Trajectory Generation by Chance-Constrained Nonlinear MPC With Probabilistic Prediction

Continued great efforts have been dedicated toward high-quality trajectory generation based on optimization methods; however, most of them do not suitably and effectively consider the situation with moving obstacles; more particularly, future position these obstacles in presence uncertainty within some possible prescribed prediction horizon. To cater to this rather major shortcoming, work shows how a variational Bayesian Gaussian mixture model (vBGMM) framework can be employed predict then methodology, is proposed which will efficiently address obstacles, incorporate In work, full predictive conditional probability density function (PDF) mean covariance obtained and, thus, formulated as collision region represented by confidence ellipsoid. avoid region, chance constraints are imposed restrict probability, subsequently, nonlinear control problem constructed constraints. It shown that approach able effectively; environmental information probabilistic prediction, it also timing avoidance earlier than method without prediction. The tracking error distance smaller compared