Publications (26)
Curriculum Learning with a Progression Function
Andrea Bassich, Francesco Foglino, Matteo Leonetti +1
Curriculum Learning for Reinforcement Learning is an increasingly popular technique that involves training an agent on a sequence of intermediate tasks, called a Curriculum, to inc…
Occlusion-Aware Search for Object Retrieval in Clutter
Wissam Bejjani, Wisdom C. Agboh, Mehmet R. Dogar +1
We address the manipulation task of retrieving a target object from a cluttered shelf. When the target object is hidden, the robot must search through the clutter for retrieving it…
Planning with a Receding Horizon for Manipulation in Clutter using a Learned Value Function
Wissam Bejjani, Rafael Papallas, Matteo Leonetti +1
Manipulation in clutter requires solving complex sequential decision making problems in an environment rich with physical interactions. The transfer of motion planning solutions fr…
Visual-Tactile Peg-in-Hole Assembly Learning from Peg-out-of-Hole Disassembly
Yongqiang Zhao, Xuyang Zhang, Zhuo Chen +3
Peg-in-hole (PiH) assembly is a fundamental yet challenging robotic manipulation task. While reinforcement learning (RL) has shown promise in tackling such tasks, it requires exten…
AI-HRI 2021 Proceedings
Reuth Mirsky, Megan Zimmerman, Muneed Ahmad +10
The Artificial Intelligence (AI) for Human-Robot Interaction (HRI) Symposium has been a successful venue of discussion and collaboration since 2014. During that time, these symposi…
Human-like Planning for Reaching in Cluttered Environments
Mohamed Hasan, Matthew Warburton, Wisdom C. Agboh +6
Humans, in comparison to robots, are remarkably adept at reaching for objects in cluttered environments. The best existing robot planners are based on random sampling of configurat…
A Utility Maximization Model of Pedestrian and Driver Interactions
Yi-Shin Lin, Aravinda Ramakrishnan Srinivasan, Matteo Leonetti +2
Many models account for the traffic flow of road users but few take the details of local interactions into consideration and how they could deteriorate into safety-critical situati…
A gray-box approach for curriculum learning
Francesco Foglino, Matteo Leonetti, Simone Sagratella +1
Curriculum learning is often employed in deep reinforcement learning to let the agent progress more quickly towards better behaviors. Numerical methods for curriculum learning in t…
The COMMOTIONS Urban Interactions Driving Simulator Study Dataset
Aravinda Ramakrishnan Srinivasan, Julian Schumann, Yueyang Wang +7
Accurate modelling of road user interaction has received lot of attention in recent years due to the advent of increasingly automated vehicles. To support such modelling, there is…
Partner Capability Estimation for Task-Agnostic Adaptation in Ad-Hoc Teamwork
Peter Tisnikar, Maja Swieczkowska, Benteng Ma +2
The paper proposes a Bayesian method (CE-CM) for estimating hidden partner capabilities in multi‑task ad‑hoc teamwork, allowing agents to plan with decentralized execution and adap…
Proceedings of the AI-HRI Symposium at AAAI-FSS 2022
Zhao Han, Emmanuel Senft, Muneeb I. Ahmad +12
The Artificial Intelligence (AI) for Human-Robot Interaction (HRI) Symposium has been a successful venue of discussion and collaboration on AI theory and methods aimed at HRI since…
Comparing merging behaviors observed in naturalistic data with behaviors generated by a machine learned model
Aravinda Ramakrishnan Srinivasan, Mohamed Hasan, Yi-Shin Lin +4
There is quickly growing literature on machine-learned models that predict human driving trajectories in road traffic. These models focus their learning on low-dimensional error me…
Learning Physics-Based Manipulation in Clutter: Combining Image-Based Generalization and Look-Ahead Planning
Wissam Bejjani, Mehmet R. Dogar, Matteo Leonetti
Physics-based manipulation in clutter involves complex interaction between multiple objects. In this paper, we consider the problem of learning, from interaction in a physics simul…
Curriculum Learning for Cumulative Return Maximization
Francesco Foglino, Christiano Coletto Christakou, Ricardo Luna Gutierrez +1
Curriculum learning has been successfully used in reinforcement learning to accelerate the learning process, through knowledge transfer between tasks of increasing complexity. Crit…
Proceedings of the AI-HRI Symposium at AAAI-FSS 2019
Justin W. Hart, Nick DePalma, Richard G. Freedman +8
The past few years have seen rapid progress in the development of service robots. Universities and companies alike have launched major research efforts toward the deployment of amb…
Learning Social Cost Functions for Human-Aware Path Planning
Andrea Eirale, Matteo Leonetti, Marcello Chiaberge
Achieving social acceptance is one of the main goals of Social Robotic Navigation. Despite this topic has received increasing interest in recent years, most of the research has foc…
Beyond RMSE: Do machine-learned models of road user interaction produce human-like behavior?
