14 citations · 31 across the 12 of their papers we have counts for
12 papers
Aquatic Navigation: A Challenging Benchmark for Deep Reinforcement Learning
Davide Corsi, Davide Camponogara, Alessandro Farinelli
An exciting and promising frontier for Deep Reinforcement Learning (DRL) is its application to real-world robotic systems. While modern DRL approaches achieved remarkable successes…
Analyzing Adversarial Inputs in Deep Reinforcement Learning
Davide Corsi, Guy Amir, Guy Katz +1
In recent years, Deep Reinforcement Learning (DRL) has become a popular paradigm in machine learning due to its successful applications to real-world and complex systems. However,…
Enumerating Safe Regions in Deep Neural Networks with Provable Probabilistic Guarantees
Luca Marzari, Davide Corsi, Enrico Marchesini +2
Identifying safe areas is a key point to guarantee trust for systems that are based on Deep Neural Networks (DNNs). To this end, we introduce the AllDNN-Verification problem: given…
Formally Explaining Neural Networks within Reactive Systems
Shahaf Bassan, Guy Amir, Davide Corsi +2
Deep neural networks (DNNs) are increasingly being used as controllers in reactive systems. However, DNNs are highly opaque, which renders it difficult to explain and justify their…
Constrained Reinforcement Learning and Formal Verification for Safe Colonoscopy Navigation
Davide Corsi, Luca Marzari, Ameya Pore +4
The field of robotic Flexible Endoscopes (FEs) has progressed significantly, offering a promising solution to reduce patient discomfort. However, the limited autonomy of most robot…
The #DNN-Verification Problem: Counting Unsafe Inputs for Deep Neural Networks
Luca Marzari, Davide Corsi, Ferdinando Cicalese +1
Deep Neural Networks are increasingly adopted in critical tasks that require a high level of safety, e.g., autonomous driving. While state-of-the-art verifiers can be employed to c…
Constrained Reinforcement Learning for Robotics via Scenario-Based Programming
Davide Corsi, Raz Yerushalmi, Guy Amir +3
Deep reinforcement learning (DRL) has achieved groundbreaking successes in a wide variety of robotic applications. A natural consequence is the adoption of this paradigm for safety…
Verifying Learning-Based Robotic Navigation Systems
Guy Amir, Davide Corsi, Raz Yerushalmi +4
Deep reinforcement learning (DRL) has become a dominant deep-learning paradigm for tasks where complex policies are learned within reactive systems. Unfortunately, these policies a…
Curriculum Learning for Safe Mapless Navigation
Luca Marzari, Davide Corsi, Enrico Marchesini +1
This work investigates the effects of Curriculum Learning (CL)-based approaches on the agent's performance. In particular, we focus on the safety aspect of robotic mapless navigati…
Benchmarking Safe Deep Reinforcement Learning in Aquatic Navigation
Enrico Marchesini, Davide Corsi, Alessandro Farinelli
We propose a novel benchmark environment for Safe Reinforcement Learning focusing on aquatic navigation. Aquatic navigation is an extremely challenging task due to the non-stationa…
Safe Reinforcement Learning using Formal Verification for Tissue Retraction in Autonomous Robotic-Assisted Surgery
Ameya Pore, Davide Corsi, Enrico Marchesini +4
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 tas…
Evaluating the Safety of Deep Reinforcement Learning Models using Semi-Formal Verification
Davide Corsi, Enrico Marchesini, Alessandro Farinelli
Groundbreaking successes have been achieved by Deep Reinforcement Learning (DRL) in solving practical decision-making problems. Robotics, in particular, can involve high-cost hardw…