This paper presents a Bayesian optimization framework for the automatic tuning of shared controllers which are defined as a Model Predictive Control (MPC) problem. The proposed framework includes the design of performance metrics as well as the representation of user inputs for simulation-based optimization. The framework is applied to the optimization of a shared controller for an Image Guided Therapy robot. VR-based user experiments confirm the increase in performance of the automatically tuned MPC shared controller with respect to a hand-tuned baseline version as well as its generalization ability
International audienceDesigning controllers for complex robots such as humanoids is not an easy task...
International audienceDesigning controllers for complex robots such as humanoids is not an easy task...
Preference-based optimization is a powerful tool to improve the performance of a system in an intuit...
Robotics has the potential to be one of the most revolutionary technologies in human history. The im...
Robotics has the potential to be one of the most revolutionary technologies in human history. The im...
We propose an adaptive optimisation approach for tuning stochastic model predictive control (MPC) hy...
In this paper, we propose a method to automatically and efficiently tune high-dimensional vectors of...
International audienceThe purpose of this paper is to develop an automated tuning procedure for auto...
Robotic setups often need fine-tuned controller parameters both at low- and task-levels. Finding an ...
An important class of black-box optimization problems relies on using simulations to assess the qual...
Autonomy is increasingly demanded to industrial manipulators. Robots have to be capable to regulate ...
An important class of black-box optimization problems relies on using simulations to assess the qual...
Bayesian Optimization (BO) is an effective method for optimizing expensive-to-evaluate black-box fun...
Designing controllers for complex robots is not an easy task. Often, researchers hand-tune controlle...
Model predictive control (MPC) is a promising approach to the lateral and longitudinal control of au...
International audienceDesigning controllers for complex robots such as humanoids is not an easy task...
International audienceDesigning controllers for complex robots such as humanoids is not an easy task...
Preference-based optimization is a powerful tool to improve the performance of a system in an intuit...
Robotics has the potential to be one of the most revolutionary technologies in human history. The im...
Robotics has the potential to be one of the most revolutionary technologies in human history. The im...
We propose an adaptive optimisation approach for tuning stochastic model predictive control (MPC) hy...
In this paper, we propose a method to automatically and efficiently tune high-dimensional vectors of...
International audienceThe purpose of this paper is to develop an automated tuning procedure for auto...
Robotic setups often need fine-tuned controller parameters both at low- and task-levels. Finding an ...
An important class of black-box optimization problems relies on using simulations to assess the qual...
Autonomy is increasingly demanded to industrial manipulators. Robots have to be capable to regulate ...
An important class of black-box optimization problems relies on using simulations to assess the qual...
Bayesian Optimization (BO) is an effective method for optimizing expensive-to-evaluate black-box fun...
Designing controllers for complex robots is not an easy task. Often, researchers hand-tune controlle...
Model predictive control (MPC) is a promising approach to the lateral and longitudinal control of au...
International audienceDesigning controllers for complex robots such as humanoids is not an easy task...
International audienceDesigning controllers for complex robots such as humanoids is not an easy task...
Preference-based optimization is a powerful tool to improve the performance of a system in an intuit...