With the advancement of robotics, the field of path planning is currently experiencing a period of prosperity. Researchers strive to address this nonlinear problem and have achieved remarkable results through the implementation of the Deep Reinforcement Learning (DRL) algorithm DQN (Deep Q-Network). However, persistent challenges remain, including the curse of dimensionality, difficulties of model convergence and sparsity in rewards. To tackle these problems, this paper proposes an enhanced DDQN (Double DQN) path planning approach, in which the information after dimensionality reduction is fed into a two-branch network that incorporates expert knowledge and an optimized reward function to guide the training process. The data generated during the training phase are initially discretized into corresponding low-dimensional spaces. An “expert experience” module is introduced to facilitate the model’s early-stage training acceleration in the Epsilon–Greedy algorithm. To tackle navigation and obstacle avoidance separately, a dual-branch network structure is presented. We further optimize the reward function enabling intelligent agents to receive prompt feedback from the environment after performing each action. Experiments conducted in both virtual and real-world environments have demonstrated that the enhanced algorithm can accelerate model convergence, improve training stability and generate a smooth, shorter and collision-free path.
A reconstruction method based on differential manifold and non-uniform rational B-spline is proposed to improve the reconstruction performance of massive point complex surface models. First, this method is simplified based on the Hausdorff distance of feature points. Second, in order to completely reconstruct the model and avoid the complex splicing of non-uniform rational B-spline, the regular domain of non-uniform rational B-spline is extended to differential manifolds, and the basis functions of the control vertices are established by using the shortest distance. Finally, the element decomposition of the differential manifold is calculated through the normalized basis functions, composite element decomposition, and control vertices to achieve the final surface model. The experiment results show that the proposed method has high reconstruction efficiency and accuracy for arbitrary topological surfaces.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.