Dual Control Reference Generation for Optimal Pick-and-Place Execution under Payload Uncertainty

2025-10-23

AI Summary

For robotic pick-and-place tasks under unknown load dynamics, this paper proposes a dual-control trajectory planning method integrating active exploration with online parameter adaptation. The approach jointly minimizes task cost and parameter identifiability loss within a unified optimization framework, implicitly leveraging Fisher information to enhance learning efficiency. By synthesizing robust optimal control, dual-control principles, and explicit adaptive feedback, it concurrently performs trajectory planning and parametric sensitivity analysis. Experimental results demonstrate that the method ensures closed-loop stability while significantly accelerating parameter convergence, improving pick-and-place accuracy and robustness, and effectively mitigating modeling uncertainties in dynamic, unknown environments.

Technology Category

• Intelligent Robots: Learning & Optimization for ROB
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This work addresses the problem of robot manipulation tasks under unknown dynamics, such as pick-and-place tasks under payload uncertainty, where active exploration and(/for) online parameter adaptation during task execution are essential to enable accurate model-based control. The problem is framed as dual control seeking a closed-loop optimal control problem that accounts for parameter uncertainty. We simplify the dual control problem by pre-defining the structure of the feedback policy to include an explicit adaptation mechanism. Then we propose two methods for reference trajectory generation. The first directly embeds parameter uncertainty in robust optimal control methods that minimize the expected task cost. The second method considers minimizing the so-called optimality loss, which measures the sensitivity of parameter-relevant information with respect to task performance. We observe that both approaches reason over the Fisher information as a natural side effect of their formulations, simultaneously pursuing optimal task execution. We demonstrate the effectiveness of our approaches for a pick-and-place manipulation task. We show that designing the reference trajectories whilst taking into account the control enables faster and more accurate task performance and system identification while ensuring stable and efficient control.

Problem

• Robot manipulation under unknown payload dynamics
• Dual control for active exploration and adaptation
• Optimal trajectory generation under parameter uncertainty

Innovation

• Uses dual control with explicit adaptation mechanism
• Embeds parameter uncertainty in robust optimal control
• Minimizes optimality loss using Fisher information