Flexible Endoscopes (FEs) for colonoscopy present several limitations due to their inherent complexity, resulting in patient discomfort and lack of intuitiveness for clinicians. Robotic FEs with autonomous control represent a viable solution to reduce the workload of endoscopists and the training time while improving the procedure outcome. Prior works on autonomous endoscope FE control use heuristic policies that limit their generalisation to the unstructured and highly deformable colon environment and require frequent human intervention. This work proposes an image-based FE control using Deep Reinforcement Learning, called Deep Visuomotor Control (DVC), to exhibit adaptive behaviour in convoluted sections of the colon. DVC learns a mapping between the images and the FE control signal. A first user study of 20 expert gastrointestinal endoscopists was carried out to compare their navigation performance with DVC using a realistic virtual simulator. The results indicate that DVC shows equivalent performance on several assessment parameters, being more safer. Moreover, a second user study with 20 novice users was performed to demonstrate easier human supervision compared to a state-of-the-art heuristic control policy. Seamless supervision of colonoscopy procedures would enable endoscopists to focus on the medical decision rather than on the control of FE.

Since the emergence of soft robotics around two decades ago, research interest in the field has escalated at a pace. It is fuelled by the industry’s appreciation of the wide range of soft materials available that can be used to create highly dexterous robots with adaptability characteristics far beyond that which can be achieved with rigid component devices. The ability, inherent in soft robots, to compliantly adapt to the environment, has significantly sparked interest from the surgical robotics community. This article provides an in-depth overview of recent progress and outlines the remaining challenges in the development of soft robotics for minimally invasive surgery.

Soft material robots offer a number of advantages over traditional rigid robots in applications including human-robot interaction, rehabilitation and surgery. These robots can navigate around obstacles, elongate, squeeze through narrow openings or be squeezed - and they are considered to be inherently safe. The ability to stiffen compliant soft actuators has been achieved by embedding various mechanisms that are generally decoupled from the actuation principle. Miniaturisation becomes challenging due to space limitations which can in turn result in diminution of stiffening effects. Here, we propose to hydraulically actuate soft manipulators with low-melting-point material and, at the same time, be able to switch between a soft and stiff state. Instead of allocating an additional stiffening chamber within the soft robot, one chamber only is used for actuation and stiffening. Low Melting Point Alloy is integrated into the actuation chamber of a single-compartment soft robotic manipulator and the interfaced robotic syringe pump. Temperature change is enabled through embedded nichrome wires. Our experimental results show higher stiffness factors, from 9-12 opposing the motion of curvature, than those previously found for jamming mechanisms incorporated in separate additional chambers, in the range of 2-8 for the same motion.

Wireless capsule endoscopy offers significant advantages compared with traditional endoscopic procedures, since it limits the invasiveness of gastrointestinal tract screening and diagnosis. Moreover, active locomotion devices would allow endoscopy to be performed in a totally controlled manner, avoiding failures in the correct visualization of pathologies. Previous works demonstrated that magnetic locomotion through a robotic-aided platform would allow us to reach this goal reliably. In this paper, the authors present a comparative evaluation of control methodologies and user interfaces for a robotic-aided magnetic platform for capsule endoscopy, controlled through human-robot cooperative and teleoperated control algorithms. A detailed statistical analysis of significant control parameters was performed: teleoperated control is the more reliable control approach, and a serial kinematic haptic device results as the most suitable control interface to perform effective robotic-aided endoscopic procedures.