# Combining Planning, Reasoning and Reinforcement Learning to solve Industrial Robot Tasks

arXiv: https://arxiv.org/abs/2212.03570 · HTML: https://mlsanity.com/paper/2212.03570/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2022.

## Built on by (most cited first, 4 of 4)

- [SkiROS2: A skill-based Robot Control Platform for ROS](https://mlsanity.com/paper/2306.17030/) (2023)
- [Using Knowledge Representation and Task Planning for Robot-agnostic Skills on the Example of Contact-Rich Wiping Tasks](https://mlsanity.com/paper/2308.14206/) (2023)
- [Adaptable Recovery Behaviors in Robotics: A Behavior Trees and Motion Generators(BTMG) Approach for Failure Management](https://mlsanity.com/paper/2404.06129/) (2024)
- [Neurosymbolic Reasoning with Incremental Knowledge for Sample Efficient Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2608.02993/) (2026)

## Abstract (arXiv)

One of today's goals for industrial robot systems is to allow fast and easy provisioning for new tasks. Skill-based systems that use planning and knowledge representation have long been one possible answer to this. However, especially with contact-rich robot tasks that need careful parameter settings, such reasoning techniques can fall short if the required knowledge not adequately modeled. We show an approach that provides a combination of task-level planning and reasoning with targeted learning of skill parameters for a task at hand. Starting from a task goal formulated in PDDL, the learnable parameters in the plan are identified and an operator can choose reward functions and parameters for the learning process. A tight integration with a knowledge framework allows to form a prior for learning and the usage of multi-objective Bayesian optimization eases to balance aspects such as safety and task performance that can often affect each other. We demonstrate the efficacy and versatility of our approach by learning skill parameters for two different contact-rich tasks and show their successful execution on a real 7-DOF KUKA-iiwa.