Learning Stack-of-Tasks Management for Redundant Robots

TL;DR

This paper introduces an automated framework for learning complete Stack-of-Tasks controllers for redundant robots, optimizing task hierarchies and parameters from user preferences using genetic programming and simulation.

Contribution

It presents a novel method that automatically learns hierarchical control structures for robots, replacing manual tuning with an optimization approach based on user-defined cost functions.

Findings

Controllers transfer seamlessly from simulation to real robots

The method achieves robust obstacle avoidance and high tracking accuracy

Learned hierarchies resemble expert-designed task structures

Abstract

This paper presents a novel framework for automatically learning complete Stack-of-Tasks (SoT) controllers for redundant robotic systems, including task priorities, activation logic, and control parameters. Unlike classical SoT pipelines-where task hierarchies are manually defined and tuned-our approach optimizes the full SoT structure directly from a user-specified cost function encoding intuitive preferences such as safety, precision, manipulability, or execution speed. The method combines Genetic Programming with simulation-based evaluation to explore both discrete (priority order, task activation) and continuous (gains, trajectory durations) components of the controller. We validate the framework on a dual-arm mobile manipulator (the ABB mobile-YuMi research platform), demonstrating robust convergence across multiple cost definitions, automatic suppression of irrelevant tasks, and strong resilience to distractors. Learned SoTs exhibit expert-like hierarchical structure and adapt naturally to multi-objective trade-offs. Crucially, all controllers transfer from Gazebo simulation to the real robot, achieving safe and precise motion without additional tuning. Experiments in static and dynamic environments show reliable obstacle avoidance, high tracking accuracy, and predictable behavior in the presence of humans. The proposed method provides an interpretable and scalable alternative to manual SoT design, enabling rapid, user-driven generation of task execution hierarchies for complex robotic systems.