In order to solve the problems of long-term cumulative error and the absence of absolute pose in the existing Lidar-Inertial Measurement Unit (IMU) fusion methods for Automated Guided Vehicle (AGV) Simultaneous Locali...
详细信息
ISBN:
(数字)9798350361674
ISBN:
(纸本)9798350361681
In order to solve the problems of long-term cumulative error and the absence of absolute pose in the existing Lidar-Inertial Measurement Unit (IMU) fusion methods for Automated Guided Vehicle (AGV) Simultaneous Localization and Mapping (SLAM), we propose a new SLAM method for mobile robot, integrating Lidar, IMU, and a downward vision camera. Firstly, we tightly couple Lidar-IMU and downward vision camera using a multimodal fusion framework. Downward visual measurements are integrated as QR factors into the factor graph, providing absolute pose information to correct cumulative error in the Lidar-IMU system and enable the joint pose estimation of the AGV. Secondly, an enhanced Iterative Closest Point (ICP) point cloud matching algorithm has been developed to correct the incorrect pose. This approach achieves Scan-to-Map alignment by employing a coarse-to-fine matching strategy, thereby enhancing the accuracy of point cloud alignment. Finally, the extended Kalman filter is used to optimize the Lidar pose drift, as well as the Lidar mapping effectively by using the Lidar-IMU as the measurements and the downward visual measurements as the updates. The algorithm has been extensively evaluated on the developed AGV experimental platform. The experimental results show that the position error is less than 0.02 meters and the orientation error is less than 1°, which solves the problems of long-term error accumulation and the lack of absolute pose information for AGV navigation.
The increasing demand for heterogeneous functionality in the automotive industry and the evolution of chip manufac-turing processes have led to the transition from federated to integrated critical real-time embedded s...
详细信息
ISBN:
(数字)9783981926385
ISBN:
(纸本)9798350348606
The increasing demand for heterogeneous functionality in the automotive industry and the evolution of chip manufac-turing processes have led to the transition from federated to integrated critical real-time embedded systems (CRTESs). This leads to higher integration challenges of conventional timing predictability techniques due to access contention on shared resources, which can be resolved by providing system-level observability and controllability in hardware. We focus on the interconnect as a shared resource and propose AXI-REALM, a lightweight, modular, and technology - independent real-time extension to industry-standard AXI4 interconnects, available open-source. AXI-REALM uses a credit-based mechanism to distribute and control the bandwidth in a multi-subordinate system on periodic time windows, proactively prevents denial of service from malicious actors in the system, and tracks each manager's access and interference statistics for optimal budget and period selection. We provide detailed performance and implementation cost assessment in a 12nm node and an end-to-end functional case study implementing AXI-REALM into an open-source Linux-capable RISC-V SoC. In a system with a general-purpose core and a hardware accelerator's DMA engine causing interference on the interconnect, AXI-REALM achieves fair bandwidth distribution among managers, allowing the core to recover 68.2 % of its performance compared to the case without contention. Moreover, near-ideal performance (above 95 %) can be achieved by distributing the available bandwidth in favor of the core, improving the worst-case memory access latency from 264 to below eight cycles. Our approach minimizes buffering compared to other solutions and introduces only 2.45 % area overhead compared to the original SoC.
Although remarkable advances have been achieved in generic object detection, small object detection (SOD) remains challenging owing to small objects’ information loss and noisy representation caused by their non-unif...
详细信息
ISBN:
(数字)9798350377705
ISBN:
(纸本)9798350377712
Although remarkable advances have been achieved in generic object detection, small object detection (SOD) remains challenging owing to small objects’ information loss and noisy representation caused by their non-uniform distribution. Their limited width and height, scale variations, and redundant computation make SOD hard. To overcome them, this work proposes a new SOD method based on sparse convolutional network (SCNet) and Query Mechanism called QuerySOD. First, an extended feature pyramid network is constructed for extracting feature maps of small objects with more regional details. Then, a Sparse Head is neatly designed by using SCNet for accelerating the interfering speed and obtaining weights of each layer. After that, a Query Mechanism is innovatively introduced for harvesting the benefit of sparse value feature maps from the Sparse Head. QuerySOD is evaluated on public benchmarks including COCO and VisDrone. Finally, we apply it on ‘Jinghai’ unmanned survey vehicles and receive excellent SOD performance from this real-world application.
Topological semantic maps provide a practical solution to enhance indoor navigation for the Partially Sighted or Visually Impaired (PSVI). Segmenting indoor floor plans and extracting boundaries are key to constructin...
