A Novel Approach for Outlier Detection and Robust Sensory Data Model Learning

Cursi, Francesco; Yang, Guang‐Zhong

doi:10.1109/iros40897.2019.8967653

Cited by 11 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly to Feedforward Artificial Neural Networks (ANN), BNN are capable of representing complicated behaviours, without the need of knowing any mathematical or physical model. ANN, however, are highly influenced by outliers in the dataset [12], suffer from overfitting, and it is difficult to control their complexity [13]. BNN, instead, allow including uncertainties in the model, by adding priors to the weights of the network.…”

Section: Bayesian Neural Network For Modellingmentioning

confidence: 99%

Bayesian Neural Network Modeling and Hierarchical MPC for a Tendon-Driven Surgical Robot With Uncertainty Minimization

Cursi

Modugno

Lanari

et al. 2021

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

In order to guarantee precision and safety in robotic surgery, accurate models of the robot and proper control strategies are needed. Bayesian Neural Networks (BNN) are capable of learning complex models and provide information about the uncertainties of the learned system. Model Predictive Control (MPC) is a reliable control strategy to ensure optimality and satisfaction of safety constraints. In this work we propose the use of BNN to build the highly nonlinear kinematic and dynamic models of a tendon-driven surgical robot, and exploit the information about the epistemic uncertainties by means of a Hierarchical MPC (Hi-MPC) control strategy. Simulation and real world experiments show that the method is capable of ensuring accurate tip positioning, while satisfying imposed safety bounds on the kinematics and dynamics of the robot.

show abstract

Section: Bayesian Neural Network For Modellingmentioning

confidence: 99%

Bayesian Neural Network Modeling and Hierarchical MPC for a Tendon-Driven Surgical Robot With Uncertainty Minimization

Cursi

Modugno

Lanari

et al. 2021

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is known that regression approaches are highly influenced by outliers [26][27][28], and ANN are no exception [29,30]. To improve the performance of the learning approach, the method presented in [31] is employed. This method consists in iteratively reweighting each data point, based on a user defined weighting function, thus allowing discarding points too far from the model's expected output (outliers).…”

Section: Elbow1mentioning

confidence: 99%

“…The acquired dataset has been randomly divided into three subsets for the training (70%), validation (15%), and testing (15%). The robust approach [31] is able to find a very good model for the data acquired offline, yielding very small errors between the estimated outputs and the ground truths (Table 1).…”

Section: Robot Modellingmentioning

confidence: 99%

Adaptive Kinematic Modelling for Multiobjective Control of a Redundant Surgical Robotic Tool

2020

Self Cite

View full text Add to dashboard Cite

Accurate kinematic models are essential for effective control of surgical robots. For tendon driven robots, which are common for minimally invasive surgery, the high nonlinearities in the transmission make modelling complex. Machine learning techniques are a preferred approach to tackle this problem. However, surgical environments are rarely structured, due to organs being very soft and deformable, and unpredictable, for instance, because of fluids in the system, wear and break of the tendons that lead to changes of the system’s behaviour. Therefore, the model needs to quickly adapt. In this work, we propose a method to learn the kinematic model of a redundant surgical robot and control it to perform surgical tasks both autonomously and in teleoperation. The approach employs Feedforward Artificial Neural Networks (ANN) for building the kinematic model of the robot offline, and an online adaptive strategy in order to allow the system to conform to the changing environment. To prove the capabilities of the method, a comparison with a simple feedback controller for autonomous tracking is carried out. Simulation results show that the proposed method is capable of achieving very small tracking errors, even when unpredicted changes in the system occur, such as broken joints. The method proved effective also in guaranteeing accurate tracking in teleoperation.

show abstract

“…Based on the structure of the neural network as a cascade of layers, the final derivative of the network output with respect to the network inputs can be calculated iteratively by applying the chain rule to the derivatives of each layer. In order to have a more robust model estimation, less affected by possible outliers in the data, the method proposed in [30], [31] is employed in this work to learn the mapping from θ θ → Γ d .…”

Section: Dynamics Model Learningmentioning

confidence: 99%

Model Predictive Control for a Tendon-Driven Surgical Robot with Safety Constraints in Kinematics and Dynamics

Cursi

Modugno

Kormushev

2020

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

Self Cite

View full text Add to dashboard Cite

In fields such as minimally invasive surgery, effective control strategies are needed to guarantee safety and accuracy of the surgical task. Mechanical designs and actuation schemes have inevitable limitations such as backlash and joint limits. Moreover, surgical robots need to operate in narrow pathways, which may give rise to additional environmental constraints. Therefore, the control strategies must be capable of satisfying the desired motion trajectories and the imposed constraints. Model Predictive Control (MPC) has proven effective for this purpose, allowing to solve an optimal problem by taking into consideration the evolution of the system states, cost function, and constraints over time. The high nonlinearities in tendon-driven systems, adopted in many surgical robots, are difficult to be modelled analytically. In this work, we use a model learning approach for the dynamics of tendon-driven robots. The dynamic model is then employed to impose constraints on the torques of the robot under consideration and solve an optimal constrained control problem for trajectory tracking by using MPC. To assess the capabilities of the proposed framework, both simulated and real world experiments have been conducted.

show abstract

A Novel Approach for Outlier Detection and Robust Sensory Data Model Learning

Cited by 11 publications

References 18 publications

Bayesian Neural Network Modeling and Hierarchical MPC for a Tendon-Driven Surgical Robot With Uncertainty Minimization

Bayesian Neural Network Modeling and Hierarchical MPC for a Tendon-Driven Surgical Robot With Uncertainty Minimization

Adaptive Kinematic Modelling for Multiobjective Control of a Redundant Surgical Robotic Tool

Model Predictive Control for a Tendon-Driven Surgical Robot with Safety Constraints in Kinematics and Dynamics

Contact Info

Product

Resources

About