Learning accurate kinematic control of cable-driven surgical robots using data cleaning and Gaussian Process Regression
By Jeffrey Mahler, Sanjay Krishnan, Michael Laskey, Siddarth Sen, Adithyavairavan Murali, Ben Kehoe, Sachin Patil, Jiannan Wang, M. Franklin, Pieter Abbeel and 1 more. 2014
84 citations recorded by the source corpus.
Subfields: Biomedical Engineering, Medical Laboratory Technology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Biomedical Engineering
- Ken Goldberg
- Jeffrey Mahler
- Pieter Abbeel
- Sanjay Krishnan
- Anca Dragan
- Brijen Thananjeyan
- Sachin Patil
- Ben Kehoe
Citations in the corpus
- ActiveClean: An Interactive Data Cleaning Framework For Modern Machine Learning (2016, background): “Despite this importance, in theory and practice, the academic community has decoupled the data cleaning problem from featurization and ML.”
- Comparing human-centric and robot-centric sampling for robot deep learning from demonstrations (2016, background): “The interest in stochastic policies instead of deterministic is two-fold: 1) human supervisor can be noisy in nature and 2) due to noise in robot execution, such as cable coupling, the intended and actual control may differ in a stochastic way [17].”
- ActiveClean: Interactive Data Cleaning While Learning Convex Loss Models (2016, methodology): “In robotics, Mahler et al. explored a calibration problem in which data was systematically corrupted [25] and proposed a rule-based technique for cleaning data.”
- Deep Imitation Learning of Sequential Fabric Smoothing Policies (2019, methodology): “The da Vinci Research Kit (dVRK) surgical robot [15] is a cable-driven surgical robot with imprecision as reviewed in prior work [24], [43].”
- A Survey of Research on Cloud Robotics and Automation (2015, background): “New approaches are required that are robust to dirty data.”
- Image Object Label 3 D CAD Model Candidate Grasps Google Object Recognition Engine Google Cloud Storage Select Feasible Grasp with Highest Success Probability Pose EstimationCamera Robots Cloud 3 D Sensor (2014, background): “Large datasets collected from distributed sources are often " dirty " with erroneous, duplicated, or corrupted data [6], [158], such as 3D position data collected during robot calibration [111].”