Reward Learning from Suboptimal Demonstrations with Applications in Surgical Electrocautery

Automating robotic surgery via learning from demonstration (LfD) techniques is extremely challenging. This is because surgical tasks often involve sequential decision-making processes with complex interactions of physical objects and have low tolerance for mistakes. Prior works assume that all demonstrations are fully observable and optimal, which might not be practical in the real world. This paper introduces a sample-efficient method that learns a robust reward function from a limited amount of ranked suboptimal demonstrations consisting of partial-view point cloud observations. The method then learns a policy by optimizing the learned reward function using reinforcement learning (RL). We show that using a learned reward function to obtain a policy is more robust than pure imitation learning. We apply our approach on a physical surgical electrocautery task and demonstrate that our method can perform well even when the provided demonstrations are suboptimal and the observations are high-dimensional point clouds.

Modeling Kinematic Uncertainty of Tendon-Driven Continuum Robots via Mixture Density Networks

Tendon-driven continuum robot kinematic models are frequently computationally expensive, inaccurate due to unmodeled effects, or both. In particular, unmodeled effects produce uncertainties that arise during the robot's operation that lead to variability in the resulting geometry. We propose a novel solution to these issues through the development of a Gaussian mixture kinematic model. We train a mixture density network to output a Gaussian mixture model representation of the robot geometry given the current tendon displacements. This model computes a probability distribution that is more representative of the true distribution of geometries at a given configuration than a model that outputs a single geometry, while also reducing the computation time. We demonstrate one use of this model through a trajectory optimization method that explicitly reasons about the workspace uncertainty to minimize the probability of collision.

Accounting for Hysteresis in the Forward Kinematics of Nonlinearly-Routed Tendon-Driven Continuum Robots via a Learned Deep Decoder Network

Tendon-driven continuum robots have been gaining popularity in medical applications due to their ability to curve around complex anatomical structures, potentially reducing the invasiveness of surgery. However, accurate modeling is required to plan and control the movements of these flexible robots. Physics-based models have limitations due to unmodeled effects, leading to mismatches between model prediction and actual robot shape. Recently proposed learning-based methods have been shown to overcome some of these limitations but do not account for hysteresis, a significant source of error for these robots. To overcome these challenges, we propose a novel deep decoder neural network that predicts the complete shape of tendon-driven robots using point clouds as the shape representation, conditioned on prior configurations to account for hysteresis. We evaluate our method on a physical tendon-driven robot and show that our network model accurately predicts the robot's shape, significantly outperforming a state-of-the-art physics-based model and a learning-based model that does not account for hysteresis.

General-purpose foundation models for increased autonomy in robot-assisted surgery

The dominant paradigm for end-to-end robot learning focuses on optimizing task-specific objectives that solve a single robotic problem such as picking up an object or reaching a target position. However, recent work on high-capacity models in robotics has shown promise toward being trained on large collections of diverse and task-agnostic datasets of video demonstrations. These models have shown impressive levels of generalization to unseen circumstances, especially as the amount of data and the model complexity scale. Surgical robot systems that learn from data have struggled to advance as quickly as other fields of robot learning for a few reasons: (1) there is a lack of existing large-scale open-source data to train models, (2) it is challenging to model the soft-body deformations that these robots work with during surgery because simulation cannot match the physical and visual complexity of biological tissue, and (3) surgical robots risk harming patients when tested in clinical trials and require more extensive safety measures. This perspective article aims to provide a path toward increasing robot autonomy in robot-assisted surgery through the development of a multi-modal, multi-task, vision-language-action model for surgical robots. Ultimately, we argue that surgical robots are uniquely positioned to benefit from general-purpose models and provide three guiding actions toward increased autonomy in robot-assisted surgery.

DefGoalNet: Contextual Goal Learning from Demonstrations For Deformable Object Manipulation

Shape servoing, a robotic task dedicated to controlling objects to desired goal shapes, is a promising approach to deformable object manipulation. An issue arises, however, with the reliance on the specification of a goal shape. This goal has been obtained either by a laborious domain knowledge engineering process or by manually manipulating the object into the desired shape and capturing the goal shape at that specific moment, both of which are impractical in various robotic applications. In this paper, we solve this problem by developing a novel neural network DefGoalNet, which learns deformable object goal shapes directly from a small number of human demonstrations. We demonstrate our method's effectiveness on various robotic tasks, both in simulation and on a physical robot. Notably, in the surgical retraction task, even when trained with as few as 10 demonstrations, our method achieves a median success percentage of nearly 90%. These results mark a substantial advancement in enabling shape servoing methods to bring deformable object manipulation closer to practical, real-world applications.

Efficient and Accurate Mapping of Subsurface Anatomy via Online Trajectory Optimization for Robot Assisted Surgery

Robotic surgical subtask automation has the potential to reduce the per-patient workload of human surgeons. There are a variety of surgical subtasks that require geometric information of subsurface anatomy, such as the location of tumors, which necessitates accurate and efficient surgical sensing. In this work, we propose an automated sensing method that maps 3D subsurface anatomy to provide such geometric knowledge. We model the anatomy via a Bayesian Hilbert map-based probabilistic 3D occupancy map. Using the 3D occupancy map, we plan sensing paths on the surface of the anatomy via a graph search algorithm, $A^*$ search, with a cost function that enables the trajectories generated to balance between exploration of unsensed regions and refining the existing probabilistic understanding. We demonstrate the performance of our proposed method by comparing it against 3 different methods in several anatomical environments including a real-life CT scan dataset. The experimental results show that our method efficiently detects relevant subsurface anatomy with shorter trajectories than the comparison methods, and the resulting occupancy map achieves high accuracy.

