Tang Yuhu, Bai Ying, Chen Qiang
School of Artificial Intelligence and Big Data, Hefei University, Hefei 230601, China.
Anhui JinHai Deer Information Technology Co., Ltd., Hefei 230088, China.
Sensors (Basel). 2025 Mar 15;25(6):1839. doi: 10.3390/s25061839.
Accurate obstacle recognition and avoidance are critical for ensuring the safety and operational efficiency of autonomous robots in dynamic and complex environments. Despite significant advances in deep-learning techniques in these areas, their adaptability in dynamic and complex environments remains a challenge. To address these challenges, we propose an improved Transformer-based architecture, GAS-H-Trans. This approach uses a grouped aggregation strategy to improve the robot's semantic understanding of the environment and enhance the accuracy of its obstacle avoidance strategy. This method employs a Transformer-based dual-coupling grouped aggregation strategy to optimize feature extraction and improve global feature representation, allowing the model to capture both local and long-range dependencies. The Harris hawk optimization (HHO) algorithm is used for hyperparameter tuning, further improving model performance. A key innovation of applying the GAS-H-Trans model to obstacle avoidance tasks is the implementation of a secondary precise image segmentation strategy. By placing observation points near critical obstacles, this strategy refines obstacle recognition, thus improving segmentation accuracy and flexibility in dynamic motion planning. The particle swarm optimization (PSO) algorithm is incorporated to optimize the attractive and repulsive gain coefficients of the artificial potential field (APF) methods. This approach mitigates local minima issues and enhances the global stability of obstacle avoidance. Comprehensive experiments are conducted using multiple publicly available datasets and the Unity3D virtual robot environment. The results show that GAS-H-Trans significantly outperforms existing baseline models in image segmentation tasks, achieving the highest mIoU (85.2%). In virtual environment obstacle avoidance tasks, the GAS-H-Trans + PSO-optimized APF framework achieves an impressive obstacle avoidance success rate of 93.6%. These results demonstrate that the proposed approach provides superior performance in dynamic motion planning, offering a promising solution for real-world autonomous navigation applications.
在动态复杂环境中，准确的障碍物识别与避障对于确保自主机器人的安全性和运行效率至关重要。尽管深度学习技术在这些领域取得了显著进展，但其在动态复杂环境中的适应性仍然是一个挑战。为应对这些挑战，我们提出了一种改进的基于Transformer的架构GAS-H-Trans。该方法采用分组聚合策略来提高机器人对环境的语义理解，并增强其避障策略的准确性。此方法采用基于Transformer的双耦合分组聚合策略来优化特征提取并改善全局特征表示，使模型能够捕捉局部和远程依赖关系。哈里斯鹰优化（HHO）算法用于超参数调整，进一步提高模型性能。将GAS-H-Trans模型应用于避障任务的一个关键创新是实施二次精确图像分割策略。通过在关键障碍物附近设置观察点，该策略细化了障碍物识别，从而提高了动态运动规划中的分割精度和灵活性。引入粒子群优化（PSO）算法来优化人工势场（APF）方法的吸引和排斥增益系数。这种方法减轻了局部极小值问题，并增强了避障的全局稳定性。使用多个公开可用数据集和Unity3D虚拟机器人环境进行了综合实验。结果表明，GAS-H-Trans在图像分割任务中显著优于现有的基线模型，实现了最高的平均交并比（mIoU）（85.2%）。在虚拟环境避障任务中，GAS-H-Trans + PSO优化的APF框架实现了令人印象深刻的93.6%的避障成功率。这些结果表明，所提出的方法在动态运动规划中提供了卓越的性能，为实际的自主导航应用提供了一个有前景的解决方案。
