Bo Lu

Prof. Dr. Bo Lu


Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 March 2021 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
YLYiang Lu
Yiang Lu
Bo LuBo Lu
Bo Lu
BLBin Li
Bin Li
HGHuanhuan Guo
Huanhuan Guo
YLYunhui Liu
Yunhui Liu
In this letter, we propose a novel 3D shape sensing algorithm for flexible endoscopic surgery using multi-core fiber Bragg grating (FBG) sensors. Considering the signal noises and environmental perturbations, the direct use of FBG measurements for shape sensing and position estimation is regarded as far from accurate and stable, especially when utilized in the sensing of long and flexible surgical instruments. To solve this problem, a novel and generic model-based filtering technique for the iterative curvature/twist estimation by taking advantage of the configurations of the multi-core FBGs in the optical fiber is introduced to remedy the sensory noises. Besides, we introduce an enhanced moving average approach to smooth the estimated curvatures and twists spatially on the fiber. We extensively validate our algorithm by conducting shape sensing tasks in simulations under varying conditions, and in experiments using a robotic-assisted colonoscope system integrated with a multi-core FBG fiber. The results prove our method substantially outperforms the conventional approach in the aspect of estimation accuracy and robustness, showing the superiority and application feasibility.

29 July 2022 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
RWRuofeng Wei
Ruofeng Wei
BLBin Li
Bin Li
HMHangjie Mo
Hangjie Mo
Bo LuBo Lu
Bo Lu
YLYonghao Long
Yonghao Long
DSDong Sun
Dong Sun
Objective: The computation of anatomical information and laparoscope position is a fundamental block of surgical navigation in Minimally Invasive Surgery (MIS). Recovering a dense 3D structure of surgical scene using visual cues remains a challenge, and the online laparoscopic tracking primarily relies on external sensors, which increases system complexity. Methods: Here, we propose a learning-driven framework, in which an image-guided laparoscopic localization with 3D reconstructions of anatomical structures is obtained. To reconstruct the structure of the whole surgical environment, we first fine-tune a learning-based stereoscopic depth perception method, which is robust to texture-less and variant soft tissues, for depth estimation. Then, we develop a dense reconstruction algorithm to represent the scene by surfels, estimate the laparoscope poses and fuse the depth into a unified reference coordinate for tissue reconstruction. To estimate poses of new laparoscope views, we achieve a coarse-to-fine localization method, which incorporates our reconstructed model. Results: We evaluate the reconstruction method and the localization module on three datasets, namely, the stereo correspondence and reconstruction of endoscopic data (SCARED), the ex-vivo data collected with Universal Robot (UR) and Karl Storz Laparoscope, and the in-vivo DaVinci robotic surgery dataset, where the reconstructed structures have rich details of surface texture with an error under 1.71 mm and the localization module can accurately track the laparoscope with images as input. Conclusions: Experimental results demonstrate the superior performance of the proposed method in anatomy reconstruction and laparoscopic localization. Significance: The proposed framework can be potentially extended to the current surgical navigation system.

22 June 2021 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
JLJiewen Lai
Jiewen Lai
KHKaicheng Huang
Kaicheng Huang
Bo LuBo Lu
Bo Lu
QZQingxiang Zhao
Qingxiang Zhao
HCHenry Kar Hang Chu
Henry Kar Hang Chu
Soft-bodied robotic manipulators have great potential for use in minimally invasive surgery, owing to their advantages of high flexibility with infinite degrees of freedom (DOF). One of the potential applications is to perform blood suctioning, which is inevitable during the surgery. To attain higher efficiency in suctioning, the robotic tip should remain vertical while moving along on the work surface. Motivated by this application, this article presents a novel soft robot design and its control scheme to properly configure the tip of a two-segment soft robot while following a planned trajectory on the work surface. Aiming to reduce the incision size and the possibility of infection, a 3D-printed soft-bodied manipulator utilizing the cable-driven mechanism with a diameter of 9 mm was designed and fabricated. An additional DOF was added through a motorized insertion stage. The robot system was modeled using piecewise constant-curvature assumption, and an RGB-D vision was employed to enhance the accuracy of the kinematic-based controller. Performances of the tip positioning and verticalizing were evaluated via simulation, and further verified through experiments. The results confirm that the manipulator is capable of following different trajectories at various velocities while keeping its tip vertical. Compared to other similar works, our results are satisfactory with an root-mean-square error of trajectory tracking within 7 mm, and a maximum angular deviation of 6 $^\circ$ . Fluid suction experiments were conducted to demonstrate its effectiveness for automated 3-D suction. This article offers a new tool to support the surgeons for surgical blood suction.

