Learning to control from expert demonstrations
Not on the map. Why?
Abstract (arXiv)
In this paper, we revisit the problem of learning a stabilizing controller from a finite number of demonstrations by an expert. By first focusing on feedback linearizable systems, we show how to combine expert demonstrations into a stabilizing controller, provided that demonstrations are sufficiently long and there are at least n+1 of them, where n is the number of states of the system being controlled. When we have more than n+1 demonstrations, we discuss how to optimally choose the best n+1 demonstrations to construct the stabilizing controller. We then extend these results to a class of systems that can be embedded into a higher-dimensional system containing a chain of integrators. The feasibility of the proposed algorithm is demonstrated by applying it on a CrazyFlie 2.0 quadrotor.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 9 of its 49 references that are in the map. First posted on arXiv 9 Mar 2022.
Builds on
9 of 49 references.
References · 9
- 2021Convex optimizationcited by 2,515
- 2016End to End Learning for Self-Driving Carscited by 1,009
- 2017End-to-end Driving via Conditional Imitation Learningcited by 485
- 2019Learning by Cheatingcited by 383
- 2019A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithmscited by 142
- 2020Deep Drone Acrobaticscited by 75
- 2021On Imitation Learning of Linear Control Policies: Enforcing Stability and Robustness Constraints via LMI Conditionscited by 10
- 2020Fitting a Linear Control Policy to Demonstrations with a Kalman Constraintcited by 9
- 2020Data-driven Stabilization of SISO Feedback Linearizable Systemscited by 3
Built on by
Not cited yet.