Paolo Fiorini

Ameya Pore, Martina Finocchiaro, Diego Dall'Alba et al.

Flexible endoscopes for colonoscopy present several limitations due to their inherent complexity, resulting in patient discomfort and lack of intuitiveness for clinicians. Robotic devices together with autonomous control represent a viable solution to reduce the workload of endoscopists and the training time while improving the overall procedure outcome. Prior works on autonomous endoscope 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 control of the endoscope using Deep Reinforcement Learning, called Deep Visuomotor Control (DVC), to exhibit adaptive behaviour in convoluted sections of the colon tract. DVC learns a mapping between the endoscopic images and the control signal of the endoscope. A first user study of 20 expert gastrointestinal endoscopists was carried out to compare their navigation performance with DVC policies 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 participants was performed to demonstrate easier human supervision compared to a state-of-the-art heuristic control policy. Seamless supervision of colonoscopy procedures would enable interventionists to focus on the medical decision rather than on the control problem of the endoscope.

Sanat Ramesh, Diego Dall'Alba, Cristians Gonzalez et al.

Automatic recognition of fine-grained surgical activities, called steps, is a challenging but crucial task for intelligent intra-operative computer assistance. The development of current vision-based activity recognition methods relies heavily on a high volume of manually annotated data. This data is difficult and time-consuming to generate and requires domain-specific knowledge. In this work, we propose to use coarser and easier-to-annotate activity labels, namely phases, as weak supervision to learn step recognition with fewer step annotated videos. We introduce a step-phase dependency loss to exploit the weak supervision signal. We then employ a Single-Stage Temporal Convolutional Network (SS-TCN) with a ResNet-50 backbone, trained in an end-to-end fashion from weakly annotated videos, for temporal activity segmentation and recognition. We extensively evaluate and show the effectiveness of the proposed method on a large video dataset consisting of 40 laparoscopic gastric bypass procedures and the public benchmark CATARACTS containing 50 cataract surgeries.

Daniele Meli, Hirenkumar Nakawala, Paolo Fiorini

Over the last decade, the use of robots in production and daily life has increased. With increasingly complex tasks and interaction in different environments including humans, robots are required a higher level of autonomy for efficient deliberation. Task planning is a key element of deliberation. It combines elementary operations into a structured plan to satisfy a prescribed goal, given specifications on the robot and the environment. In this manuscript, we present a survey on recent advances in the application of logic programming to the problem of task planning. Logic programming offers several advantages compared to other approaches, including greater expressivity and interpretability which may aid in the development of safe and reliable robots. We analyze different planners and their suitability for specific robotic applications, based on expressivity in domain representation, computational efficiency and software implementation. In this way, we support the robotic designer in choosing the best tool for his application.

Giovanni Menegozzo, Diego Dall'Alba, Paolo Fiorini

Causal relationships are commonly examined in manufacturing processes to support faults investigations, perform interventions, and make strategic decisions. Industry 4.0 has made available an increasing amount of data that enable data-driven Causal Discovery (CD). Considering the growing number of recently proposed CD methods, it is necessary to introduce strict benchmarking procedures on publicly available datasets since they represent the foundation for a fair comparison and validation of different methods. This work introduces two novel public datasets for CD in continuous manufacturing processes. The first dataset employs the well-known Tennessee Eastman simulator for fault detection and process control. The second dataset is extracted from an ultra-processed food manufacturing plant, and it includes a description of the plant, as well as multiple ground truths. These datasets are used to propose a benchmarking procedure based on different metrics and evaluated on a wide selection of CD algorithms. This work allows testing CD methods in realistic conditions enabling the selection of the most suitable method for specific target applications. The datasets are available at the following link: https://github.com/giovanniMen

Michele Ginesi, Paolo Fiorini

Latent variable models are widely used to perform unsupervised segmentation of time series in different context such as robotics, speech recognition, and economics. One of the most widely used latent variable model is the Auto-Regressive Hidden Markov Model (ARHMM), which combines a latent mode governed by a Markov chain dynamics with a linear Auto-Regressive dynamics of the observed state. In this work, we propose two generalizations of the ARHMM. First, we propose a more general AR dynamics in Cartesian space, described as a linear combination of non-linear basis functions. Second, we propose a linear dynamics in unit quaternion space, in order to properly describe orientations. These extensions allow to describe more complex dynamics of the observed state. Although this extension is proposed for the ARHMM, it can be easily extended to other latent variable models with AR dynamics in the observed space, such as Auto-Regressive Hidden semi-Markov Models.

