Efficiently Calibrating Cable-Driven Surgical Robots With RGBD Fiducial Sensing and Recurrent Neural Networks

Hwang, Mina; Thananjeyan, Brijen; Paradis, Samuel; Seita, Daniel; Ichnowski, Jeffrey; Fer, Danyal; Low, Thomas; Goldberg, Ken

doi:10.1109/lra.2020.3010746

Cited by 34 publications

(57 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The LSTM model is a typical algorithm for processing the sequential samples, 40 and usually used to capture the hysteresis features due to its outstanding memory ability for the historical information of samples 41,42 . As can be verified in the Figure 12(A), the prediction accuracies of LSTM models were indeed high in case of sufficient samples.…”

Section: Experiments and Resultsmentioning

confidence: 84%

“…As can be observed from Figure 14, the error convergence rate during EHNN model training is superior to that of LSTM model, and the trained EHNN model can eventually achieve a better error convergence result, from which the smaller network complexity of the proposed EHNN model can be verified. Even though it has been proved that LSTM model has an outstanding capacity of capturing hysteretic features in various fields, 18–20,41,42 its poor response speed caused by its complex network structure is not suitable for the real‐time robotic control compared with that of our proposed EHNN model. Through the above conducted experiments, our proposed EHNN model shows great superiority over the LSTM model that is widely used in the hysteresis feature capture, in aspects of the prediction accuracy and the network structure complexity.…”

Section: Experiments and Resultsmentioning

confidence: 94%

See 1 more Smart Citation

A hybrid learning‐based hysteresis compensation strategy for surgical robots

Gao

Tan

Sun

2021

Robotics Computer Surgery

View full text Add to dashboard Cite

Background The hysteretic forces arising from the electric cables that externally run along the robotic joints are the main disturbance to the precise parameter estimation of gravity compensation model, for the Master Tool Manipulator (MTM) of the da Vinci Research Kit (dVRK). Because such nonlinear disturbance forces and the gravitational forces are often hybrid and in the same magnitude. Methods A strategy is proposed to separate these two hybrid forces, and model them by individual learning‐based algorithms. A specially designed Elastic Hysteresis Neural Network model is employed to capture the hysteresis nature of disturbance forces. Results The experimental results show that our proposed strategy has higher compensation accuracy (78.64%–93.32%), and fewer real samples are required for model estimation (100 samples for each joint). Conclusions Our proposed gravity compensation strategy for the MTM of the dVRK shows great improvement over existing state‐of‐the‐arts methods through conducted comparative experiments.

show abstract

Section: Experiments and Resultsmentioning

confidence: 84%

Section: Experiments and Resultsmentioning

confidence: 94%

A hybrid learning‐based hysteresis compensation strategy for surgical robots

Gao

Tan

Sun

2021

Robotics Computer Surgery

View full text Add to dashboard Cite

show abstract

“…The workspace is equipped with an overhead Zivid OnePlus RGBD sensor which captures 1900 × 1200 RGBD image observations, although only the RGB channels are used in HULK, LOKI, and SPiDERMan inference. The dVRK is calibrated with a standard pixel-toworld camera transformation using the fiducial registration procedure described in [11]. The complete experimental setup has workspace bounds w l , w r .…”

Section: Methodsmentioning

confidence: 99%

Untangling Dense Non-Planar Knots by Learning Manipulation Features and Recovery Policies

Sundaresan

Grannen

Thananjeyan

et al. 2021

Robotics: Science and Systems XVII

Self Cite

View full text Add to dashboard Cite

Robot manipulation for untangling 1D deformable structures such as ropes, cables, and wires is challenging due to their infinite dimensional configuration space, complex dynamics, and tendency to self-occlude. Analytical controllers often fail in the presence of dense configurations, due to the difficulty of grasping between adjacent cable segments. We present two algorithms that enhance robust cable untangling, LOKI and SPi-DERMan, which operate alongside HULK, a high-level planner from prior work. LOKI uses a learned model of manipulation features to refine a coarse grasp keypoint prediction to a precise, optimized location and orientation, while SPiDERMan uses a learned model to sense task progress and apply recovery actions. We evaluate these algorithms in physical cable untangling experiments with 336 knots and over 1500 actions on real cables using the da Vinci surgical robot. We find that the combination of HULK, LOKI, and SPiDERMan is able to untangle dense overhand, figure-eight, double-overhand, square, bowline, granny, stevedore, and triple-overhand knots. The composition of these methods successfully untangles a cable from a dense initial configuration in 68.3% of 60 physical experiments and achieves 50% higher success rates than baselines from prior work. Supplementary material, code, and videos can be found at https://tinyurl.com/rssuntangling.

show abstract

“…RGB‐D cameras can capture color and depth images simultaneously. It has been widely used in a large number of areas [17,31,33]. In this paper, the Microsoft Kinect sensor, one kind of RGB‐D camera, is utilized to perceive the environment.…”

Section: Data Processing and Motion Planningmentioning

confidence: 99%

Simulation for senior undergraduate education of robot engineering based on Webots

Yue

Miao

Zhang

et al. 2020

Comp Applic In Engineering

View full text Add to dashboard Cite

In this paper, a comprehensive simulation framework is presented for senior undergraduates of robot engineering based on open‐source simulation software, Webots. In our curriculum, a virtual quadruped robot is used to test different theories. First, students should design the physical structure of the robot and select proper drivers according to the requirements on its motion ability. Then, the kinematics and workspace of each leg should be analyzed. To overcome different terrains, terrain recognition, and motion planning methods are presented. Finally, the processes of building a virtual robot and its test environment are introduced. Simulation results demonstrate that it is possible to test different robot techniques in our proposed simulation framework. Teaching practice and feedback from students show their promotion of understanding of robot theories. Their interest in robots are also increased.

show abstract

Efficiently Calibrating Cable-Driven Surgical Robots With RGBD Fiducial Sensing and Recurrent Neural Networks

Cited by 34 publications

References 26 publications

A hybrid learning‐based hysteresis compensation strategy for surgical robots

A hybrid learning‐based hysteresis compensation strategy for surgical robots

Untangling Dense Non-Planar Knots by Learning Manipulation Features and Recovery Policies

Simulation for senior undergraduate education of robot engineering based on Webots

Contact Info

Product

Resources

About