研究目的
To develop a mobile robot navigation control system that integrates LiDAR SLAM localization with real-time obstacle avoidance for personnel guidance in daily-life services, enabling the robot to navigate to a target location while avoiding obstacles.
研究成果
The proposed navigation control system successfully integrates LiDAR SLAM with obstacle avoidance, allowing the robot to guide users to target locations safely and accurately in environments with obstacles. Future work may involve extending the method to multi-robot systems and investigating learning models for obstacle avoidance in complex environments.
研究不足
The paper does not explicitly mention limitations, but potential areas for optimization could include handling more complex environments, reducing computational load, or improving robustness to dynamic obstacles. The use of LiDAR, while accurate, is noted to be expensive.
1：Experimental Design and Method Selection:
The system uses a behavior fusion scheme based on shared control to integrate LiDAR SLAM (Cartographer SLAM and AMCL) with reactive obstacle avoidance. The goal-seeking controller and obstacle avoidance controller are combined using a safety-weight parameter.
2：Sample Selection and Data Sources:
A mobile robot equipped with two laser scanners (front for SLAM and obstacle avoidance, rear for user position estimation) is used in experiments conducted in a collider environment.
3：List of Experimental Equipment and Materials:
Mobile robot with laser scanners (specific models not mentioned), ROS software architecture, Cartographer SLAM, AMCL algorithms.
4：Experimental Procedures and Operational Workflow:
The robot performs localization experiments (e.g., square trajectory motion) and autonomous guidance experiments where it guides users to targets while avoiding obstacles. Data is collected on robot position, trajectory, and obstacle interactions.
5：Data Analysis Methods:
Position errors are calculated by comparing ground truth with SLAM estimates; trajectory and map data are visualized and analyzed to verify navigation accuracy and obstacle avoidance effectiveness.
独家科研数据包，助您复现前沿成果，加速创新突破
获取完整内容