Joel L. Lavanchy, Sanat Ramesh, Diego Dall'Alba et al.

Most studies on surgical activity recognition utilizing Artificial intelligence (AI) have focused mainly on recognizing one type of activity from small and mono-centric surgical video datasets. It remains speculative whether those models would generalize to other centers. In this work, we introduce a large multi-centric multi-activity dataset consisting of 140 videos (MultiBypass140) of laparoscopic Roux-en-Y gastric bypass (LRYGB) surgeries performed at two medical centers: the University Hospital of Strasbourg (StrasBypass70) and Inselspital, Bern University Hospital (BernBypass70). The dataset has been fully annotated with phases and steps. Furthermore, we assess the generalizability and benchmark different deep learning models in 7 experimental studies: 1) Training and evaluation on BernBypass70; 2) Training and evaluation on StrasBypass70; 3) Training and evaluation on the MultiBypass140; 4) Training on BernBypass70, evaluation on StrasBypass70; 5) Training on StrasBypass70, evaluation on BernBypass70; Training on MultiBypass140, evaluation 6) on BernBypass70 and 7) on StrasBypass70. The model's performance is markedly influenced by the training data. The worst results were obtained in experiments 4) and 5) confirming the limited generalization capabilities of models trained on mono-centric data. The use of multi-centric training data, experiments 6) and 7), improves the generalization capabilities of the models, bringing them beyond the level of independent mono-centric training and validation (experiments 1) and 2)). MultiBypass140 shows considerable variation in surgical technique and workflow of LRYGB procedures between centers. Therefore, generalization experiments demonstrate a remarkable difference in model performance. These results highlight the importance of multi-centric datasets for AI model generalization to account for variance in surgical technique and workflows.

Daniele Meli, Paolo Fiorini

The increasing level of autonomy of robots poses challenges of trust and social acceptance, especially in human-robot interaction scenarios. This requires an interpretable implementation of robotic cognitive capabilities, possibly based on formal methods as logics for the definition of task specifications. However, prior knowledge is often unavailable in complex realistic scenarios. In this paper, we propose an offline algorithm based on inductive logic programming from noisy examples to extract task specifications (i.e., action preconditions, constraints and effects) directly from raw data of few heterogeneous (i.e., not repetitive) robotic executions. Our algorithm leverages on the output of any unsupervised action identification algorithm from video-kinematic recordings. Combining it with the definition of very basic, almost task-agnostic, commonsense concepts about the environment, which contribute to the interpretability of our methodology, we are able to learn logical axioms encoding preconditions of actions, as well as their effects in the event calculus paradigm. Since the quality of learned specifications depends mainly on the accuracy of the action identification algorithm, we also propose an online framework for incremental refinement of task knowledge from user feedback, guaranteeing safe execution. Results in a standard manipulation task and benchmark for user training in the safety-critical surgical robotic scenario, show the robustness, data- and time-efficiency of our methodology, with promising results towards the scalability in more complex domains.

Marco Bombieri, Paolo Fiorini, Simone Paolo Ponzetto et al.

Large Language Models (LLMs) have demonstrated remarkable performance across diverse natural language processing tasks, yet their ability to memorize structured knowledge remains underexplored. In this paper, we investigate the extent to which general-purpose pre-trained LLMs retain and correctly reproduce concept identifier (ID)-label associations from publicly available ontologies. We conduct a systematic evaluation across multiple ontological resources, including the Gene Ontology, Uberon, Wikidata, and ICD-10, using LLMs such as Pythia-12B, Gemini-1.5-Flash, GPT-3.5, and GPT-4. Our findings reveal that only a small fraction of ontological concepts is accurately memorized, with GPT-4 demonstrating the highest performance. To understand why certain concepts are memorized more effectively than others, we analyze the relationship between memorization accuracy and concept popularity on the Web. Our results indicate a strong correlation between the frequency of a concept's occurrence online and the likelihood of accurately retrieving its ID from the label. This suggests that LLMs primarily acquire such knowledge through indirect textual exposure rather than directly from structured ontological resources. Furthermore, we introduce new metrics to quantify prediction invariance, demonstrating that the stability of model responses across variations in prompt language and temperature settings can serve as a proxy for estimating memorization robustness.

Ameya Pore, Eleonora Tagliabue, Marco Piccinelli et al.

