# Data-Driven Hierarchical Predictive Learning in Unknown Environments

arXiv: https://arxiv.org/abs/2005.05948 · HTML: https://mlsanity.com/paper/2005.05948/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 May 2020.

## Built on by (most cited first, 2 of 2)

- [AI Autonomy : Self-Initiated Open-World Continual Learning and Adaptation](https://mlsanity.com/paper/2203.08994/) (2022)
- [A Risk-Averse Preview-based Q-Learning Algorithm: Application to Highway Driving of Autonomous Vehicles](https://mlsanity.com/paper/2112.03232/) (2021)

## Abstract (arXiv)

We propose a hierarchical learning architecture for predictive control in unknown environments. We consider a constrained nonlinear dynamical system and assume the availability of state-input trajectories solving control tasks in different environments. A parameterized environment model generates state constraints specific to each task, which are satisfied by the stored trajectories. Our goal is to find a feasible trajectory for a new task in an unknown environment. From stored data, we learn strategies in the form of target sets in a reduced-order state space. These strategies are applied to the new task in real-time using a local forecast of the new environment, and the resulting output is used as a terminal region by a low-level receding horizon controller. We show how to i) design the target sets from past data and then ii) incorporate them into a model predictive control scheme with shifting horizon that ensures safety of the closed-loop system when performing the new task. We prove the feasibility of the resulting control policy, and verify the proposed method in a robotic path planning application.