Helping Hand: A Continuum Robotic Grasper for Traction in Single-Channel Endoscopic Submucosal Dissection
Authors: Bendavid Maimon, Thompson Wong, Aedan Mangan, Sukjun Kim, Michael C. Yip, Tania K. Morimoto
Organizations: Department of Mechanical and Aerospace Engineering, University of California San Diego, La Jolla, CA, USA. · School of Manufacturing Systems and Networks, Arizona State University, Mesa, AZ, USA · Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA, USA.
Endoscopic submucosal dissection (ESD) is a minimally invasive approach for removing large polyps from the colon and offers many benefits compared to other surgical approaches. However, ESD is technically very challenging to perform, leading to limited adoption by physicians. We propose the Helping Hand, a two-segment continuum robotic grasper that, together with an electrosurgical knife, enables tissue traction and cutting within a single 3.7 mm working channel. We achieve this functionality by creating a slot at the base of the Helping Hand that lets the electrosurgical knife extend out, enabling countertraction and cutting through one instrument lumen. We evaluate the Helping Hand's workspace and its ability to provide traction forces from different starting configurations. Finally, we demonstrate the full workflow by isolating and removing tissue in an ex vivo chicken thigh, illustrating the potential for the Helping Hand to help improve ESD procedures.
Figures & tables
Fig. 1: The Helping Hand is a two-degree-of-freedom continuum robotic grasper. It consists of two bending segments, along with a slot at the base that enables a custom electrosurgical knife to be exposed for cutting as the grasper at the tip of the Helping Hand is simultaneously used to provide tissue traction (See Supplementary Video S1).
Fig. 2: Overview of the Helping Hand and actuation architecture. (a) The Instrument subsystem consists of the Helping Hand and the electrosurgical knife. (b) The actuation subsystem comprises four lead-screw-driven linear motion units for proximal and distal tendon actuation, grasper operation, and knife translation. Load cells at the tendon attachments measure tension during articulation of the Helping Hand. (c) The electrosurgical generator subsystem connects to the knife and return pad through the ESG controller, with activation controlled by a pedal switch.
Symbol
Def.
Proximal ( p1 , p2 )
Distal ( d )
g
Notch depth
2.8 mm
3.2 mm
h
Notch height
1.0 mm
1.0 mm
c
Uncut height
1.0 mm
1.0 mm
n
Number of notches
1, 4
8
ri
Inner radius of tube
1.65 mm
1.65 mm
ro
Outer radius of tube
1.75 mm
1.75 mm
TABLE I: Helping Hand Parameters
Fig. 3: Exploded view of the Helping Hand, including detailed views of the medial and proximal routers, and the grasper collet.
Fig. 4: CNC milling setup for the Helping Hand notched tube. (a) The tube is secured in the custom fixture beneath a 1 mm end mill. (b) The CAM setup shows the programmed toolpaths in orange for Operation 1 (left) and Operation 2 (right), between which the tube is rotated 180∘ . Two operations on one reusable fixture produce both notch patterns with consistent alignment.
Fig. 5: Side view of the Helping Hand notched tube, with the base frame {s} at the proximal end and the tip frame {t} at the distal end. One tendon actuates the proximal segment, which consists of the knife exit notch p1 and retraction section p2 , and the second tendon actuates the distal section d . The knife slot sits between p1 and p2 , so two tendons let a single tube expose the knife, aim the grasper, and retract tissue.
Fig. 6: Measured Helping Hand tip positions (colored) and model predictions (gray) during (a) distal-only actuation and (b) proximal-only actuation, with the other tendon slack. Each tendon was displaced in 0.2 mm increments. The model captures the shape of each trajectory but overestimates tip travel, consistent with tendon elongation and friction.
Fig. 7: Traction test setup. A silicone phantom of an 18 mm sessile serrated polyp sits on a six axis force and torque sensor below the Helping Hand. We varied the phantom height to change the Helping Hand configuration at grasping. This setup measured the retraction force on the polyp across different Helping Hand configurations.
Fig. 8: Representative phantom traction trial. The plots show the resultant and normal force on the phantom and the proximal and distal tendon tensions over time, with dashed lines marking articulation, grasping, traction, and release. The force on the phantom rose as we loaded the proximal tendon and fell when we released it.
