Reinforcement Learning-Based Neuroadaptive Control of Robotic Manipulators under Deferred Constraints

2025-03-18

AI Summary

This paper addresses the adaptive control problem of robotic manipulators subject to communication/computation delays and initial constraint violations. We propose a safety-critical control framework integrating neural adaptive control with model-free reinforcement learning. Methodologically, we introduce a novel smooth progressive constraint activation mechanism coupled with a prescribed-time offset function, and synergistically combine barrier Lyapunov functions with an Actor-Critic architecture to enable online policy learning and real-time safety enforcement without precise system modeling. Theoretical analysis guarantees uniform boundedness of all closed-loop signals. Simulation results demonstrate rapid, safe convergence even under initial constraint violation, along with a 23.6% reduction in steady-state energy consumption. The core contribution lies in establishing a new robust adaptive control paradigm that simultaneously ensures delay-aware constraint satisfaction, initial safety recovery, and energy efficiency.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Natural Language Processing: Safety and Robustness
• Multiagent Systems: Adversarial Agents

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This paper presents a reinforcement learning-based neuroadaptive control framework for robotic manipulators operating under deferred constraints. The proposed approach improves traditional barrier Lyapunov functions by introducing a smooth constraint enforcement mechanism that offers two key advantages: (i) it minimizes control effort in unconstrained regions and progressively increases it near constraints, improving energy efficiency, and (ii) it enables gradual constraint activation through a prescribed-time shifting function, allowing safe operation even when initial conditions violate constraints. To address system uncertainties and improve adaptability, an actor-critic reinforcement learning framework is employed. The critic network estimates the value function, while the actor network learns an optimal control policy in real time, enabling adaptive constraint handling without requiring explicit system modeling. Lyapunov-based stability analysis guarantees the boundedness of all closed-loop signals. The effectiveness of the proposed method is validated through numerical simulations.

Problem

• Develops neuroadaptive control for robotic manipulators under deferred constraints.
• Enhances energy efficiency and safety via smooth constraint enforcement.
• Uses reinforcement learning for real-time adaptive control without system modeling.

Innovation

• Reinforcement learning-based neuroadaptive control framework
• Smooth constraint enforcement with energy efficiency
• Actor-critic framework for real-time adaptive control