DeformerNet: Learning Bimanual Manipulation of 3D Deformable Objects

Applications in fields ranging from home care to warehouse fulfillment to surgical assistance require robots to reliably manipulate the shape of 3D deformable objects. Analytic models of elastic, 3D deformable objects require numerous parameters to describe the potentially infinite degrees of freedom present in determining the object's shape. Previous attempts at performing 3D shape control rely on hand-crafted features to represent the object shape and require training of object-specific control models. We overcome these issues through the use of our novel DeformerNet neural network architecture, which operates on a partial-view point cloud of the manipulated object and a point cloud of the goal shape to learn a low-dimensional representation of the object shape. This shape embedding enables the robot to learn a visual servo controller that computes the desired robot end-effector action to iteratively deform the object toward the target shape. We demonstrate both in simulation and on a physical robot that DeformerNet reliably generalizes to object shapes and material stiffness not seen during training. Crucially, using DeformerNet, the robot successfully accomplishes three surgical sub-tasks: retraction (moving tissue aside to access a site underneath it), tissue wrapping (a sub-task in procedures like aortic stent placements), and connecting two tubular pieces of tissue (a sub-task in anastomosis).

Toward a Millimeter-Scale Tendon-Driven Continuum Wrist with Integrated Gripper for Microsurgical Applications

Microsurgery is a particularly impactful yet challenging form of surgery. Robot assisted microsurgery has the potential to improve surgical dexterity and enable precise operation on such small scales in ways not previously possible. Intraocular microsurgery is a particularly challenging domain in part due to the lack of dexterity that is achievable with rigid instruments inserted through the eye. In this work, we present a new design for a millimeter-scale, dexterous wrist intended for microsurgery applications. The wrist is created via a state-of-the-art two-photon-polymerization (2PP) microfabrication technique, enabling the wrist to be constructed of flexible material with complex internal geometries and critical features at the micron-scale. The wrist features a square cross section with side length of 1.25 mm and total length of 3.75 mm. The wrist has three tendons routed down its length which, when actuated by small-scale linear actuators, enable bending in any plane. We present an integrated gripper actuated by a fourth tendon routed down the center of the robot. We evaluate the wrist and gripper by characterizing its bend-angle. We achieve more than 90 degrees bending in both axes. We demonstrate out of plane bending as well as the robot's ability to grip while actuated. Our integrated gripper/tendon-driven continuum robot design and meso-scale assembly techniques have the potential to enable small-scale wrists with more dexterity than has been previously demonstrated. Such a wrist could improve surgeon capabilities during teleoperation with the potential to improve patient outcomes in a variety of surgical applications, including intraocular surgery.

Interactive-Rate Supervisory Control for Arbitrarily-Routed Multi-Tendon Robots via Motion Planning

Tendon-driven robots, where one or more tendons under tension bend and manipulate a flexible backbone, can improve minimally invasive surgeries involving difficult-to-reach regions in the human body. Planning motions safely within constrained anatomical environments requires accuracy and efficiency in shape estimation and collision checking. Tendon robots that employ arbitrarily-routed tendons can achieve complex and interesting shapes, enabling them to travel to difficult-to-reach anatomical regions. Arbitrarily-routed tendon-driven robots have unintuitive nonlinear kinematics. Therefore, we envision clinicians leveraging an assistive interactive-rate motion planner to automatically generate collision-free trajectories to clinician-specified destinations during minimally-invasive surgical procedures. Standard motion-planning techniques cannot achieve interactive-rate motion planning with the current expensive tendon robot kinematic models. In this work, we present a 3-phase motion-planning system for arbitrarily-routed tendon-driven robots with a Precompute phase, a Load phase, and a Supervisory Control phase. Our system achieves an interactive rate by developing a fast kinematic model (over 1,000 times faster than current models), a fast voxel collision method (27.6 times faster than standard methods), and leveraging a precomputed roadmap of the entire robot workspace with pre-voxelized vertices and edges. In simulated experiments, we show that our motion-planning method achieves high tip-position accuracy and generates plans at 14.8 Hz on average in a segmented collapsed lung pleural space anatomical environment. Our results show that our method is 17,700 times faster than popular off-the-shelf motion planning algorithms with standard FK and collision detection approaches. Our open-source code is available online.

Autonomous Medical Needle Steering In Vivo

The use of needles to access sites within organs is fundamental to many interventional medical procedures both for diagnosis and treatment. Safe and accurate navigation of a needle through living tissue to an intra-tissue target is currently often challenging or infeasible due to the presence of anatomical obstacles in the tissue, high levels of uncertainty, and natural tissue motion (e.g., due to breathing). Medical robots capable of automating needle-based procedures in vivo have the potential to overcome these challenges and enable an enhanced level of patient care and safety. In this paper, we show the first medical robot that autonomously navigates a needle inside living tissue around anatomical obstacles to an intra-tissue target. Our system leverages an aiming device and a laser-patterned highly flexible steerable needle, a type of needle capable of maneuvering along curvilinear trajectories to avoid obstacles. The autonomous robot accounts for anatomical obstacles and uncertainty in living tissue/needle interaction with replanning and control and accounts for respiratory motion by defining safe insertion time windows during the breathing cycle. We apply the system to lung biopsy, which is critical in the diagnosis of lung cancer, the leading cause of cancer-related death in the United States. We demonstrate successful performance of our system in multiple in vivo porcine studies and also demonstrate that our approach leveraging autonomous needle steering outperforms a standard manual clinical technique for lung nodule access.