Ken Goldberg in WAFR 2020 Proceedings
BCNM faculty Ken Goldberg was recently featured in the International Workshop on the Algorithmic Foundations of Robotics (WAFR) 2020 Proceedings. His article, titled "ABC-LMPC: Safe Sample-Based Learning MPC for Stochastic Nonlinear Dynamical Systems with Adjustable Boundary Conditions" was discussed during the conference and included in a journal on the 2020 WAFR Proceedings.
From the article abstract:
We present a novel LMPC algorithm, Adjustable Boundary Condition LMPC (ABC-LMPC), which enables rapid adaptation to novel start and goal configurations and theoretically show that the resulting controller guarantees iterative improvement in expectation for stochastic nonlinear systems. We present results with a practical instantiation of this algorithm and experimentally demonstrate that the resulting controller adapts to a variety of initial and terminal conditions on 3 stochastic continuous control tasks.
Read about Goldberg's work here, and check out his conference presentation in video format here and below!