Daniele Meli

Giulio Mazzi, Daniele Meli, Alberto Castellini et al.

Partially Observable Monte Carlo Planning (POMCP) is an efficient solver for Partially Observable Markov Decision Processes (POMDPs). It allows scaling to large state spaces by computing an approximation of the optimal policy locally and online, using a Monte Carlo Tree Search based strategy. However, POMCP suffers from sparse reward function, namely, rewards achieved only when the final goal is reached, particularly in environments with large state spaces and long horizons. Recently, logic specifications have been integrated into POMCP to guide exploration and to satisfy safety requirements. However, such policy-related rules require manual definition by domain experts, especially in real-world scenarios. In this paper, we use inductive logic programming to learn logic specifications from traces of POMCP executions, i.e., sets of belief-action pairs generated by the planner. Specifically, we learn rules expressed in the paradigm of answer set programming. We then integrate them inside POMCP to provide soft policy bias toward promising actions. In the context of two benchmark scenarios, rocksample and battery, we show that the integration of learned rules from small task instances can improve performance with fewer Monte Carlo simulations and in larger task instances. We make our modified version of POMCP publicly available at https://github.com/GiuMaz/pomcp_clingo.git.

Celeste Veronese, Edoardo Zorzi, Daniele Meli et al.

Explainable Reinforcement Learning (XRL) seeks to make Reinforcement Learning (RL) policies more transparent and interpretable, a key requirement in safety-critical and human-centric scenarios. However, it is mostly based on user studies, thus targeting the needs of a specific audience and lacking shared evaluation metrics. On the other hand, logic-based approaches within eXplainable Artificial Intelligence (XAI) provide compact, human-readable abstractions of decision-making. However, the systematic quantification of the explainability degree of logical representations remains an open problem. This work aims to advance the state of the art in XRL by introducing objective and planning-oriented metrics for policy explainability in RL settings. At the same time, it contributes to the field of logic for XAI by providing a principled way to quantify the explainability of logical rules, moving beyond common-sense assessments and simple propositional fragments. We employ Inductive Logic Programming (ILP) to extract symbolic representations of RL policies and define a novel set of explainability metrics, including activation rate, feature coverage, syntactic distance and semantic distance. These metrics quantify alignment between symbolic rules and agent behavior, the role of features in decision-making, and the evolution of policies during training and across agents in single and multi-agent RL. Experiments across different RL domains show that the proposed metrics highlight action-specific learning dynamics beyond global return, provide fine-grained insights into domain features beyond classical approaches for global feature importance estimation, and uncover coordination, specialization, and adaptation patterns in MARL. Moreover, they provide crucial insights for the transfer and generalization of action-specific policies.

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.

Simone Murari, Celeste Veronese, Daniele Meli

Deep Reinforcement Learning (DRL) algorithms often require a large amount of data and struggle in sparse-reward domains with long planning horizons and multiple sub-goals. In this paper, we propose a neuro-symbolic extension of Proximal Policy Optimization (PPO) that transfers partial logical policy specifications learned in easier instances to guide learning in more challenging settings. We introduce two integrations of symbolic guidance: (i) H-PPO-Product, which biases the action distribution at sampling time, and (ii) H-PPO-SymLoss, which augments the PPO loss with a symbolic regularization term. We evaluate our methods on three benchmarks (OfficeWorld, WaterWorld, and DoorKey), showing consistently faster learning and higher return at convergence than PPO and a Reward Machine baseline, also under imperfect symbolic knowledge.

Daniele Meli

Online unsupervised detection of anomalies is crucial to guarantee the correct operation of cyber-physical systems and the safety of humans interacting with them. State-of-the-art approaches based on deep learning via neural networks achieve outstanding performance at anomaly recognition, evaluating the discrepancy between a normal model of the system (with no anomalies) and the real-time stream of sensor time series. However, large training data and time are typically required, and explainability is still a challenge to identify the root of the anomaly and implement predictive maintainance. In this paper, we use causal discovery to learn a normal causal graph of the system, and we evaluate the persistency of causal links during real-time acquisition of sensor data to promptly detect anomalies. On two benchmark anomaly detection datasets, we show that our method has higher training efficiency, outperforms the accuracy of state-of-the-art neural architectures and correctly identifies the sources of >10 different anomalies. The code is at https://github.com/Isla-lab/causal_anomaly_detection.

