面向视觉导航的离线深度模型预测控制（MPC）
Offline Deep Model Predictive Control (MPC) for Visual Navigation
- International Artificial Intelligence Center of Morocco（摩洛哥国际人工智能中心）
- Mohammed VI Polytechnic University（穆罕默德六世理工大学）
- ENSAM（高等艺术与制造学院）
- Moulay Ismail University（穆莱·伊斯梅尔大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对单RGB相机视觉导航问题，提出结合ViewNet与VelocityNet的离线深度MPC方法，在VT&R框架下实现轨迹跟随，兼具低计算资源需求与高精度，经仿真验证可有效降低轨迹度量误差。
AI中文摘要：
本文提出了一种基于单RGB视角相机的新型视觉导航方法。采用Visual Teach & Repeat（VT&R，视觉示教与复现）方法，机器人在示教阶段获取由多个子目标图像组成的视觉轨迹。在复现阶段，我们提出两种网络架构，即ViewNet和VelocityNet。两个网络的结合使机器人能够跟随视觉轨迹。ViewNet被训练为基于当前视图和速度指令生成未来图像。生成的未来图像与子目标图像结合用于训练VelocityNet。我们在VelocityNet中开发了一种离线Model Predictive Control（MPC，模型预测控制）策略，其双重目标为：(1) 减小当前图像与子目标图像之间的差异；(2) 通过缓解速度不连续性确保轨迹平滑。离线训练节省计算资源，使其更适合计算能力有限的场景，例如嵌入式系统。我们在仿真环境中验证了实验，结果表明我们的模型能够有效最小化真实轨迹与复现轨迹之间的度量误差。
英文摘要：
In this paper, we propose a new visual navigation method based on a single RGB perspective camera. Using the Visual Teach & Repeat (VT&R) methodology, the robot acquires a visual trajectory consisting of multiple subgoal images in the teaching step. In the repeat step, we propose two network architectures, namely ViewNet and VelocityNet. The combination of the two networks allows the robot to follow the visual trajectory. ViewNet is trained to generate a future image based on the current view and the velocity command. The generated future image is combined with the subgoal image for training VelocityNet. We develop an offline Model Predictive Control (MPC) policy within VelocityNet with the dual goals of (1) reducing the difference between current and subgoal images and (2) ensuring smooth trajectories by mitigating velocity discontinuities. Offline training conserves computational resources, making it a more suitable option for scenarios with limited computational capabilities, such as embedded systems. We validate our experiments in a simulation environment, demonstrating that our model can effectively minimize the metric error between real and played trajectories.
