Learning-informed motion planning toward workspace goal regions for object manipulation in constrained environments

Duman, Furkan, Patino Minan, Jose, Romero Cano, Victor ORCID: https://orcid.org/0000-0003-2910-5116 and Hernandez, Juan David ORCID: https://orcid.org/0000-0002-9593-6789 2026. Learning-informed motion planning toward workspace goal regions for object manipulation in constrained environments. Presented at: IEEE International Conference on Automation Science and Engineering (CASE 2026), Shenyang, China, August 2026. Item availability restricted.

	PDF - Accepted Post-Print Version Restricted to Repository staff only Download (1MB)
	PDF (Provisional file) - Accepted Post-Print Version Download (17kB)

Abstract

Motion planning for a pick-and-place task can be formulated as start-to-goal-region problems, in which the multiple grasp and place poses that are valid to complete the task can be represented as workspace goal regions. However, when objects must be manipulated in constrained environments such as shelves, the planner may struggle to rapidly find a path to any of the available goal regions while navigating the complex robot configuration space. Motivated by this challenge, we propose a learning-informed sampling-based tree planner, which increases planning efficiency and the likelihood of finding feasible solutions to such start-to-goal-region problems. Our proposed planner leverages a transformer model to generate configuration samples, which are conditioned on the start configuration, goal configurations, and visual observations of the environment. Such generated configurations are used to help guide the expansion of a sampling-based tree planner, while also maintaining stochastic behavior. We evaluate our planner in both simulated and real-world scenarios of increasing complexity, including shelf environments with a 7-DoF Franka Emika robot. Across all settings, the proposed approach improves planning efficiency while maintaining or increasing success rates. In the most challenging scenarios, our proposed approach increases success rates by over 20% and reduces average planning time by more than a factor of two compared to a goal-region–aware sampling-based tree planner baseline. We also demonstrate effective generalization from simulation to real-world execution.

Item Type:	Conference or Workshop Item - published (Paper)
Status:	In Press
Schools:	Schools > Computer Science & Informatics
Date of First Compliant Deposit:	15 June 2026
Date of Acceptance:	27 May 2026
Last Modified:	04 Aug 2026 22:46
URI:	https://orca.cardiff.ac.uk/id/eprint/187553

Actions (repository staff only)

Edit Item