Sample-efficient low-level motion planning for robotic manipulation tasks via zero-shot transfer learning

He, Yuanzhi ORCID: https://orcid.org/0009-0007-8424-2654, Romero Cano, Victor ORCID: https://orcid.org/0000-0003-2910-5116, Patino Minan, Jose, Hernandez, Juan David ORCID: https://orcid.org/0000-0002-9593-6789, Sawtell, William and Colombo, Gualtiero 2026. Sample-efficient low-level motion planning for robotic manipulation tasks via zero-shot transfer learning. Presented at: International Conference on Artificial Neural Networks (ICANN), Padua, Italy, September 14-17 2026. Lecture Notes on Artificial Intelligence (LNAI). Springer Nature, Item availability restricted.

	PDF - Accepted Post-Print Version Restricted to Repository staff only Download (3MB) | Request a copy
	PDF (Provisional file) - Accepted Post-Print Version Download (17kB)

Abstract

As robotic systems become more sophisticated, the grow- ing complexity of their motion planning models and the longer training times pose substantial challenges. Evolutionary algorithms such as the Sample-efficient Cross-Entropy Method (iCEM) have recently demon- strated promising potential for low-level real-time planning by leveraging efficientknowledgereusestrategiestoimproveperformance.Althoughef- fective in many control tasks, iCEM’s performance can be constrained in more complex scenarios, particularly those requiring stacking, sliding, and shelf placement. In this work, we propose a novel iCEM+TL frame- work that explicitly leverages Transfer Learning (TL), where key iCEM parameters are transferred from simpler upstream tasks to guide more complex downstream tasks. Additionally, we applied Reward Redesign (RR) through task decomposition for stacking objects and shelf place- ment to optimize task-specific performance. Results from the simulation show that our framework achieves success rate improvements of up to 23%. The framework is further validated on a real Franka Emika robot in a stacking task, demonstrating its practical feasibility for real-world deployment.

Item Type:	Conference or Workshop Item - published (Paper)
Status:	In Press
Schools:	Schools > Computer Science & Informatics
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Uncontrolled Keywords:	EvolutionaryAlgorithm, MotionPlanning, Transfer Learning
Publisher:	Springer Nature
Date of First Compliant Deposit:	10 June 2026
Date of Acceptance:	29 May 2026
Last Modified:	04 Aug 2026 22:18
URI:	https://orca.cardiff.ac.uk/id/eprint/187517

Actions (repository staff only)

Edit Item