Multilateral surgical pattern cutting in 2D orthotropic gauze with deep reinforcement learning policies for tensioning

By Brijen Thananjeyan, Animesh Garg, Sanjay Krishnan, Carolyn L. Chen, Lauren Miller, Ken Goldberg. 2017

147 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computational Mechanics, Control and Systems Engineering

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

In Computational Mechanics

In Control and Systems Engineering

Citations in the corpus

Reinforcement Learning in Healthcare: A Survey (2019, methodology): “Thananjeyan et al. [220] and Nguyen et al. [168] applied the DRL algorithm, TRPO, in learning tensioning policies effectively for surgical gauze cutting.”
Sim-to-Real Reinforcement Learning for Deformable Object Manipulation (2018, background): “Key domains of interest are home assistance robotics (cloth folding [1], bed making [2], getting dressed [3, 4]); medicine (robot surgery [5], suturing [6]); and industry (cable insertion [7]).”
Path Planning for Automation of Surgery Robot based on Probabilistic Roadmap and Reinforcement Learning (2018, methodology): “In particular, CAL-MR of UC-Berkeley has been continuously applying automation technology to surgical robots [1,7,8,9,10] (Fig.”
Empowering Things With Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things (2020, methodology): “, self-driving vehicle [199], [203], medical robot [213], and mobile service robot.”
Deep Imitation Learning of Sequential Fabric Smoothing Policies (2019, background): “Robot manipulation of fabric has applications in senior care and dressing assistance [11], [12], [13], sewing [41], ironing [21], laundry folding [22], [27], [44], [54], fabric upholstery manufacturing [32], [50], and handling gauze in robotic surgery [48].”
Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Tasks (2019, background): “In practice, the most common A in RL for robot manipulation are a) joint torques [25], b) joint velocities [7, 46, 48], c) joint positions [8], and d) end-effector position [23, 43] possibly with orientation.”
Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data (2020, background): “Manipulating deformable objects is valuable for a wide variety of applications from surgery and manufacturing to household robotics [2, 8, 11, 14, 15, 19, 26, 37–39].”
A New Tensioning Method using Deep Reinforcement Learning for Surgical Pattern Cutting (2019, methodology): “[9] investigated a method to learn the tensioning force using deep reinforcement learning (DRL), namely trust region policy optimization (TRPO) [33] for soft tissue cutting [34].”
Deep Learning Applications in Medical Image Analysis (2018, background): “New areas of research include prognostication [97], content-based image retrieval [98], [99], image report or caption generation [100], [101], and manipulation of physical objects with LSTMs and reinforcement learning [102], [103] involving surgical robots [104], [105].”