Aravinda Ramakrishnan Srinivasan, Yi-Shin Lin, Morris Antonello +9
Autonomous vehicles use a variety of sensors and machine-learned models to predict the behavior of surrounding road users. Most of the machine-learned models in the literature focu…
An Optimization Framework for Task Sequencing in Curriculum Learning
Francesco Foglino, Christiano Coletto Christakou, Matteo Leonetti
Curriculum learning in reinforcement learning is used to shape exploration by presenting the agent with increasingly complex tasks. The idea of curriculum learning has been largely…
Imitation Learning for Adaptive Control of a Virtual Soft Exoglove
Shirui Lyu, Vittorio Caggiano, Matteo Leonetti +2
The use of wearable robots has been widely adopted in rehabilitation training for patients with hand motor impairments. However, the uniqueness of patients' muscle loss is often ov…
Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey
Sanmit Narvekar, Bei Peng, Matteo Leonetti +3
Reinforcement learning (RL) is a popular paradigm for addressing sequential decision tasks in which the agent has only limited environmental feedback. Despite many advances over th…
Proceedings of the AI-HRI Symposium at AAAI-FSS 2020
Shelly Bagchi, Jason R. Wilson, Muneeb I. Ahmad +9
The Artificial Intelligence (AI) for Human-Robot Interaction (HRI) Symposium has been a successful venue of discussion and collaboration since 2014. In that time, the related topic…
Realizable Abstractions: Near-Optimal Hierarchical Reinforcement Learning
Roberto Cipollone, Luca Iocchi, Matteo Leonetti
The main focus of Hierarchical Reinforcement Learning (HRL) is studying how large Markov Decision Processes (MDPs) can be more efficiently solved when addressed in a modular way, b…
Towards Generalisable Imitation Learning Through Conditioned Transition Estimation and Online Behaviour Alignment
Nathan Gavenski, Matteo Leonetti, Odinaldo Rodrigues
State-of-the-art imitation learning from observation methods (ILfO) have recently made significant progress, but they still have some limitations: they need action-based supervised…
Learning Social Heuristics for Human-Aware Path Planning
Andrea Eirale, Matteo Leonetti, Marcello Chiaberge
Social robotic navigation has been at the center of numerous studies in recent years. Most of the research has focused on driving the robotic agent along obstacle-free trajectories…
Information-theoretic Task Selection for Meta-Reinforcement Learning
Ricardo Luna Gutierrez, Matteo Leonetti
In Meta-Reinforcement Learning (meta-RL) an agent is trained on a set of tasks to prepare for and learn faster in new, unseen, but related tasks. The training tasks are usually han…
Meta-Reinforcement Learning for Heuristic Planning
Ricardo Luna Gutierrez, Matteo Leonetti
In Meta-Reinforcement Learning (meta-RL) an agent is trained on a set of tasks to prepare for and learn faster in new, unseen, but related tasks. The training tasks are usually han…