外观
论文arXiv 2610.1596617 天前
用于操作员监督式神经驾驶的硬件分区 micro-ROS 微型车
原文链接：A Hardware-Partitioned micro-ROS Mini-Vehicle for Operator-Supervised Neural Driving（arXiv 2610.15966 · 发布日期：2026-10-11）
A Hardware-Partitioned micro-ROS Mini-Vehicle for Operator-Supervised Neural Driving
面向嵌入式神经驾驶研究，提出硬件分区的低成本微型Ackermann车，并在真实闭环神经驾驶中验证。
核心要点
- 动机是为嵌入式神经驾驶研究提供低成本、可复现实验平台。
- 采用感知-决策-执行硬件分区：相机经Wi-Fi传帧，主机推理，底盘控制器执行安全关键控制。
- 真实闭环测试中，无线感知主导延迟；12次自主会话零碰撞、零人工接管。
- 编码器-IMU融合将里程计回环误差降低22%，平台软件已开源。
验证范围与局限：验证范围为真实闭环神经驾驶中的十二次自主会话。
英文摘要 (Abstract)
We present a low-cost miniature Ackermann vehicle for embedded neural-driving research, organized as a hardware-partitioned perceive-decide-act agent: an ESP32 camera node streams frames over Wi-Fi to a host computer, where neural inference and state estimation run, while an ESP32-S3 chassis controller executes safety-critical actuation in a 100 Hz per-wheel proportional-integral-derivative (PID) loop beneath a micro-ROS client. The partition isolates real-time control and safety on the vehicle while learning-based components run off-board, supervised by an operator from a gamepad. We characterize the complete pipeline during real closed-loop neural driving. Wireless sensing, rather than neural inference, dominates latency, with a 59.5 ms median capture-to-actuation delay; the platform absorbed wireless variability by holding the last safe command under a firmware watchdog, operating across twelve autonomous sessions with zero collisions or manual interventions; and encoder-inertial-measurement-unit (IMU) fusion cut odometry loop-closure error by 22%. These results indicate that carefully partitioned microcontroller-class vehicles support reproducible experiments in embedded AI, wireless control, and operator-supervised autonomous driving. The platform software is open source.
作者：Gustavo Cláudio Karl Couto, Eric Aislan Antonelo, Gabriel George Zipperer
来源
本页事实对应的公开页面，以原文为准。