The current research focus in Robot-Assisted Minimally Invasive Surgery (RAMIS) is directed towards increasing the level of robot autonomy, to place surgeons in a supervisory position. Although Learning from Demonstrations (LfD) approaches are among the preferred ways for an autonomous surgical system to learn expert gestures, they require a high number of demonstrations and show poor generalization to the variable conditions of the surgical environment. In this work, we propose an LfD methodology based on Generative Adversarial Imitation Learning (GAIL) that is built on a Deep Reinforcement Learning (DRL) setting. GAIL combines generative adversarial networks to learn the distribution of expert trajectories with a DRL setting to ensure generalisation of trajectories providing human-like behaviour. We consider automation of tissue retraction, a common RAMIS task that involves soft tissues manipulation to expose a region of interest. In our proposed methodology, a small set of expert trajectories can be acquired through the da Vinci Research Kit (dVRK) and used to train the proposed LfD method inside a simulated environment. Results indicate that our methodology can accomplish the tissue retraction task with human-like behaviour while being more sample-efficient than the baseline DRL method. Towards the end, we show that the learnt policies can be successfully transferred to the real robotic platform and deployed for soft tissue retraction on a synthetic phantom.

Ameya Pore, Davide Corsi, Enrico Marchesini et al.

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.

Morteza Daneshmand, Fatemeh Noroozi, Ciprian Corneanu et al.

Despite their contributions to the financial efficiency and environmental sustainability of industrial processes, robotic assembly and disassembly have been understudied in the existing literature. This is in contradiction to their importance in realizing the Fourth Industrial Revolution. More specifically, although most of the literature has extensively discussed how to optimally assemble or disassemble given products, the role of other factors has been overlooked. For example, the types of robots involved in implementing the sequence plans, which should ideally be taken into account throughout the whole chain consisting of design, assembly, disassembly and reassembly. Isolating the foregoing operations from the rest of the components of the relevant ecosystems may lead to erroneous inferences toward both the necessity and efficiency of the underlying procedures. In this paper we try to alleviate these shortcomings by comprehensively investigating the state-of-the-art in robotic assembly and disassembly. We consider and review various aspects of manufacturing and remanufacturing frameworks while particularly focusing on their desirability for supporting a circular economy.

Daniele Meli, Paolo Fiorini

Robot-assisted surgery is an established clinical practice. The automatic identification of surgical actions is needed for a range of applications, including performance assessment of trainees and surgical process modeling for autonomous execution and monitoring. However, supervised action identification is not feasible, due to the burden of manually annotating recordings of potentially complex and long surgical executions. Moreover, often few example executions of a surgical procedure can be recorded. This paper proposes a novel fast algorithm for unsupervised identification of surgical actions in a standard surgical training task, the ring transfer, executed with da Vinci Research Kit. Exploiting kinematic and semantic visual features automatically extracted from a very limited dataset of executions, we are able to significantly outperform state-of-the-art results on a dataset of non-expert executions (58\% vs. 24\% F1-score), and improve performance in the presence of noise, short actions and non-homogeneous workflows, i.e. non repetitive action sequences.

Sanat Ramesh, Diego Dall'Alba, Cristians Gonzalez et al.

Purpose: Automatic segmentation and classification of surgical activity is crucial for providing advanced support in computer-assisted interventions and autonomous functionalities in robot-assisted surgeries. Prior works have focused on recognizing either coarse activities, such as phases, or fine-grained activities, such as gestures. This work aims at jointly recognizing two complementary levels of granularity directly from videos, namely phases and steps. Method: We introduce two correlated surgical activities, phases and steps, for the laparoscopic gastric bypass procedure. We propose a Multi-task Multi-Stage Temporal Convolutional Network (MTMS-TCN) along with a multi-task Convolutional Neural Network (CNN) training setup to jointly predict the phases and steps and benefit from their complementarity to better evaluate the execution of the procedure. We evaluate the proposed method on a large video dataset consisting of 40 surgical procedures (Bypass40). Results: We present experimental results from several baseline models for both phase and step recognition on the Bypass40 dataset. The proposed MTMS-TCN method outperforms in both phase and step recognition by 1-2% in accuracy, precision and recall, compared to single-task methods. Furthermore, for step recognition, MTMS-TCN achieves a superior performance of 3-6% compared to LSTM based models in accuracy, precision, and recall. Conclusion: In this work, we present a multi-task multi-stage temporal convolutional network for surgical activity recognition, which shows improved results compared to single-task models on the Bypass40 gastric bypass dataset with multi-level annotations. The proposed method shows that the joint modeling of phases and steps is beneficial to improve the overall recognition of each type of activity.

Luca Marzari, Ameya Pore, Diego Dall'Alba et al.

