# Reinforcement Learning for Docking Maneuvers with Prescribed Performance

arXiv: https://arxiv.org/abs/2402.08306 · HTML: https://mlsanity.com/paper/2402.08306/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods.
- Builds on 12 of its 24 references that are in the map.
- First posted on arXiv 13 Feb 2024.

## Placed in

- Deep reinforcement learning methods / [RL for robot navigation and UAV control](https://mlsanity.com/deeprl/rl-for-robot-navigation-and-uav-control/)

## Builds on (most cited first, 12 of 12)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Funnel-based Reward Shaping for Signal Temporal Logic Tasks in Reinforcement Learning](https://mlsanity.com/paper/2212.03181/) (2022)
- [Funnel Control Under Hard and Soft Output Constraints (extended version)](https://mlsanity.com/paper/2208.02006/) (2022)
- [Optimal Rendezvous Path Planning to an Uncontrolled Tumbling Target](https://mlsanity.com/paper/1307.1327/) (2013)
- [Funnel control of nonlinear systems](https://mlsanity.com/paper/2007.10123/) (2020)
- [Tracking control for underactuated non-minimum phase multibody systems](https://mlsanity.com/paper/2010.01010/) (2020)
- [Robust Funnel Model Predictive Control for output tracking with prescribed performance](https://mlsanity.com/paper/2302.01754/) (2023)
- [Sampled-data funnel control and its use for safe continual learning](https://mlsanity.com/paper/2303.00523/) (2023)
- [Safe continual learning in model predictive control with prescribed bounds on the tracking error](https://mlsanity.com/paper/2304.10910/) (2023)
- [Experimental validation for the combination of funnel control with a feedforward control strategy](https://mlsanity.com/paper/2312.04380/) (2023)
- [Safe data-driven reference tracking with prescribed performance](https://mlsanity.com/paper/2312.08734/) (2023)

## Abstract (arXiv)

We propose a two-component data-driven controller to safely perform docking maneuvers for satellites. Reinforcement Learning is used to deduce an optimal control policy based on measurement data. To safeguard the learning phase, an additional feedback law is implemented in the control unit, which guarantees the evolution of the system within predefined performance bounds. We define safe and safety-critical areas to train the feedback controller based on actual measurements. To avoid chattering, a dwell-time activation scheme is implemented. We provide numerical evidence for the performance of the proposed controller for a satellite docking maneuver with collision avoidance.