End-to-End Velocity Estimation For Autonomous Racing
This addresses the problem of costly velocity sensors for autonomous racing vehicles, offering a more affordable solution with competitive performance in high-slip conditions, though it is incremental as it builds on existing sensor fusion methods.
The paper tackles velocity estimation for autonomous race cars in extreme scenarios with high sideslip and slip ratios, presenting an end-to-end recurrent neural network that uses raw sensors (IMU, wheel odometry, motor currents) to achieve lateral velocity estimates up to 15x better than a Kalman filter without expensive sensors and matches one with such sensors at 0.06 m/s RMSE.
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.