• Publications
  • Influence
RAWSEEDS: Robotics Advancement through Web-publishing of Sensorial and Elaborated Extensive Data Sets
The absence of standard benchmarks is an acknowledged problem in the field of robotics, and is doubly harmful to it. First, it prevents recognition of scientific and technical progress, thusExpand
  • 77
  • 12
  • PDF
Transfer of samples in batch reinforcement learning
TLDR
We introduce a novel algorithm that transfers samples (i.e., tuples ⟨s, a, s', r⟩) from source to target tasks that are mostly similar to the target task, and use them as input for batch reinforcement-learning algorithms. Expand
  • 110
  • 9
  • PDF
Evolutionary Learning of Fuzzy rules: competition and cooperation
TLDR
We discuss the problem of learning fuzzy rules using Evolutionary Learning techniques, such as Genetic Algorithms and Learning Classifier Systems. Expand
  • 154
  • 8
Physically Interactive Robogames: Definition and design guidelines
TLDR
This paper presents the definition and design guidelines for a new application field for autonomous robots: Physically Interactive RoboGames (PIRG). Expand
  • 23
  • 6
  • PDF
Reinforcement Learning in Continuous Action Spaces through Sequential Monte Carlo Methods
TLDR
In this paper, we propose a novel actor-critic approach in which the policy of the actor is estimated through sequential Monte Carlo methods. Expand
  • 98
  • 5
  • PDF
A kinematic-independent dead-reckoning sensor for indoor mobile robotics
TLDR
In this paper, we present a dead reckoning sensor to support reliable odometry on mobile robots. Expand
  • 64
  • 5
  • PDF
Modeling enjoyment preference from physiological responses in a car racing game
TLDR
We propose a framework to estimate player enjoyment preference from physiological signals. Expand
  • 86
  • 4
  • PDF
A qualitative simulation approach for fuzzy dynamical models
TLDR
We propose a fuzzy simulator based on the Fuzzy Sets theory for qualitative modeling and simulation of approximate models of dynamic systems. Expand
  • 90
  • 4
An Introduction to Learning Fuzzy Classifier Systems
TLDR
We present a class of Learning Classifier Systems that learn fuzzy rule-based models, instead of interval-based or Boolean models, based on data interpretation implemented by fuzzy sets. Expand
  • 89
  • 3
R2P: An open source hardware and software modular approach to robot prototyping
TLDR
We propose R2P (Rapid Robot Prototyping), a framework to implement real-time, high-quality architectures for robotic systems with off-the-shelf basic modules (e.g., sensors, actuators, and controllers), integrating hardware and software, which can be assembled in a plug-and-play way. Expand
  • 35
  • 3
...
1
2
3
4
5
...