Model-Free Online Neuroadaptive Controller With Intent Estimation for Physical Human–Robot Interaction

Cremer, Sven; Das, Sumit Kumar; Wijayasinghe, Indika B.; Popa, Dan O.; Lewis, Frank L.

doi:10.1109/tro.2019.2946721

Cited by 45 publications

(16 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A novel neural adaptive controller, that achieves globally asymptotically trajectory tracking for a flexible-joint robot with unknown dynamics, is presented by Chen and Wen in [83], where the tracking performance of the controller is improved by using the regressor online learning. Lastly, Cremer et al [84] propose another neuroadaptive controller framework for stable and efficient HRC using a two-loop structure where both the robot dynamics and the human intent during collaboration are being evaluated online. Two NNs in the outer-loop predict human motion intent and estimate a reference trajectory for the robot that the inner-loop follows.…”

Section: Safety-oriented Control System Designmentioning

confidence: 99%

“…RL is also implemented to solve the linear quadratic regulator (LQR) control problem that is formulated to find the optimal parameters of the impedance model. Furthermore, in the paper [84] by Cremer et al, already mentioned from the safety point of view, the human effort is minimized by using the so-called human intent estimator that proactively helps the user follow the desired trajectory. The human factor analysis tools are also involved in the design of the gesture commands.…”

Section: Ergonomics-oriented Control System Designmentioning

confidence: 99%

See 1 more Smart Citation

Control Techniques for Safe, Ergonomic, and Efficient Human-Robot Collaboration in the Digital Industry: A Survey

Proia

Carli

Cavone

et al. 2022

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

The fourth industrial revolution, also known as Industry 4.0, is reshaping the way individuals live and work while providing a substantial influence on the manufacturing scenario.The key enabling technology that has made Industry 4.0 a concrete reality is without doubt collaborative robotics, which is also evolving as a fundamental pillar of the next revolution, the so-called Industry 5.0. The improvement of employees' safety and well-being, together with the increase of profitability and productivity, are indeed the main goals of human-robot collaboration (HRC) in the industrial setting. The robotic controller design and the analysis of existing decision and control techniques are crucially needed to develop innovative models and state-of-the-art methodologies for a safe, ergonomic, and efficient HRC. To this aim, this paper presents an accurate review of the most recent and relevant contributions to the related literature, focusing on the control perspective. All the surveyed works are carefully selected and categorized by target (i.e., safety, ergonomics, and efficiency), and then by problem and type of control, in presence or absence of optimization. Finally, the discussion of the achieved results and the analysis of the emerging challenges in this research field are reported, highlighting the identified gaps and the promising future developments in the context of the digital evolution.Note to Practitioners-The design and development of manufacturing systems are experiencing substantial changes towards full automation. This ongoing challenge is being tackled by academia and industrial practitioners with the adoption of collaborative robots, where the skills and peculiarities of humans (e.g., intelligence, creativity, adaptability, etc.) and robots (e.g., flexibility, pinpoint accuracy, tirelessness, etc.) are combined to better perform a variety of tasks. Nevertheless, due to their different characteristics, there is an emerging need for designing suitable decision and control techniques to ensure a safe and ergonomic HRC, while keeping the highest level of productivity. Against this background, the aim of this paper is to provide researchers and practitioners with a reference source in the related field, which can help them designing and developing suitable solutions to control problems in safe, ergonomic, and efficient collaborative robotics.

show abstract

Section: Safety-oriented Control System Designmentioning

confidence: 99%

Section: Ergonomics-oriented Control System Designmentioning

confidence: 99%

Control Techniques for Safe, Ergonomic, and Efficient Human-Robot Collaboration in the Digital Industry: A Survey

Proia

Carli

Cavone

et al. 2022

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

show abstract

“…Finally, based on the data-driven discrete-time nonlinear terminal sliding surface, a robust controller is designed. The researchers proposed a cascade-loop pHRI controller in [28], which consists of two parts. The outer loop is composed of two neural networks (NN) and is mainly used to predict human movement intentions.…”

Section: Model-based Control and Model-free Controlmentioning

confidence: 99%

Model-Based and Model-Free Robot Control: A Review

Zhang

Liu

2021

Lecture Notes in Mechanical Engineering

View full text Add to dashboard Cite

Robot control is one of the key aspects of robotics research. Models are essential tools in robotics, such as robot's own body dynamics and kinematics models, actuator/motor models, and the models of external controllable objects. In this paper, we review the latest advances in model-based and model-free approaches with a strong focus on robot control. Based on the designed search strategy, several prevailing control approaches are classified and discussed according to their control strategies. An insight into the gripper control is also explored. Then the research problems and applicability of the control methods are discussed by investigating their merits and demerits. Based on the discussion, we summarize the challenges and future research trends of robot control.

show abstract

“…Human-in-the-loop online learning techniques have demonstrated significant potential in human-robot interaction tasks [1]- [3], such as in improving the performance of robotic assistive devices. In particular, online learning from human feedback can help to optimize walking gaits for lower-body exoskeletons [4]- [6], which are placed over existing limbs to assist mobility-impaired individuals.…”

Section: Introductionmentioning

confidence: 99%

Human Preference-Based Learning for High-dimensional Optimization of Exoskeleton Walking Gaits

Tucker

Cheng

Novoseller

et al. 2020

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Understanding users' gait preferences of a lowerbody exoskeleton requires optimizing over the high-dimensional gait parameter space. However, existing preference-based learning methods have only explored low-dimensional domains due to computational limitations. To learn user preferences in high dimensions, this work presents LINECOSPAR, a human-inthe-loop preference-based framework that enables optimization over many parameters by iteratively exploring one-dimensional subspaces. Additionally, this work identifies gait attributes that characterize broader preferences across users. In simulations and human trials, we empirically verify that LINECOSPAR is a sample-efficient approach for high-dimensional preference optimization. Our analysis of the experimental data reveals a correspondence between human preferences and objective measures of dynamic stability, while also highlighting inconsistencies in the utility functions underlying different users' gait preferences. This has implications for exoskeleton gait synthesis, an active field with applications to clinical use and patient rehabilitation.

show abstract

Model-Free Online Neuroadaptive Controller With Intent Estimation for Physical Human–Robot Interaction

Cited by 45 publications

References 26 publications

Control Techniques for Safe, Ergonomic, and Efficient Human-Robot Collaboration in the Digital Industry: A Survey

Control Techniques for Safe, Ergonomic, and Efficient Human-Robot Collaboration in the Digital Industry: A Survey

Model-Based and Model-Free Robot Control: A Review

Human Preference-Based Learning for High-dimensional Optimization of Exoskeleton Walking Gaits

Contact Info

Product

Resources

About