Superhuman performance of surgical tasks by robots using iterative learning from human-guided demonstrations

By Jur van den Berg, Stephen Miller, Daniel Duckworth, Humphrey Hu, Andrew Wan, Xiao-Yu Fu, Ken Goldberg, Pieter Abbeel. 2010

268 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Control and Systems Engineering, Surgery, Reinforcement Learning

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 Control and Systems Engineering

In Surgery

In Reinforcement Learning

Citations in the corpus

Domain randomization for transferring deep neural networks from simulation to the real world (2017, background): “Iterative learning control has been applied to a variety of robotic control problems, from model car control (e.g., [1] and [8]) to surgical robotics (e.g., [48]).”
An Algorithmic Perspective on Imitation Learning (2018, methodology): “In the M-step, the time mapping τ and the covariance matrices R are updated by maximizing the likelihood with respect to the estimated z. DTW is used to update the time mapping τ in [Abbeel et al., 2010, van den Berg et al., 2010].”
Ray: A Distributed Framework for Emerging AI Applications (2017, background): “ms have already yielded remarkable results, such as Google’s AlphaGo beating a human world champion [54], and are beginning to ﬁnd their way into dialogue systems, UAVs [42], and robotic manipulation [25, 60]. The central goal of an RL application is to learn a policy—a mapping from the state of the”
Surgical robotics beyond enhanced dexterity instrumentation: a survey of machine learning techniques and their role in intelligent and autonomous surgical actions (2016, background): “[9] developed an algorithm that learns a task from multiple human demonstrations.”
Evolution of autonomous and semi‐autonomous robotic surgical systems: a review of the literature (2011, methodology): “(41), using two Berkeley surgical robots (Figure 6).”
A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges (2023, unknown): “As such, IL holds potential across a spectrum of applications necessitating autonomous behavior akin to human expertise, ranging from manufacturing and healthcare to autonomous vehicles and gaming [4], [5], [6], [7].”
SHIV: Reducing supervisor burden in DAgger using support vectors for efficient learning from demonstrations in high dimensional state spaces (2016, background): “from demonstration has been used successfully in recent year for a large number of robotic tasks, including helicopter maneuvering [1], car parking [2], and robot surgery [33].”
Skill learning and task outcome prediction for manipulation (2011, background): “A large number of related project have been published in recent years [13], [14].”
Guiding Trajectory Optimization by Demonstrated Distributions (2017, methodology): “Therefore, we synchronize the demonstrated trajectories in time domain using Dynamic Time Warping [23] in the same manner as in [24].”
A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms (2019, background): “This is an especially important question in robotic manipulation, in which many future applications will require behaviors that are safe and correct with high confidence: robots that operate alongside humans in homes and workplaces must not cause injuries, destroy property, or damage themselves; saf”
Motion generation of robotic surgical tasks: Learning from expert demonstrations (2010, methodology): “Other approaches rely on hardwiring controllers for specialized stitching machines [5] and laparoscopic instruments [3] or optimizing controllers [6], [ 7 ].”
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].”
Multilateral surgical pattern cutting in 2D orthotropic gauze with deep reinforcement learning policies for tensioning (2017, methodology): “[34] proposed an iterative technique to learn a reference trajectory and execute it at higher than demonstration speeds for suture knot tying.”
A case study of trajectory transfer through non-rigid registration for a simplified suturing scenario (2013, methodology): “At the core of our procedure is the trajectory transfer algorithm recently proposed by the authors in [12], which takes trajectories from human demonstrations and adapts them to a new environment geometry.”