Height (mm)
Fres (N)
Fz (N)
0
0.331±0.015
0.279±0.029
−4
0.345±0.037
0.299±0.067
−8
0.316±0.027
0.275±0.030
−12
0.325±0.016
0.243±0.037
All
0.329±0.024
0.274±0.043
TABLE II: Force on the Phantom at 9 N Proximal Tendon Tension
Fig. 9: En bloc resection in ex vivo chicken thigh tissue with the Helping Hand and electrosurgical knife deployed from the tip of a mock endoscope. The panels show (a) insertion and alignment, (b) repositioning and knife exposure, (c) grasper positioning, (d) traction and initial incision, (e) lifting of the cut flap, (f) extraction of the grasped specimen, and (g) close up views. The Helping Hand and knife together completed grasping, traction, cutting, and retrieval through one working channel (See Supplementary Video S1).
Augmented dexterity has the potential to reduce the fatigue experienced by surgeons during repetitive surgical tasks. In this paper, we propose the first AGentic RObotics framework for SUrgical VIscoelastic DEbridement (AGRO-SUVIDE), the repeated removal of small fragments attached to a viscoelastic substrate. Leveraging the self-improving and coding capability of agents, AGRO-SUVIDE adopts a modular framework. Specifically, the demonstration analysis module automatically identifies recurring skills from a single expert demonstration, using both visual and kinematic information. The construction module then builds each skill, either as a procedural model-based skill the agent codes against a scaffolded library or as a model-free policy-based skill. At runtime, the monitoring module composes the skills into a loop-style graph sized to the number of fragments it observes, then verifies pre- and post-conditions of each skill to decide whether to advance or retry. We evaluate AGRO-SUVIDE through 340 physical trials on the da Vinci Research Kit (dVRK). AGRO-SUVIDE achieves an average single-fragment removal success rate of 85%, completing consecutive three-fragment removal at 60% and at 95% with one human intervention. It further generalizes to unseen five-fragment scenarios with an average success rate of 80% for single-fragment removal. Project page: https://surgical-robotics.github.io/AGRO-SUVIDE/
Shutong Jin, Ziyang Chen, Preethi Satish +4
Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720, USA. · Department of Robotics, Perception and Learning, KTH Royal Institute of Technology, Stockholm, SE 10044, Sweden. · Intuitive Surgical, Sunnyvale, CA 94086, USA.
Augmenting the dexterity of human surgeons has the potential to free them from tedious subtasks. We consider debridement (removal of diseased or dead tissue fragments), which is challenging due to imprecision in spatial perception and cable actuation. We develop an augmented dexterity system for surgical debridement that uses visual servoing to align the cable-driven gripper with the target position in the image plane, and then introduces a novel approach to depth control, MACAW: Monocular Adaptive Compact Attention Windows. Across 100 physical trials using the da Vinci Research Kit (dVRK) robot, camera-frame servoing reduced average gripper position offset from 37 to fewer than 5 pixels within 4 optimization steps, taking an average of only 0.39s. MACAW significantly outperforms procedural and learned VLA baselines, achieving a 93% success rate at 11 seconds per fragment, yielding a throughput of 304 fragments per hour. Extending MACAW to a bimanual debridement setup maintains a 92% success rate at an average of 7 seconds per fragment, increasing the throughput to 473 fragments per hour.
Ziyang Chen, Shutong Jin, Preethi Satish +6
University of California, Berkeley, USA · David Grant USAF Medical Center, USA. · Intuitive Surgical Inc., USA.
Advanced surgical robotics has made robot-assisted endoscopic submucosal dissection (ESD) a promising approach for the en-bloc resection of large lesions, with the potential to reduce recurrence and improve long-term outcomes. However, the technical complexity and risk of complications in ESD demand stable and precise visual guidance to maintain an accurate dissection corridor and a safe tissue margin. Dense confidence fields provide an effective representation for this purpose by describing both the preferred dissection region and its spatial transition to surrounding tissue. However, reliable confidence field estimation remains challenging in dynamic endoscopic scenes due to smoke, specular highlights, tissue deformation, weak texture, and the thin geometric structure of the target region. To address these challenges, we formulate dissection guidance as a geometry-aware confidence field estimation problem and propose GeoCFNet, a geometry-aware confidence field network built on a pretrained DINOv3 backbone. GeoCFNet integrates a Token-Differentiated Fusion module to aggregate class-token context with dense patch representations, a SegFormer decoder for confidence regression, and Geometry-Aware Spatial Regularization (GASR) to preserve spatial coherence and local geometric transitions. Experimental results show that GeoCFNet achieves RMSE 0.0480, PSNR 27.1995, SSIM 0.3397, and CC 0.2466, indicating accurate and geometrically stable confidence field estimation for robot-assisted ESD guidance.
Rui Tang, Guankun Wang, Long Bai +5
Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China · Theory Lab, Central Research Institute, 2012 Labs, Huawei Technologies Co. Ltd., Hong Kong SAR, China