A Factor-Graph-Based Approach to Vehicle Sideslip Angle Estimation

Abstract

Sideslip angle is an important variable for understanding and monitoring vehicle dynamics, but there is currently no inexpensive method for its direct measurement. Therefore, it is typically estimated from proprioceptive sensors onboard using filtering methods from the family of the Kalman filter. As a novel alternative, this work proposes modeling the problem directly as a graphical model (factor graph), which can then be optimized using a variety of methods, such as whole-dataset batch optimization for offline processing or fixed-lag smoothing for on-line operation. Experimental results on real vehicle datasets validate the proposal, demonstrating a good agreement between estimated and actual sideslip angle, showing similar performance to state-of-the-art methods but with a greater potential for future extensions due to the more flexible mathematical framework. An open-source implementation of the proposed framework has been made available online.

Robust and Sample-Efficient Estimation of Vehicle Lateral Velocity Using Neural Networks With Explainable Structure Informed by Kinematic Principles

“…• Being a linear parameter varying model, it can be implemented easily with automotive-grade hardware. The study evaluates 28 variants of our specialized model in 4 groups, 10 variants of benchmark general-purpose recurrent neural networks in 2 groups (GRU and LSTM, from [9] and [10]), the benchmark Luenberger kinematic observer [11], and the benchmarks factor graph and Kalman filter [12].…”

“…Linear, nonlinear, and sliding mode observers were compared in [17], using dynamic vehicle models restricted to moderate accelerations. The authors of [12] presented a factor graph approach based on a vehicle dynamic model.…”

Adaptive Lag Smoother for State Estimation

“…Fixed-lag smoothers have been used for identifying time-varying process models based on input–output observations [ 13 ], vehicle side slip angle estimation [ 14 ], gravity anomaly estimation [ 15 , 16 ] and pre-processing of geophysical data [ 17 ]. The fixed lag smoothers marginalize the old data in the localization pipeline for fusing information from different sensors such as inertial sensors, visual camera [ 18 ], ultra-wide band location systems [ 19 ], indoor localization using multiple sensors [ 20 ], visible light positioning using a photodiode and camera [ 21 ] and target tracking in a wireless network environment [ 22 ].…”

Editorial of Special Issue “Combining Sensors and Multibody Models for Applications in Vehicles, Machines, Robots and Humans”

“…The ninth work [ 9 ] intends to estimate the sideslip angle in road vehicles, and proposes an alternative to traditional methods of state estimation by representing the problem as a probabilistic graphical model which can be optimized by several methods.…”

“…In summary, it can be seen that the papers gathered in the Special Issue contributed either by proposing solutions to the general problem of state, input and/or parameter estimation [ 4 , 5 , 7 , 8 , 9 ], and/or by suggesting applications of the combined use of sensors and multibody models to different fields, such as automotive [ 6 , 8 , 9 ], railway [ 2 ], naval [ 5 ], spatial [ 10 ], machinery [ 4 , 7 ], robotics [ 3 ], biomechanics [ 1 ] and music [ 6 ] applications, thus showing the theoretical challenges and practical interest of this research topic.…”