no code implementations • 11 Nov 2020 • Dilusha Weeraddana, Nguyen Lu Dang Khoa, Lachlan O Neil, Weihong Wang, Chen Cai
Given these considerations, we construct a stacked GP method where the predictive posteriors of each GP applied to each task are used in the prior and likelihood of the next level GP.
no code implementations • 15 Apr 2019 • Chen Liang, Weihong Wang, Zhenghua Liu, Chao Lai, Benchun Zhou
However the traditional MPPI framework assumes the actual environment similar to the training dataset for the deep neural network which is impractical in practice with different maneuvering of target, other perturbations and actuator failures.
Robotics Systems and Control