18 February 2022 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
JLJiewen Lai
Jiewen Lai
Bo LuBo Lu
Bo Lu
QZQingxiang Zhao
Qingxiang Zhao
HCHenry Kar Hang Chu
Henry Kar Hang Chu
A cable-driven soft robot with redundancy can perform the tip trajectory tracking task and in the meanwhile fulfill some extra constraints, such as tracking with a designated tip orientation, or avoiding obstacles in the environment. These constraints require proper motion planning of the soft material-based body that can be axially compressed. In this letter, we derive the compressible curvature kinematics of a cable-driven soft robot which takes the undesirable axial compression caused by the cable-driven mechanism into account. Robot motion planning for tip trajectory tracking tasks in constrained conditions, including fixed orientation tip and manipulator–obstacle collision avoidance, are investigated. The inverse solution of cable actuation is formulated as a damped least-square optimization problem and iteratively computed off-line. The performance of path and trajectory tracking, and the obedience to constraints are evaluated via the simulation we make open-source, as well as prototype experiments. The method can be generalized to similar multisegment cable-driven soft robotic systems by customizing the robot parameters for the prior motion planning in tip trajectory following tasks.

14 February 2022 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
JSJiankai Sun
Jiankai Sun
DHDe-An Huang
De-An Huang
Bo LuBo Lu
Bo Lu
YLYunhui Liu
Yunhui Liu
BZBolei Zhou
Bolei Zhou
AGAnimesh Garg
Animesh Garg
In this work, we study the problem of how to leverage instructional videos to facilitate the understanding of human decision-making processes, focusing on training a model with the ability to plan a goal-directed procedure from real-world videos. Learning structured and plannable state and action spaces directly from unstructured videos is the key technical challenge of our task. There are two problems: first, the appearance gap between the training and validation datasets could be large for unstructured videos; second, these gaps lead to decision errors that compound over the steps. We address these limitations with Pla nning T ransform e r (PlaTe), which has the advantage of circumventing the compounding prediction errors that occur with single-step models during long model-based rollouts. Our method simultaneously learns the latent state and action information of assigned tasks and the representations of the decision-making process from human demonstrations. Experiments conducted on real-world instructional videos show that our method can achieve a better performance in reaching the indicated goal than previous algorithms. We also validated the possibility of applying procedural tasks on a UR-5 platform. Please see 1

10 May 2021 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Open access
JLJiewen Lai
Jiewen Lai
Bo LuBo Lu
Bo Lu
HCHenry Kar Hang Chu
Henry Kar Hang Chu
A soft-bodied robot exhibits prominent dexterity due to the soft nature of its material. However, the softness can become a burden when the robot needs to interact with the environment, given that the targeted object is usually much stiffer than the compliant soft robot. A variable-stiffness soft robot, fusing the merits of softness and stiffness, is in favor of many applications, such as robot-assisted minimally invasive surgeries. In this article, we propose a tendon-tensioning method to adaptively control the stiffness of a dual-segment tendon-driven backboneless soft robot based on depth vision. A depth-vision-based closed-loop controller is designed for stiffness compensation when the manipulator is subjected to the external load. Experiments were conducted to examine the feasibility and performance of the proposed method. The results confirm our control scheme on the robot with controllability of stiffness up to 132%. Based on our method, the manipulator with an external payload can follow designated trajectories with positioning errors reduced up to 50% comparing to that with open-loop control. Without quantifying the instantaneous stiffness, this work contributes a generalized method for tuning the stiffness of the tendon-driven soft robots in the presence of external disturbances without onboard sensing.