Commonly used robot map models include occupancy grid maps, topological maps, and semantic maps. Among these, an occupancy grid map is mainly represented as a quadrilateral grid. This paper proposes an occupancy information grid for intelligent robots by exploiting the advantages of the occupancy grid map and spatial information grid. In terms of geometric structure, a regular hexagonal grid is used instead of a regular quadrilateral grid. In terms of attribute structure, the single obstacle attribute is replaced by the grid terrain characteristics, grid element attributes, and grid edge attributes. Thus, the occupancy information grid model is transformed into a new data structure describing the spatial environment, and it can be effectively applied to map construction and path planning of intelligent robots. For the map construction application of intelligent robots, this paper describes the basic process of laser sensor-based grid model construction. For the path planning application of intelligent robots, this paper extends the A* algorithm based on a regular hexagonal grid. Additionally, map construction and path planning applications for intelligent robots are experimentally verified. Several experimental results were obtained. First, the experimental results confirmed the theoretical conclusion that the minimum sampling density of the hexagonal structure was 13.4% lower than that of the quadrilateral structure. Second, the regular hexagonal grid is clearly more advantageous in describing environmental scenes, which can ameliorate the "undercompleteness" phenomenon. Third, there were large differences in the planning paths based on two types of grids, as shown by the fact that the distance of the planning paths obtained by the regular hexagonal grid was reduced by at least 10.8% and at most 15.6% compared with the regular quadrilateral grid.

Facing the realistic demands of the application environment of robots, the application of simultaneous localisation and mapping (SLAM) has gradually moved from static environments to complex dynamic environments, while traditional SLAM methods usually result in pose estimation deviations caused by errors in data association due to the interference of dynamic elements in the environment. This problem is effectively solved in the present study by proposing a SLAM approach based on light detection and ranging (LiDAR) under semantic constraints in dynamic environments. Four main modules are used for the projection of point cloud data, semantic segmentation, dynamic element screening, and semantic map construction. A LiDAR point cloud semantic segmentation network SANet based on a spatial attention mechanism is proposed, which significantly improves the real-time performance and accuracy of point cloud semantic segmentation. A dynamic element selection algorithm is designed and used with prior knowledge to significantly reduce the pose estimation deviations caused by SLAM dynamic elements. The results of experiments conducted on the public datasets SemanticKITTI, KITTI, and SemanticPOSS show that the accuracy and robustness of the proposed approach are significantly improved.

This paper takes 6-DOF manipulator as the research object, proposes the improved Artificial Potential Field (APF) method to plan the obstacle avoidance path of the manipulator, and combines the Danger Field (DF) method to evaluate the safety of the path planned using APF. According to the characteristics of the manipulator, the kinematics model of the manipulator is analyzed, and the ball envelope algorithm is applied to simplify the physical model of the obstacle. Compared with the traditional APF method, the improved APF searches in the joint space and introduces the joint attraction potential to improve the search speed and accuracy. The problem of local minimum is dealt with by the combination of adding virtual obstacles and increasing joint attraction potential. The improved APF not only has the advantages of good real-time performance and smooth path, but also solves the problem of the traditional APF falling into a local minimum, and combines the danger field method to judge the path rationality to ensure no collision with obstacles. Through simulation verification, the proposed method realizes the obstacle avoidance path planning of the manipulator and the safety evaluation of the planned path.

Grid-based Generalized Voronoi Diagrams (GVDs) are widely used to represent the surrounding environment of intelligent agents in the fields of robotics, computer games, and military simulations, which improve the efficiency of path planning of intelligent agents. Current studies mainly focus on square-grid-based GVD construction approaches, and little attention has been paid to constructing GVDs from hexagonal grids. In this paper, an algorithm named hexagon-based crystal growth (HCG) is presented to extract GVDs from hexagonal grids. In addition, two thinning patterns for obtaining one-cell-wide GVDs from rough hexagon-based GVDs are proposed. On the basis of the principles of a leading square-grid-based algorithm named Brushfire, a hexagon-based Brushfire algorithm is realized. A comparison of the HCG and the hexagon-based Brushfire algorithm shows that HCG is much more efficient. Further, the usefulness of hexagon-based GVDs for the path planning tasks of intelligent agents is demonstrated using several representative simulation experiments.

Path planning for unmanned ground vehicles (UGVs) in off-road environments faces challenges such as inadequate trafficability assessment, local optima issues, and limited dynamic obstacle avoidance. This article presents a dynamic path planning algorithm called LSTM-DPPO, which combines long short-term memory (LSTM) and distributed proximal policy optimization (DPPO). First, a UGV trafficability map was created that incorporates three environmental factors, which provides reliable environmental representation for the UGV. Second, a comprehensive reward function was developed, which combines dynamic obstacle avoidance with trafficability assessment. This function facilitates the collaborative optimization of both path safety and overall trafficability. Additionally, to address the issues of ineffective dynamic obstacle avoidance and the challenges of model convergence commonly found in reinforcement learning algorithms, we introduced an LSTM network to build a dynamic obstacle prediction module. We also employed a distributed proximal policy optimization (PPO) architecture to enhance the training speed of the model. Finally, a comparative simulation experiment was conducted between the LSTM-DPPO algorithm and six path planning algorithms, and the generalization ability of the LSTM-DPPO algorithm was verified in three new scenarios. The results indicate that the average inference time of the complete LSTM-DPPO algorithm is 1.74 ms, which meets the requirements of real-time path planning. Although its planning time is slightly longer than the DPPO algorithm and constant velocity model (CV)-DPPO algorithm (constant velocity model, CV), it is much faster than the other four algorithms. The LSTM-DPPO algorithm excels in obstacle avoidance, has the highest success rate, and demonstrates good generalization in new scenarios.