arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.06917cs.ROcs.LG
收藏

自动驾驶赛车的端到端速度估计

End-to-End Velocity Estimation For Autonomous Racing

Autonomous Systems Lab, ETH Zürich(苏黎世联邦理工学院自主系统实验室);Robotics and Autonomous Systems Group, CSIRO(澳大利亚联邦科学与工业研究组织机器人与自主系统组);Sevensense Robotics A.G(Sevensense Robotics 股份公司)

Sirish Srinivasan, Inkyu Sa, Alex Zyner, Victor Reijgwart, Miguel I. Valls, Roland Siegwart

摘要:

速度估计在无人驾驶汽车中起着核心作用,但标准和负担得起的方法难以应对极端情况,如由于存在高侧滑而导致的激进机动。为了解决这个问题,自动驾驶赛车通常配备昂贵的外部速度传感器。在本文中,我们提出了一个端到端的递归神经网络,该网络将可用的原始传感器作为输入(IMU,车轮里程计和电机电流)并输出速度估计。两个国家的最先进的卡尔曼滤波器,分别包括和排除昂贵的速度传感器的结果进行比较。所有方法都在一辆方程式学生无人驾驶赛车上进行了广泛的测试,该赛车具有非常高的侧滑(后轴10°)和滑移率(~20%),接近操纵极限。建议的网络是能够估计横向速度高达15倍,优于卡尔曼滤波器与等效的传感器输入和匹配(0.06 m/s RMSE)的卡尔曼滤波器与昂贵的速度传感器设置。

英文摘要:

Velocity estimation plays a central role in driverless vehicles, but standard and affordable methods struggle to cope with extreme scenarios like aggressive maneuvers due to the presence of high sideslip. To solve this, autonomous race cars are usually equipped with expensive external velocity sensors. In this paper, we present an end-to-end recurrent neural network that takes available raw sensors as input (IMU, wheel odometry, and motor currents) and outputs velocity estimates. The results are compared to two state-of-the-art Kalman filters, which respectively include and exclude expensive velocity sensors. All methods have been extensively tested on a formula student driverless race car with very high sideslip (10° at the rear axle) and slip ratio (~20%), operating close to the limits of handling. The proposed network is able to estimate lateral velocity up to 15x better than the Kalman filter with the equivalent sensor input and matches (0.06 m/s RMSE) the Kalman filter with the expensive velocity sensor setup.

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。

↑