# Learn Fast, Forget Slow: Safe Predictive Learning Control for Systems with Unknown and Changing Dynamics Performing Repetitive Tasks

arXiv: https://arxiv.org/abs/1810.06681 · HTML: https://mlsanity.com/paper/1810.06681/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Oct 2018.

## Built on by (most cited first, 8 of 8)

- [Contraction Theory for Nonlinear Stability Analysis and Learning-based Control: A Tutorial Overview](https://mlsanity.com/paper/2110.00675/) (2021)
- [VINet: Visual and Inertial-based Terrain Classification and Adaptive Navigation over Unknown Terrain](https://mlsanity.com/paper/2209.07725/) (2022)
- [HYPERmotion: Learning Hybrid Behavior Planning for Autonomous Loco-manipulation](https://mlsanity.com/paper/2406.14655/) (2024)
- [Bridging the Model-Reality Gap with Lipschitz Network Adaptation](https://mlsanity.com/paper/2112.03756/) (2021)
- [Online Residual Learning from Offline Experts for Pedestrian Tracking](https://mlsanity.com/paper/2409.04069/) (2024)
- [Discrete fully probabilistic design: towards a control pipeline for the synthesis of policies from examples](https://mlsanity.com/paper/2112.11210/) (2021)
- [Improving the Region of Attraction of a Multi-rotor UAV by Estimating Unknown Disturbances](https://mlsanity.com/paper/2409.00257/) (2024)
- [Guiding Reinforcement Learning with Incomplete System Dynamics](https://mlsanity.com/paper/2410.16821/) (2024)

## Abstract (arXiv)

We present a control method for improved repetitive path following for a ground vehicle that is geared towards long-term operation where the operating conditions can change over time and are initially unknown. We use weighted Bayesian Linear Regression (wBLR) to model the unknown dynamics, and show how this simple model is more accurate in both its estimate of the mean behaviour and model uncertainty than Gaussian Process Regression and generalizes to novel operating conditions with little or no tuning. In addition, wBLR allows us to use fast adaptation and long-term learning in one, unified framework, to adapt quickly to new operating conditions and learn repetitive model errors over time. This comes with the added benefit of lower computational cost, longer look-ahead, and easier optimization when the model is used in a stochastic Model Predictive Controller (MPC). In order to fully capitalize on the long prediction horizons that are possible with this new approach, we use Tube MPC to reduce the growth of predicted uncertainty. We demonstrate the effectiveness of our approach in experiment on a 900,kg ground robot showing results over 3.0,km of driving with both physical and artificial changes to the robot's dynamics. All of our experiments are conducted using a stereo camera for localization.