Neural Adaptive Admittance Control With Guaranteed Performance for Physical Human–Robot Interaction

AI-Enabled Force and Torque Control for Human Robot Interaction

Safe and intuitive human robot interaction (HRI) requires precise regulation of contact forces and torques while adapting to dynamic and uncertain human behavior. Traditional impedance and admittance control strategies rely on fixed parameters and accurate system modeling, which often limit their performance in unstructured or collaborative environments. This paper presents an AI-enabled force and torque control framework that integrates machine learning techniques with conventional control methods to enhance adaptability, compliance, and safety in physical human robot interaction. The proposed approach employs deep neural networks and reinforcement learning to learn human intent and interaction dynamics directly from multi-modal sensor data, including force torque sensors, joint encoders, and inertial measurements. By continuously adjusting control gains in real time, the system achieves stable interaction while minimizing excessive contact forces and undesired torques. Experimental evaluations conducted on a collaborative robotic platform demonstrate significant improvements over classical control schemes, including reduced interaction force peaks, smoother torque profiles, and improved task execution efficiency during cooperative manipulation tasks. The results indicate that AI-driven force and torque control can substantially improve robustness, adaptability, and user comfort in human robot collaboration, making it a promising solution for applications in rehabilitation robotics, assistive devices, and industrial cobots.

Adaptive Energy-Based Robot Control for Physical Human-Robot Interaction: A Less Conservative Approach

Passivity-based control theory has emerged as a promising framework for physical human-robot interaction by explicitly enforcing the energetically passive relation. However, maintaining passivity at all times may overly limit the task execution capability of the robot, potentially increasing human physical workload. Furthermore, interaction safety can be violated in conventional passivity-based control approaches due to ignoring stored energy level and energy rate constraints. In this paper, an adaptive energy-based robot control is proposed for physical human-robot interaction by extending the passivitybased control and integrating additional safety constraints. Specifically, this method alleviates the inherent conservatism of conventional passivity-based control by ensuring passivity in the closed-loop system only when the system's energy exceeds a predefined threshold, while allowing more flexible behaviors otherwise. Additionally, adaptive control parameter laws, stored energy level saturation, and energy rate constraints are integrated into the control method to enhance task performance and safe interaction. Numerical simulation and human-in-the-loop co-carrying experiment are conducted to validate the feasibility and effectiveness of the proposed approach.

Mode-selective adaptive admittance force-position control for safe robotic interaction in unknown time-varying environments.

With the increasing complexity of robotic interaction tasks, robotic manipulators are required to safely interact with unknown and time-varying environments while maintaining accurate trajectory tracking. Such tasks involve frequent switching between free-motion and contact-motion phases, uncertain environmental parameters, and transient impact-induced force oscillations. To address these issues, this paper proposes a mode-selective adaptive admittance force-position control framework in task space. First, an activation matrix is introduced to select the force-controlled and position-controlled subspaces according to contact and tracking conditions. Second, an environment-aware adaptive admittance outer loop is developed by integrating Gaussian Process Regression-enhanced Extended Kalman Filter (GPR-EKF) estimation, Lyapunov-based parameter adaptation, and radial basis function neural network (RBFNN) compensation. Third, a mode-gated self-tuning PID inner loop is employed to improve trajectory tracking accuracy under different interaction modes. Simulation and experimental results demonstrate that the proposed method can reduce force overshoot, improve steady-state force tracking accuracy, and enhance safe interaction in unknown time-varying environments.

Adaptive SMC for Lower Limb Rehabilitation Robots Using a Sliding Mode Hyperbolic ESO

Adaptive Motion Intention Estimation and Impedance Learning for Human–Robot Interaction

This paper proposes a safe and effective human–robot physical interaction control framework for exoskeleton robots that enhances system compliance and safety while enabling the robot to adapt to human motion. The framework is designed around two primary objectives: first, a model-free adaptive control method is employed for reference trajectory estimation to achieve real-time estimation of human motion intention; second, the Forgetting Factor Recursive Least Squares (FFRLS) method is utilized for online estimation and the learning of human impedance parameters, considering their time-varying nature. In addition, a model-free adaptive trajectory tracking control strategy is proposed to optimize control performance during human–robot physical interaction. Simulation results demonstrate that the proposed control framework outperforms conventional methods significantly in terms of safety and compliance.

Contact-responsive high-gain robot motion controllers using a constrained disturbance observer

High-gain robot controllers are well known for their robustness against unknown disturbances, ensuring high control accuracy. However, this robustness makes handling unexpected contacts challenging, particularly in the absence of joint torque sensors (JTSs). This paper presents a contact-responsive high-gain motion controller (CRMC) that ensures accurate tracking in free motion while adapting to unknown interactions, even without joint torque sensing. To achieve CRMC, we propose a constrained disturbance observer (CDOB), an extension of the DOB framework designed to optimize the nominal robot’s motion. The real robot follows this optimized motion using an inner-loop high-gain disturbance compensator that reduces the deviation between the nominal and real robot motions. The optimization of CDOB allows the user to impose various motion constraints, enabling contact-responsive behavior and broader task-specific designs. The proposed method is subjected to rigorous stability analysis and extensive experimental validation on a collaborative robot without JTSs, demonstrating its effectiveness in real-world contact scenarios.