the superiority and effectiveness of the system. Moreover, this system has already been deployed in production at Baidu Maps since July 2020, handling 96% of automatic road database updates. DuARUS improves the annual update mileage from millions to tens of millions, and it achieves weekly updates.

The task of road extraction has aroused remarkable attention due to its critical role in facilitating urban development and up-to-date map maintenance, which has widespread applications such as navigation and autonomous driving. Existing solutions either rely on a single source of data for road graph extraction or simply fuse the multimodal information in a sub-optimal way. In this paper, we present an automatic road extraction solution named DuARE, which is designed to exploit the multimodal knowledge for underlying road extraction in a fully automatic manner. Specifically, we collect a large-scale real-world dataset for paired aerial image and trajectory data, covering over 33,000 km2 in more than 80 cities. First, road extraction is performed on the abundant spatial-temporal trajectory data adaptively based on the density distribution. Then, a coarse-to-fine road graph learner from aerial images is proposed to take advantage of the local and global context. Finally, our cross-check-based fusion approach keeps the optimal state of each modality while revisiting the original trajectory map with the guidance of aerial predictions to further improve the performance. Extensive experiments conducted on large-scale real-world datasets demonstrate the superiority and effectiveness of DuARE. In addition, DuARE has been deployed in production at Baidu Maps since June 2021 and keeps updating the road network by 100,000 km per month. This confirms that DuARE is a practical and industrial-grade solution for large-scale cost-effective road extraction from multimodal data.

The autonomous robots consisting of an immovable lander and a rover are widely deployed to explore extraterrestrial planets. However, these robots have two main limitations: (1) the separate design for lander and rover respectively results in heavy mass and big volume of the whole system, which increases the launching cost sharply; (2) the rover’s detection area has to be restricted to the vicinity of the immovable lander. To overcome these problems, we designed a novel six-legged mobile repetitive lander called "HexaMRL", which integrates the functions of both lander and rover, including folding, deploying, repetitive soft-landing, and walking. A hybrid compliant mechanism taking advantages of both active and passive compliances was adopted on its leg. An integrated drive unit (IDU) was utilized to imitate the dynamics of a spring and a damper to absorb the landing impact energy, while the structure remains intact. Moreover, a control method based on state machine for soft-landing on the Moon was proposed. HexaMRL achieved repetitive soft-landing on a 5-DoF lunar gravity testing platform (5-DoF-LGTP) with a vertical landing velocity of 1.9 m/s and a payload of 140 kg. The drive torque safety margin is improved by 23.4%p based on the hybrid compliant leg comparing with the standalone active compliant leg.

Installing a six-dimensional force/torque sensor on an industrial arm for force feedback is a common robotic force control strategy. However, because of the high price of force/torque sensors and the closedness of an industrial robot control system, this method is not convenient for industrial mass production applications. Various types of data generated by industrial robots during the polishing process can be saved, transmitted, and applied, benefiting from the growth of the industrial internet of things (IIoT). Therefore, we propose a constant force control system that combines an industrial robot control system and industrial robot offline programming software for a polishing robot based on IIoT time series data. The system mainly consists of four parts, which can achieve constant force polishing of industrial robots in mass production. (1) Data collection module. Install a six-dimensional force/torque sensor at a manipulator and collect the robot data (current series data, etc.) and sensor data (force/torque series data). (2) Data analysis module. Establish a relationship model based on variant long short-term memory which we propose between current time series data of the polishing manipulator and data of the force sensor. (3) Data prediction module. A large number of sensorless polishing robots of the same type can utilize that model to predict force time series. (4) Trajectory optimization module. The polishing trajectories can be adjusted according to the prediction sequences. The experiments verified that the relational model we proposed has an accurate prediction, small error, and a manipulator taking advantage of this method has a better polishing effect.

In order to improve the detection and recognition ability of 3D echocardiography, a method of 3D echocardiography detection based on depth learning is proposed. The information conduction model of three-dimensional echocardiography is constructed. The edge pixel feature matching method is used to extract the key information of echocardiography, and the information compensation method is used to repair the missing area of three-dimensional echocardiography information. The feature decomposition and information fusion of 3D ultrasonic imaging are carried out by using five stage wavelet decomposition method, and the feature reconstruction and adaptive template matching of 3D echocardiography are processed by depth learning algorithm, modeling and detecting the rationality of three-dimensional echocardiography. The simulation results show that this method has better detection performance; the accuracy of detection and recognition is high, which is more reasonable in the application of 3D echocardiography repair and detection recognition.

This paper deals with the problem of city scale on-device mobile visual location recognition by fusing the inertial sensors and computer vision techniques. The main contributions are as follows: Firstly, we design an efficient vector quantization strategy by combining the Transform Coding (TC) and Residual Vector Quantization (RVQ). Our method can compress a visual descriptor into only several bytes while providing reasonable searching accuracy, which makes the managing of city scale image database directly on mobile devices come true. Secondly, we integrate the information from inertial sensors into the Vector of Locally Aggregated Descriptors (VLAD) generation and image similarity evaluation processes. Our method is not only fast enough for on-device implementation, but it also can improve the location recognition accuracy obviously. Thirdly, we also release a set of 1.295 million geo-tagged street view images with the information from inertial sensors, as well as a difficult set of query images. These resources can be used as a new benchmark to facilitate further research in the area. Experimental results prove the validity of the proposed methods for on-device mobile visual location recognition applications.