The Navigation System of a Logistics Inspection Robot Based on Multi-Sensor Fusion in a Complex Storage Environment

Zhang, Yang; Zhou, Yong‐Wu; Li, Hehua; Hao, Hao; Chen, Weijiong; Zhan, Wei

doi:10.3390/s22207794

Cited by 8 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ability to perceive visual cues is essential for quadruped robots to accomplish optimal obstacle avoidance and successful navigation. Conventional navigation algorithms rely on visual sensors such as laser radars and front cameras to construct a map of the environment, and then employ path planning algorithms such as A* and DWA based on the map [17][18][19][20]. However, such vision systems are often characterized by significant blind spots, particularly for robots with intricate mechanical structures.…”

Section: Vision Sensors For Robot Navigationmentioning

confidence: 99%

Hierarchical Vision Navigation System for Quadruped Robots with Foothold Adaptation Learning

Ren

Dai

Liu

et al. 2023

Sensors

View full text Add to dashboard Cite

Legged robots can travel through complex scenes via dynamic foothold adaptation. However, it remains a challenging task to efficiently utilize the dynamics of robots in cluttered environments and to achieve efficient navigation. We present a novel hierarchical vision navigation system combining foothold adaptation policy with locomotion control of the quadruped robots. The high-level policy trains an end-to-end navigation policy, generating an optimal path to approach the target with obstacle avoidance. Meanwhile, the low-level policy trains the foothold adaptation network through auto-annotated supervised learning to adjust the locomotion controller and to provide more feasible foot placement. Extensive experiments in both simulation and the real world show that the system achieves efficient navigation against challenges in dynamic and cluttered environments without prior information.

show abstract

Section: Vision Sensors For Robot Navigationmentioning

confidence: 99%

Hierarchical Vision Navigation System for Quadruped Robots with Foothold Adaptation Learning

Ren

Dai

Liu

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Meanwhile, if the space of robot motion is a multi-layer underground space, the method based on laser odometry alone will not be applicable. To expand the application scope of the robot odometer in the hierarchical space and improve the accuracy and robustness of the odometer, the laser is usually fused with other sensors to estimate the robot state together (Prasanna et al , 2020; Zhang et al , 2022).…”

Section: Introductionmentioning

confidence: 99%

Tightly coupled IMU-Laser-RTK odometry algorithm for underground multi-layer and large-scale environment

Wang,

Cong,

Liu

et al. 2023

View full text Add to dashboard Cite

Purpose The purpose of this study is to designed a robot odometry based on three dimensional (3D) laser point cloud data, inertial measurement unit (IMU) data and real-time kinematic (RTK) data in underground spatial features and gravity fluctuations environment. This method improves the mapping accuracy in two types of underground space: multi-layer space and large-scale scenarios. Design/methodology/approach An IMU–Laser–RTK fusion mapping algorithm based on Iterative Kalman Filter was proposed, and the observation equation and Jacobian matrix were derived. Aiming at the problem of inaccurate gravity estimation, the optimization of gravity is transformed into the optimization of SO(3), which avoids the problem of gravity over-parameterization. Findings Compared with the optimization method, the computational cost is reduced. Without relying on the wheel speed odometer, the robot synchronization localization and 3D environment modeling for multi-layer space are realized. The performance of the proposed algorithm is tested and compared in two types of underground space, and the robustness and accuracy in multi-layer space and large-scale scenarios are verified. The results show that the root mean square error of the proposed algorithm is 0.061 m, which achieves higher accuracy than other algorithms. Originality/value Based on the problem of large loop and low feature scale, this algorithm can better complete the map loop and self-positioning, and its root mean square error is more than double compared with other methods. The method proposed in this paper can better complete the autonomous positioning of the robot in the underground space with hierarchical feature degradation, and at the same time, an accurate 3D map can be constructed for subsequent research.

show abstract

“…To complete the task of inspecting substations, inspection robots need to have autonomous navigation capabilities [8]. At present, inspection robots equipped with 3D LiDAR cannot recognize the grass category, so they treat the grass as an obstacle based on the information of the ultrasonic sensor [9]. Thus, substation inspection robots need to recognize the grass in the substation and safely cross the grass areas to ensure efficient inspections.…”

Section: Introductionmentioning

confidence: 99%

A New Assistance Navigation Method for Substation Inspection Robots to Safely Cross Grass Areas

Yang,

Ma,

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

With the development of intelligent substations, inspection robots are widely used to ensure the safe and stable operation of substations. Due to the prevalence of grass around the substation in the external environment, the inspection robot will be affected by grass when performing the inspection task, which can easily lead to the interruption of the inspection task. At present, inspection robots based on LiDAR sensors regard grass as hard obstacles such as stones, resulting in interruption of inspection tasks and decreased inspection efficiency. Moreover, there are inaccurate multiple object-detection boxes in grass recognition. To address these issues, this paper proposes a new assistance navigation method for substation inspection robots to cross grass areas safely. First, an assistant navigation algorithm is designed to enable the substation inspection robot to recognize grass and to cross the grass obstacles on the route of movement to continue the inspection work. Second, a three-layer convolutional structure of the Faster-RCNN network in the assistant navigation algorithm is improved instead of the original full connection structure for optimizing the object-detection boxes. Finally, compared with several Faster-RCNN networks with different convolutional kernel dimensions, the experimental results show that at the convolutional kernel dimension of 1024, the proposed method in this paper improves the mAP by 4.13% and the mAP is 91.25% at IoU threshold 0.5 in the range of IoU thresholds from 0.5 to 0.9 with respect to the basic network. In addition, the assistant navigation algorithm designed in this paper fuses the ultrasonic radar signals with the object recognition results and then performs the safety judgment to make the inspection robot safely cross the grass area, which improves the inspection efficiency.

show abstract

The Navigation System of a Logistics Inspection Robot Based on Multi-Sensor Fusion in a Complex Storage Environment

Cited by 8 publications

References 14 publications

Hierarchical Vision Navigation System for Quadruped Robots with Foothold Adaptation Learning

Hierarchical Vision Navigation System for Quadruped Robots with Foothold Adaptation Learning

Tightly coupled IMU-Laser-RTK odometry algorithm for underground multi-layer and large-scale environment

A New Assistance Navigation Method for Substation Inspection Robots to Safely Cross Grass Areas

Contact Info

Product

Resources

About