详细信息
ISBN:
(数字)9798350377705
ISBN:
(纸本)9798350377712
Topological semantic maps provide a practical solution to enhance indoor navigation for the Partially Sighted or Visually Impaired (PSVI). Segmenting indoor floor plans and extracting boundaries are key to constructing these maps. The existing methods exhibit low accuracy in segmentation. To achieve desired high segmentation accuracy, we introduce a Context-Enhanced Full-Resolution Network (CEFRN) for floor plan segmentation. It is designed to harness the shallow detailed features and inter-category contextual dependencies inherent in floor plans. CEFRN integrates modified residual blocks to capture the low-stage full-resolution features while maintaining its compactness. A position attention module is employed to refine the deep-stage contextual information. We also propose a two-dimensional deep supervision method to merge features from both stages, which significantly boosts the feature representation ability of CEFRN. Finally, a practical topological semantic mapping method for PSVI indoor navigation is introduced. Experimental results demonstrate that CEFRN’s segmentation accuracy well exceeds the state-of-the-art methods’. It can be used to well support accurate topological semantic mapping.
In the design and planning of next-generation Internet of Things(IoT),telecommunication,and satellite communication systems,controller placement is crucial in software-defined networking(SDN).The programmability of th...
详细信息
In the design and planning of next-generation Internet of Things(IoT),telecommunication,and satellite communication systems,controller placement is crucial in software-defined networking(SDN).The programmability of the SDN controller is sophisticated for the centralized control system of the entire ***,it creates a significant loophole for the manifestation of a distributed denial of service(DDoS)attack ***,recently a Distributed Reflected Denial of Service(DRDoS)attack,an unusual DDoS attack,has been ***,minimal deliberation has given to this forthcoming single point of SDN infrastructure failure ***,recently the high frequencies of DDoS attacks have increased *** this paper,a smart algorithm for planning SDN smart backup controllers under DDoS attack scenarios has *** proposed smart algorithm can recommend single or multiple smart backup controllers in the event of DDoS *** obtained simulated results demonstrate that the validation of the proposed algorithm and the performance analysis achieved 99.99%accuracy in placing the smart backup controller under DDoS attacks within 0.125 to 46508.7 s in SDN.
This research introduces a kinetic friction modeling and measurement method for silicon nanowires (NWs) and silicon carbide substrates. The NW was pushed to slide by the micro-force probe at a constant speed. Under th...
详细信息
Face anti-spoofing is essential for ensuring the security of facial recognition systems against spoofing attacks. Recent methods have transferred Vision-Language models to face anti-spoofing (e.g., FLIP and CLIPC8), d...
详细信息
Simultaneous Localization and Mapping (SLAM) is a robot navigation approach used to estimate a movement of a sensor in an unknown environment. SLAM application examples include urban search and rescue operations in hi...
详细信息
Relying on the unique C-leg structure, RHex robots have good mobility and traffic ability when having relatively simple structures. Based on the existing RHex robots, taking into account the performance and cost, this...
详细信息
ISBN:
(纸本)9781665481106
Relying on the unique C-leg structure, RHex robots have good mobility and traffic ability when having relatively simple structures. Based on the existing RHex robots, taking into account the performance and cost, this design develops a small hexapod robot, named smallRhex, with low cost but strong performance. This paper mainly introduces the mechanical structure, robot gaits, simulation, and physical performance tests of smallRhex robots. The hardware is mainly based on the raspberry pie microcomputer and Robomaster motor and accessories. The high power density meets the dual requirements of performance and cost. Then cooperates with 3D printing and sheet metal and machined parts processing to complete the design of the mechanical structure and assembly of the robot. At the control level, raspberry pie directly controls the movement of 6 motors. The gait design includes basic motion gait, which includes straight walking and turning, and other gaits of complex motion: stair climbing, jumping, and high obstacle climbing. They are simulated in Webots. Finally, the performance test and the gait test of the robot are carried out. Then the gait design is further optimized, and the basic design of smallRhex robot is completed.
Boolean networks, as logical dynamical systems where the system states are Boolean variables, arise from applications in biology, computer networks, and social networks etc. In this paper, we present a framework to ev...
详细信息
Boolean networks, as logical dynamical systems where the system states are Boolean variables, arise from applications in biology, computer networks, and social networks etc. In this paper, we present a framework to evaluate whether and how the closed-loop dynamics of a controlled Boolean network can be shaped into any prescribed form by state-feedback control. We refer to this problem as to the feedback shaping for Boolean networks. First of all, based on the linear representation of Boolean networks, we establish a necessary and sufficient rank condition for a controlled Boolean network to be feedback shapable or not. Next, we design an algorithm for the synthesis of closed-loop dynamics for a feedback shapable Boolean network, such that for any given controlled Boolean network and a desired closed-loop dynamics, one can always find a feedback control law so that the closed-loop dynamics is precisely realized.
暂无评论