Deep Reinforcement Learning (DRL) is emerging as a promising approach to generate adaptive behaviors for robotic platforms. However, a major drawback of using DRL is the data-hungry training regime that requires millions of trial and error attempts, which is impractical when running experiments on robotic systems. Learning from Demonstrations (LfD) has been introduced to solve this issue by cloning the behavior of expert demonstrations. However, LfD requires a large number of demonstrations that are difficult to be acquired since dedicated complex setups are required. To overcome these limitations, we propose a multi-subtask reinforcement learning methodology where complex pick and place tasks can be decomposed into low-level subtasks. These subtasks are parametrized as expert networks and learned via DRL methods. Trained subtasks are then combined by a high-level choreographer to accomplish the intended pick and place task considering different initial configurations. As a testbed, we use a pick and place robotic simulator to demonstrate our methodology and show that our method outperforms a benchmark methodology based on LfD in terms of sample-efficiency. We transfer the learned policy to the real robotic system and demonstrate robust grasping using various geometric-shaped objects.

Andrea Roberti, Nicola Piccinelli, Daniele Meli et al.

Autonomy is the frontier of research in robotic surgery and its aim is to improve the quality of surgical procedures in the next future. One fundamental requirement for autonomy is advanced perception capability through vision sensors. In this paper, we propose a novel calibration technique for a surgical scenario with da Vinci robot. Calibration of the camera and the robot is necessary for precise positioning of the tools in order to emulate the high performance surgeons. Our calibration technique is tailored for RGB-D camera. Different tests performed on relevant use cases for surgery prove that we significantly improve precision and accuracy with respect to the state of the art solutions for similar devices on a surgical-size setup. Moreover, our calibration method can be easily extended to standard surgical endoscope to prompt its use in real surgical scenario.

Michele Ginesi, Daniele Meli, Andrea Roberti et al.

Obstacle avoidance for DMPs is still a challenging problem. In our previous work, we proposed a framework for obstacle avoidance based on superquadric potential functions to represent volumes. In this work, we extend our previous work to include the velocity of the trajectory in the definition of the potential. Our formulations guarantee smoother behavior with respect to state-of-the-art point-like methods. Moreover, our new formulation allows to obtain a smoother behavior in proximity of the obstacle than when using a static (i.e. velocity independent) potential. We validate our framework for obstacle avoidance in a simulated multi-robot scenario and with different real robots: a pick-and-place task for an industrial manipulator and a surgical robot to show scalability; and navigation with a mobile robot in dynamic environment.

Michele Ginesi, Daniele Meli, Andrea Roberti et al.

The use of robots in minimally invasive surgery has improved the quality of standard surgical procedures. So far, only the automation of simple surgical actions has been investigated by researchers, while the execution of structured tasks requiring reasoning on the environment and the choice among multiple actions is still managed by human surgeons. In this paper, we propose a framework to implement surgical task automation. The framework consists of a task-level reasoning module based on answer set programming, a low-level motion planning module based on dynamic movement primitives, and a situation awareness module. The logic-based reasoning module generates explainable plans and is able to recover from failure conditions, which are identified and explained by the situation awareness module interfacing to a human supervisor, for enhanced safety. Dynamic Movement Primitives allow to replicate the dexterity of surgeons and to adapt to obstacles and changes in the environment. The framework is validated on different versions of the standard surgical training peg-and-ring task.

Michele Ginesi, Nicola Sansonetto, Paolo Fiorini

Dynamic Movement Primitives (DMPs) is a framework for learning a point-to-point trajectory from a demonstration. Despite being widely used, DMPs still present some shortcomings that may limit their usage in real robotic applications. Firstly, at the state of the art, mainly Gaussian basis functions have been used to perform function approximation. Secondly, the adaptation of the trajectory generated by the DMP heavily depends on the choice of hyperparameters and the new desired goal position. Lastly, DMPs are a framework for `one-shot learning', meaning that they are constrained to learn from a unique demonstration. In this work, we present and motivate a new set of basis functions to be used in the learning process, showing their ability to accurately approximate functions while having both analytical and numerical advantages w.r.t. Gaussian basis functions. Then, we show how to use the invariance of DMPs w.r.t. affine transformations to make the generalization of the trajectory robust against both the choice of hyperparameters and new goal position, performing both synthetic tests and experiments with real robots to show this increased robustness. Finally, we propose an algorithm to extract a common behavior from multiple observations, validating it both on a synthetic dataset and on a dataset obtained by performing a task on a real robot.