外观
论文arXiv 2610.2033314 天前
VIGOR-MPC：视觉引导的目标调节 MPC
原文链接：VIGOR-MPC: Vision-Guided Objective Regulation MPC（arXiv 2610.20333 · 发布日期：2026-10-14）
VIGOR-MPC: Vision-Guided Objective Regulation MPC
VIGOR-MPC通过学生-教师蒸馏将视野感知长时域MPC转为视觉在线调参短时域MPC，并在仿真和硬件视觉自主赛车中验证。
核心要点
- 仅依赖机载视觉控制时，感知噪声、遮挡和算力共享限制实时规划时域。
- 框架与感知管线无关，将有特权信息的长时域MPC蒸馏为轻量短时域MPC。
- 学生利用噪声和遮挡的感知上下文，经多级循环映射在线推断代价参数。
- 在未见赛道可泛化，圈速接近特权教师，并将单步计算降低90%以上。
验证范围与局限：验证范围为仿真和硬件上的基于视觉的自主赛车任务。
英文摘要 (Abstract)
Controlling an agent in an environment solely perceived through onboard vision is challenging: perception yields noisy, variable-length, and partially occluded context, while onboard compute is shared between perception and control, limiting the planning horizon executable in real time. We propose VIGOR-MPC, a modular student-teacher framework, agnostic to the perception pipeline, which addresses reference tracking across navigation tasks by distilling a privileged, field-of-view-aware long-horizon MPC into a computationally lightweight short-horizon MPC whose cost parameters are determined online from vision. The teacher operates in simulation with full state knowledge and a multi-trajectory formulation that guarantees the agent can stay within its field of view. The student observes only the noisy, occluded context produced by a perception module and learns, via a multi-level recurrent mapping, to infer cost parameters that aim to recover the teacher's behavior despite missing information. We evaluate VIGOR-MPC on vision-based autonomous racing in simulation and on hardware. Using only onboard perception of the track, VIGOR-MPC generalizes to tracks unseen during training and approaches the lap times of the privileged long-horizon teacher while reducing per-step computation by over 90%.
作者：Jelena Trisovic, Rahel Rickenbach, Marek Landert, Panagiotis Minos, Melanie N. Zeilinger
来源
本页事实对应的公开页面，以原文为准。