Vision-Aided IMU Estimation of Attitude and Orientation for a Driverless Car
Estimation of attitude and orientation is a critically important technique for ground wheeled autonomous robots like driverless cars. By means of attitude estimation, robots can not only evaluate the risk of overturning the vehicle, but also correct many sensor errors caused by robot motion or vibration. Traditionally, odometry (wheel encoders) is widely used to provide speed information for localization in dead-reckoning systems, and GPS fulfills the same role when robots navigate in outdoor environments. Visual odometry determines the position and orientation of a vehicle based on analyzing a sequence of images only.
KeywordsAutonomous Robot Drift Correction Visual Odometry Mobile Robot Navigation Short Term Precision
- 1.Horn, B.K.P.: Robot Vision. MIT electrical engineering and computer science series. The MIT Press (1986)Google Scholar
- 2.Lou, L., Neal, M., Labrosse, F., Cao, J.: An Approach to Improving Attitude Estimation Based on Low-Cost MEMS-IMU for Mobile Robot Navigation. In: Groß, R., Alboul, L., Melhuish, C., Witkowski, M., Prescott, T.J., Penders, J. (eds.) TAROS 2011. LNCS, vol. 6856, pp. 378–379. Springer, Heidelberg (2011)CrossRefGoogle Scholar