Reinforcement Learning (RL) algorithms can learn robotic control tasks from visual observations, but they often require a large amount of data, especially when the visual scene is complex and unstructured. In this paper, we explore how the agent’s knowledge of its shape can improve the sample efficiency of visual RL methods. We propose a novel method, Disentangled Environment and Agent Representations (DEAR), that uses the segmentation mask of the agent as supervision to learn disentangled representations of the environment and the agent through feature separation constraints. Unlike previous approaches, DEAR does not require reconstruction of visual observations. These representations are then used as an auxiliary loss to the RL objective, encouraging the agent to focus on the relevant features of the environment. We evaluate DEAR on two challenging benchmarks: Distracting DeepMind control suite and Franka Kitchen manipulation tasks. Our findings demonstrate that DEAR surpasses state-of-the-art methods in sample efficiency, achieving comparable or superior performance with reduced parameters. Our results indicate that integrating agent knowledge into visual RL methods has the potential to enhance their learning efficiency and robustness.

The field of robotic Flexible Endoscopes (FEs) has progressed significantly, offering a promising solution to reduce patient discomfort. However, the limited autonomy of most robotic FEs results in non-intuitive and challenging manoeuvres, constraining their application in clinical settings. While previous studies have employed lumen tracking for autonomous navigation, they fail to adapt to the presence of obstructions and sharp turns when the endoscope faces the colon wall. In this work, we propose a Deep Reinforcement Learning (DRL)-based navigation strategy that eliminates the need for lumen tracking. However, the use of DRL methods poses safety risks as they do not account for potential hazards associated with the actions taken. To ensure safety, we exploit a Constrained Reinforcement Learning (CRL) method to restrict the policy in a predefined safety regime. Moreover, we present a model selection strategy that utilises Formal Verification (FV) to choose a policy that is entirely safe before deployment. We validate our approach in a virtual colonoscopy environment and report that out of the 300 trained policies, we could identify three policies that are entirely safe. Our work demonstrates that CRL, combined with model selection through FV, can improve the robustness and safety of robotic behaviour in surgical applications.

Increased demand for less invasive procedures has accelerated the adoption of Intraluminal Procedures (IP) and Endovascular Interventions (EI) performed through body lumens and vessels. As navigation through lumens and vessels is quite complex, interest grows to establish autonomous navigation techniques for IP and EI for reaching the target area. Current research efforts are directed toward increasing the Level of Autonomy (LoA) during the navigation phase. One key ingredient for autonomous navigation is Motion Planning (MP) techniques. This paper provides an overview of MP techniques categorizing them based on LoA. Our analysis investigates advances for the different clinical scenarios. Through a systematic literature analysis using the PRISMA method, the study summarizes relevant works and investigates the clinical aim, LoA, adopted MP techniques, and validation types. We identify the limitations of the corresponding MP methods and provide directions to improve the robustness of the algorithms in dynamic intraluminal environments. MP for IP and EI can be classified into four subgroups: node, sampling, optimization, and learning-based techniques, with a notable rise in learning-based approaches in recent years. One of the review's contributions is the identification of the limiting factors in IP and EI robotic systems hindering higher levels of autonomous navigation. In the future, navigation is bound to become more autonomous, placing the clinician in a supervisory position to improve control precision and reduce workload.

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.

Deep Reinforcement Learning (DRL) is a viable solution for automating repetitive surgical subtasks due to its ability to learn complex behaviours in a dynamic environment. This task automation could lead to reduced surgeon’s cognitive workload, increased precision in critical aspects of the surgery, and fewer patient-related complications. However, current DRL methods do not guarantee any safety criteria as they maximise cumulative rewards without considering the risks associated with the actions performed. Due to this limitation, the application of DRL in the safety-critical paradigm of robot-assisted Minimally Invasive Surgery (MIS) has been constrained. In this work, we introduce a Safe-DRL framework that incorporates safety constraints for the automation of surgical subtasks via DRL training. We validate our approach in a virtual scene that replicates a tissue retraction task commonly occurring in multiple phases of an MIS. Furthermore, to evaluate the safe behaviour of the robotic arms, we formulate a formal verification tool for DRL methods that provides the probability of unsafe configurations. Our results indicate that a formal analysis guarantees safety with high confidence such that the robotic instruments operate within the safe workspace and avoid hazardous interaction with other anatomical structures.

We present a behaviour-based reinforcement learning approach, inspired by Brook's subsumption architecture, in which simple fully connected networks are trained as reactive behaviours. Our working assumption is that a pick and place robotic task can be simplified by leveraging domain knowledge of a robotics developer to decompose and train reactive behaviours; namely, approach, grasp, and retract. Then the robot autonomously learns how to combine reactive behaviours via an Actor-Critic architecture. We use an Actor-Critic policy to determine the activation and inhibition mechanisms of the reactive behaviours in a particular temporal sequence. We validate our approach in a simulated robot environment where the task is about picking a block and taking it to a target position while orienting the gripper from a top grasp. The latter represents an extra degree-of-freedom of which current end-to-end reinforcement learning approaches fail to generalise. Our findings suggest that robotic learning can be more effective if each behaviour is learnt in isolation and then combined them to accomplish the task. That is, our approach learns the pick and place task in 8,000 episodes, which represents a drastic reduction in the number of training episodes required by an end-to-end approach ( 95,000 episodes) and existing state-of-the-art algorithms.

Reinforcement Learning (RL) methods have demonstrated promising results for the automation of subtasks in surgical robotic systems. Since many trial and error attempts are required to learn the optimal control policy, RL agent training can be performed in simulation and the learned behavior can be then deployed in real environments. In this work, we introduce an open-source simulation environment providing support for position based dynamics soft bodies simulation and state-of-the-art RL methods. We demonstrate the capabilities of the proposed framework by training an RL agent based on Proximal Policy Optimization in fat tissue manipulation for tumor exposure during a nephrectomy procedure. Leveraging on a preliminary optimization of the simulation parameters, we show that our agent is able to learn the task on a virtual replica of the anatomical environment. The learned behavior is robust to changes in the initial end-effector position. Furthermore, we show that the learned policy can be directly deployed on the da Vinci Research Kit, which is able to execute the trajectories generated by the RL agent. The proposed simulation environment represents an essential component for the development of next-generation robotic systems, where the interaction with the deformable anatomical environment is involved.