End-to-End Velocity Estimation For Autonomous Racing

03/15/2020
by   Sirish Srinivasan, et al.
0

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.

READ FULL TEXT

page 1

page 3

research
08/31/2018

Estimation for Quadrotors

This document describes standard approaches for filtering and estimation...
research
09/29/2022

Fully Proprioceptive Slip-Velocity-Aware State Estimation for Mobile Robots via Invariant Kalman Filtering and Disturbance Observer

This paper develops a novel slip estimator using the invariant observer ...
research
07/21/2020

INS/Odometer Land Navigation by Accurate Measurement Modeling and Multiple-Model Adaptive Estimation

Land vehicle navigation based on inertial navigation system (INS) and od...
research
09/26/2018

Redundant Perception and State Estimation for Reliable Autonomous Racing

In autonomous racing, vehicles operate close to the limits of handling a...
research
07/06/2020

TLIO: Tight Learned Inertial Odometry

In this work we propose a tightly-coupled Extended Kalman Filter framewo...
research
03/17/2023

Experimental verification of an online traction parameter identification method

Traction parameters, that characterize the ground-wheel contact dynamics...
research
04/12/2019

AI-IMU Dead-Reckoning

In this paper we propose a novel accurate method for dead-reckoning of w...

Please sign up or login with your details

Forgot password? Click here to reset