Optimal control and inverse optimal control by distribution matching

Arenz, O. and Abdulsamad, H. and Neumann, G. (2016) Optimal control and inverse optimal control by distribution matching. In: Intelligent Robots and Systems (IROS), 2016 IEEE/RSJ International Conference on, 9 - 14 October 2016, Daejeon, Korea.

07759596.pdf - Whole Document

Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive


Optimal control is a powerful approach to achieve optimal behavior. However, it typically requires a manual specification of a cost function which often contains several objectives, such as reaching goal positions at different time steps or energy efficiency. Manually trading-off these objectives is often difficult and requires a high engineering effort. In this paper, we present a new approach to specify optimal behavior. We directly specify the desired behavior by a distribution over future states or features of the states. For example, the experimenter could choose to reach certain mean positions with given accuracy/variance at specified time steps. Our approach also unifies optimal control and inverse optimal control in one framework. Given a desired state distribution, we estimate a cost function such that the optimal controller matches the desired distribution. If the desired distribution is estimated from expert demonstrations, our approach performs inverse optimal control. We evaluate our approach on several optimal and inverse optimal control tasks on non-linear systems using incremental linearizations similar to differential dynamic programming approaches.

Keywords:Optimal Control, Inverse Optimal Control, Robotics
Subjects:H Engineering > H660 Control Systems
H Engineering > H671 Robotics
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:25737
Deposited On:02 Feb 2017 16:20

Repository Staff Only: item control page