End-to-End Velocity Estimation for Autonomous Racing
- 14 August 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 5 (4) , 6869-6875
Abstract
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 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.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Redundant Perception and State Estimation for Reliable Autonomous Racing2019
- Neural network vehicle models for high-performance automated drivingScience Robotics, 2019
- Vision-Based High-Speed Driving With a Deep Dynamic ObserverIEEE Robotics and Automation Letters, 2019
- Differentiable Particle Filters: End-to-End Learning with Algorithmic Priors2018
- Design of an Autonomous Racecar: Perception, State Estimation and System Integration2018
- Vehicle dynamic state estimation: state of the art schemes and perspectivesIEEE/CAA Journal of Automatica Sinica, 2018
- Deep learning helicopter dynamics models2015
- A comparison of several nonlinear filters for mobile robot pose estimation2013
- A study on lateral speed estimation methodsInternational Journal of Vehicle Autonomous Systems, 2004
- Long Short-Term MemoryNeural Computation, 1997