基于CNN传感器融合的移动机器人实时障碍规避
Real-Time Obstacle Avoidance for a Mobile Robot Using CNN-Based Sensor Fusion
AI总结：
本文提出基于CNN的传感器融合方法，用于移动机器人在复杂环境中实时规避障碍，NetConEmb模型在精度和鲁棒性上表现最优。
摘要：
障碍规避是移动机器人在复杂和未知环境中有效运行所需导航堆栈的关键组成部分。在本研究中，三个端到端的卷积神经网络（CNNs）被离线训练和评估，并部署在差分驱动移动机器人上，用于实时障碍规避，以从Intel RealSense D415 RGB-D相机同步获取的颜色和深度图像生成低层转向指令。离线评估显示，NetConEmb模型表现最佳，具有显著低的MedAE值为0.58×10⁻³ rad/s。相比之下，较轻的NetEmb架构通过减少约25%的可训练参数并更快收敛，产生了RMSE为21.68×10⁻³ rad/s的相似结果，接近NetConEmb的21.42×10⁻³ rad/s。实时导航进一步确认了NetConEmb的鲁棒性，在已知和未知环境中均实现了100%的成功率，而NetEmb和NetGated仅在已知环境中成功导航。
英文摘要：
Obstacle avoidance is a critical component of the navigation stack required for mobile robots to operate effectively in complex and unknown environments. In this research, three end-to-end Convolutional Neural Networks (CNNs) were trained and evaluated offline and deployed on a differential-drive mobile robot for real-time obstacle avoidance to generate low-level steering commands from synchronized color and depth images acquired by an Intel RealSense D415 RGB-D camera in diverse environments. Offline evaluation showed that the NetConEmb model achieved the best performance with a notably low MedAE of $0.58 \times 10^{-3}$ rad/s. In comparison, the lighter NetEmb architecture, which reduces the number of trainable parameters by approximately 25\% and converges faster, produced comparable results with an RMSE of $21.68 \times 10^{-3}$ rad/s, close to the $21.42 \times 10^{-3}$ rad/s obtained by NetConEmb. Real-time navigation further confirmed NetConEmb's robustness, achieving a 100\% success rate in both known and unknown environments, while NetEmb and NetGated succeeded only in navigating the known environment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
