Nonlinear Model Predictive Control for Mobile Medical Robot Using Neural Optimization

Spinal cord injury (SCI) is an existing incurable disease that brings great pain and life obstacles to patients. Spinal cord electrical stimulation is an effective means to alleviate spinal cord injury. However, its complicated mechanism of action is still unclear. This article aims to summarize several different spinal cord electrical stimulation methods, analyze the stimulation effect, and briefly describe the current understanding of its origin and mechanism of action. In recent years, several application cases of the electrical stimulation system of stimulation methods have confirmed its positive effects in spinal cord injury diseases and provided new perspectives for the improvement of spinal cord injury. Finally, the possible development direction and corresponding challenges of spinal cord electrical stimulation in the future are proposed.

show abstract

“…[15]. Researchers have verified through experiments that closed-loop control may be more practical [31][32][33], as shown in Figure 2.…”

Section: Control Systemsmentioning

confidence: 87%

Complex Electrical Stimulation Systems in Motor Function Rehabilitation after Spinal Cord Injury

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Imitation learning (IL), also referred to as learning from demonstration (LfD), is a powerful approach for complex manipulation tasks, which perceives and reproduces human movements without the need of explicit programming of behavior ( Takamatsu et al, 2007 ; Kormushev et al, 2011 ; Suomalainen and Kyrki, 2017 ; Hu et al, 2020 ). Among the IL approaches, DMPs ( Ijspeert et al, 2013 ) have shown the ability to generalize demonstrations in different manipulation tasks ( Peters and Schaal, 2008 ; Metzen et al, 2014 ; Hu et al, 2018 ; Sutanto et al, 2018 ).…”

Section: Related Workmentioning

confidence: 99%

An Adaptive Imitation Learning Framework for Robotic Complex Contact-Rich Insertion Tasks

et al. 2022

View full text Add to dashboard Cite

Complex contact-rich insertion is a ubiquitous robotic manipulation skill and usually involves nonlinear and low-clearance insertion trajectories as well as varying force requirements. A hybrid trajectory and force learning framework can be utilized to generate high-quality trajectories by imitation learning and find suitable force control policies efficiently by reinforcement learning. However, with the mentioned approach, many human demonstrations are necessary to learn several tasks even when those tasks require topologically similar trajectories. Therefore, to reduce human repetitive teaching efforts for new tasks, we present an adaptive imitation framework for robot manipulation. The main contribution of this work is the development of a framework that introduces dynamic movement primitives into a hybrid trajectory and force learning framework to learn a specific class of complex contact-rich insertion tasks based on the trajectory profile of a single task instance belonging to the task class. Through experimental evaluations, we validate that the proposed framework is sample efficient, safer, and generalizes better at learning complex contact-rich insertion tasks on both simulation environments and on real hardware.

show abstract

“…(2) How to devise the desired local filter in the presence of sensor energy-induced missing measurement phenomenon? (3) Based on the acquired local localization information, how to develop a feasible fusion localization scheme for the addressed RL? Here, we endeavour in handling the listed challenges and the advantages The rest of this paper is arranged as follows.…”

Section: Introductionmentioning

confidence: 99%

Recursive fusion estimation for mobile robot localization under multiple energy harvesting sensors

Karimi

2021

IET Control Theory & Appl

Self Cite

View full text Add to dashboard Cite

This paper is concerned with the recursive fusion estimation-based mobile robot localization (RL) problem by employing multiple energy harvesting sensors (EHSs). In the addressed RL problem, multiple sensors with energy harvesting capacity are deployed to produce measurements used for RL. When the sensors own sufficient energy, the sensors can output measurements and then send them to the corresponding local filter. Otherwise, the sensor energy-induced missing measurement phenomenon will occur. In order to obtain the missing measurement rate, at each time instant, the relationship between the totality of the sensor energy and its probability distribution is derived recursively. This paper aims at seeking out a practicable solution to the addressed mobile RL problem. First, in the presence of the sensor energy-induced measurement missing phenomenon, an upper bound (UB) of the local localization error covariance is recursively acquired. Then, such a derived UB is minimized by suitably devising the desired local filter parameter. Subsequently, the covariance intersection fusion method is adopted to achieve the addressed RL problem. In the end, a simulation is conducted to verify the practicability of the developed RL scheme.

show abstract

Nonlinear Model Predictive Control for Mobile Medical Robot Using Neural Optimization

Cited by 43 publications

References 26 publications

Complex Electrical Stimulation Systems in Motor Function Rehabilitation after Spinal Cord Injury

Complex Electrical Stimulation Systems in Motor Function Rehabilitation after Spinal Cord Injury

An Adaptive Imitation Learning Framework for Robotic Complex Contact-Rich Insertion Tasks

Recursive fusion estimation for mobile robot localization under multiple energy harvesting sensors

Contact Info

Product

Resources

About