The robotic manipulator has become an indispensable piece of the manufacturing equipment. The key to guiding its movement is path planning technology, which is becoming increasingly important due to the complex working environments, in which the robotic manipulator is used. This paper proposes the improved bidirectional rapid exploration random trees algorithm( IBi-RRT ) and applies it to the path planning of a 6 degrees of freedom (6-DOF) robotic manipulator. The proposed algorithm has two improved strategies. Firstly, the idea of preferential selection of random node is adopted to reduce randomness in the expansion. Secondly, the adjustable attractive force size strategy is used to increase search speed. In order to make the planned path more in line with the actual motion path of the 6-DOF robotic manipulator, a quadratic B-spline function is used to smooth the initial path. Simulations and experiments are performed to verify the effectiveness and superiority of the proposed algorithm. Simulation results and experiments demonstrate that the IBi-RRT algorithm can safely move the 6-DOF robotic manipulator to the designated position.

When UAVs are carrying out missions, they are faced with complex task environments. To enhance the adaptability of UAV applications, it is required that they possess fast path-planning capabilities. This paper takes the execution of complex tasks by multiple UAVs in a three-dimensional environment as background and transforms the path-planning problem into a multi-constraint optimization problem. Innovatively combining the HPO algorithm and task allocation mechanism, this study achieves collaborative path planning for multiple UAVs for complex tasks. In order to improve the optimization speed of the HPO algorithm, the following improvements have been made: firstly, introducing the chaotic mapping model to improve the performance of population initialization; secondly, adopting the golden sine strategy to change the population update strategy and accelerate the convergence speed of the algorithm. Then, the single-peak and multi-peak benchmark functions are used to test the average, standard deviation, and optimal values of the algorithm. Finally, path planning experiments are carried out in a three-dimensional map with multiple task points and obstacles, and the results show that the AGSHPO algorithm improves the robustness and real-time performance of the UAVs when executing complex tasks to a certain extent.

Aiming at the accuracy problem of pose estimation under complex pose of indoor UAV, this paper proposes a dynamic threshold setting method based on vision sensor pose detection for adaptive selection of keyframes. Due to the uncertainty of camera pose estimation, this paper uses statistical theory to analyze the pose difference between camera frames to characterize the camera motion characteristics, innovatively employs a multi-layered fuzzy inference mechanism for joint judgment to derive dynamic thresholds, and applies this method to ORB-SLAM3 system to construct a new system called Fuzzy-ORB-SLAM3 for the purpose of achieving adaptive compensation in keyframe creation. Finally, the new system is validated on TUM and EuRoc public datasets. The results compared with ORB-SLAM3 and other typical SLAM systems show that the proposed system has higher positioning accuracy and can better adapt to the pose estimation of UAVs in complex motion states.

The mammalian used to direct its vision field to a sound source by its auditory system. So an auditory system of robot for sound source localization is proposed in this paper. Through using the four-element microphone array, the time differences of arrival can be achieved and the sound-source target can be localized. The experiment system is introduced. Then the localization algorithm based on the spherical wave model of propagation is developed in this paper, and the calculation error also be discussed. The experiment results show that the algorithm can accurately calculate the azimuth of the sound source and the localization system can effectively lead the robot to the direction of the target.

Novel view synthesis aims to generate new perspectives from a limited number of input views. Neural Radiance Field (NeRF) is a key method for this task, and it produces high-fidelity images from a comprehensive set of inputs. However, a NeRF’s performance drops significantly with sparse views. To mitigate this, depth information can be used to guide training, with coarse depth maps often readily available in practical settings. We propose an improved sparse view NeRF model, ATGANNeRF, which integrates an enhanced U-Net generator with a dual-discriminator framework, CBAM, and Multi-Head Self-Attention mechanisms. The symmetric design enhances the model’s ability to capture and preserve spatial relationships, ensuring a more consistent generation of novel views. Additionally, local depth ranking is employed to ensure depth consistency with coarse maps, and spatial continuity constraints are introduced to synthesize novel views from sparse samples. SSIM loss is also added to preserve local structural details like edges and textures. Evaluation on LLFF, DTU, and our own datasets shows that ATGANNeRF significantly outperforms state-of-the-art methods, both quantitatively and qualitatively.