Daniele Meli, Alberto Castellini, Alessandro Farinelli

Partially Observable Markov Decision Processes (POMDPs) are a powerful framework for planning under uncertainty. They allow to model state uncertainty as a belief probability distribution. Approximate solvers based on Monte Carlo sampling show great success to relax the computational demand and perform online planning. However, scaling to complex realistic domains with many actions and long planning horizons is still a major challenge, and a key point to achieve good performance is guiding the action-selection process with domain-dependent policy heuristics which are tailored for the specific application domain. We propose to learn high-quality heuristics from POMDP traces of executions generated by any solver. We convert the belief-action pairs to a logical semantics, and exploit data- and time-efficient Inductive Logic Programming (ILP) to generate interpretable belief-based policy specifications, which are then used as online heuristics. We evaluate thoroughly our methodology on two notoriously challenging POMDP problems, involving large action spaces and long planning horizons, namely, rocksample and pocman. Considering different state-of-the-art online POMDP solvers, including POMCP, DESPOT and AdaOPS, we show that learned heuristics expressed in Answer Set Programming (ASP) yield performance superior to neural networks and similar to optimal handcrafted task-specific heuristics within lower computational time. Moreover, they well generalize to more challenging scenarios not experienced in the training phase (e.g., increasing rocks and grid size in rocksample, incrementing the size of the map and the aggressivity of ghosts in pocman).

Lorenzo Bonanni, Daniele Meli, Alberto Castellini et al.

Online motion planning is a challenging problem for intelligent robots moving in dense environments with dynamic obstacles, e.g., crowds. In this work, we propose a novel approach for optimal and safe online motion planning with minimal information about dynamic obstacles. Specifically, our approach requires only the current position of the obstacles and their maximum speed, but it does not need any information about their exact trajectories or dynamic model. The proposed methodology combines Monte Carlo Tree Search (MCTS), for online optimal planning via model simulations, with Velocity Obstacles (VO), for obstacle avoidance. We perform experiments in a cluttered simulated environment with walls, and up to 40 dynamic obstacles moving with random velocities and directions. With an ablation study, we show the key contribution of VO in scaling up the efficiency of MCTS, selecting the safest and most rewarding actions in the tree of simulations. Moreover, we show the superiority of our methodology with respect to state-of-the-art planners, including Non-linear Model Predictive Control (NMPC), in terms of improved collision rate, computational and task performance.

Celeste Veronese, Daniele Meli, Alessandro Farinelli

This paper proposes an integration of temporal logical reasoning and Partially Observable Markov Decision Processes (POMDPs) to achieve interpretable decision-making under uncertainty with macro-actions. Our method leverages a fragment of Linear Temporal Logic (LTL) based on Event Calculus (EC) to generate \emph{persistent} (i.e., constant) macro-actions, which guide Monte Carlo Tree Search (MCTS)-based POMDP solvers over a time horizon, significantly reducing inference time while ensuring robust performance. Such macro-actions are learnt via Inductive Logic Programming (ILP) from a few traces of execution (belief-action pairs), thus eliminating the need for manually designed heuristics and requiring only the specification of the POMDP transition model. In the Pocman and Rocksample benchmark scenarios, our learned macro-actions demonstrate increased expressiveness and generality when compared to time-independent heuristics, indeed offering substantial computational efficiency improvements.

Amirhossein Zhalehmehrabi, Daniele Meli, Francesco Dal Santo et al.

Autonomous Surface Vehicles (ASVs) play a crucial role in maritime operations, yet their navigation in shallow-water environments remains challenging due to dynamic disturbances and depth constraints. Traditional navigation strategies struggle with limited sensor information, making safe and efficient operation difficult. In this paper, we propose a reinforcement learning (RL) framework for ASV navigation under depth constraints, where the vehicle must reach a target while avoiding unsafe areas with only a single depth measurement per timestep from a downward-facing Single Beam Echosounder (SBES). To enhance environmental awareness, we integrate Gaussian Process (GP) regression into the RL framework, enabling the agent to progressively estimate a bathymetric depth map from sparse sonar readings. This approach improves decision-making by providing a richer representation of the environment. Furthermore, we demonstrate effective sim-to-real transfer, ensuring that trained policies generalize well to real-world aquatic conditions. Experimental results validate our method's capability to improve ASV navigation performance while maintaining safety in challenging shallow-water environments.

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.

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.