Related papers: An Open-World Simulated Environment for Developmen…
State representation learning aims at learning compact representations from raw observations in robotics and control applications. Approaches used for this objective are auto-encoders, learning forward models, inverse dynamics or learning…
Reinforcement learning (RL) provides a naturalistic framing for learning through trial and error, which is appealing both because of its simplicity and effectiveness and because of its resemblance to how humans and animals acquire skills…
A robot simulation system is a basic need for any robotics application. With it, developers' teams of robots can test their algorithms and make initial calibrations without risk of damage to the real robots, assuring safety. However,…
Humans have internal models of robots (like their physical capabilities), the world (like what will happen next), and their tasks (like a preferred goal). However, human internal models are not always perfect: for example, it is easy to…
Simulation is an integral part in the process of developing autonomous vehicles and advantageous for training, validation, and verification of driving functions. Even though simulations come with a series of benefits compared to real-world…
Both the design and control of a robot play equally important roles in its task performance. However, while optimal control is well studied in the machine learning and robotics community, less attention is placed on finding the optimal…
Exploration of indoor environments has recently experienced a significant interest, also thanks to the introduction of deep neural agents built in a hierarchical fashion and trained with Deep Reinforcement Learning (DRL) on simulated…
Generating robot demonstrations through simulation is widely recognized as an effective way to scale up robot data. Previous work often trained reinforcement learning agents to generate expert policies, but this approach lacks sample…
Robots need to be able to adapt to unexpected changes in the environment such that they can autonomously succeed in their tasks. However, hand-designing feedback models for adaptation is tedious, if at all possible, making data-driven…
Machine learning approaches have recently enabled autonomous navigation for mobile robots in a data-driven manner. Since most existing learning-based navigation systems are trained with data generated in artificially created training…
Humans have mental models that allow them to plan, experiment, and reason in the physical world. How should an intelligent agent go about learning such models? In this paper, we will study if models of the world learned in an open-ended…
This article introduces "Baby Robot", a robot aiming to improve motor skills of babies and toddlers. Authors developed a car-like toy that moves autonomously using reinforcement learning and computer vision techniques. The robot behaviour…
We propose a novel robotic system that can improve its perception during deployment. Contrary to the established approach of learning semantics from large datasets and deploying fixed models, we propose a framework in which semantic models…
Autonomous systems such as self-driving cars and general-purpose robots are safety-critical systems that operate in highly uncertain and dynamic environments. We propose an interactive multi-agent framework where the system-under-design is…
This paper discusses a 5-year PhD project, focused upon the implementation of social robots for general child and family care settings in the Netherlands. The project is a collaboration with general Dutch family care organisations as well…
Robotics simulation has been an integral part of research and development in the robotics area. The simulation eliminates the possibility of harm to sensors, motors, and the physical structure of a real robot by enabling robotics…
Learning is usually performed by observing real robot executions. Physics-based simulators are a good alternative for providing highly valuable information while avoiding costly and potentially destructive robot executions. We present a…
Tactile information is important for robust performance in robotic tasks that involve physical interaction, such as object manipulation. However, with more data included in the reasoning and control process, modeling behavior becomes…
Self-adaptive robotic systems operate autonomously in dynamic and uncertain environments, requiring robust real-time monitoring and adaptive behaviour. Unlike traditional robotic software with predefined logic, self-adaptive robots exploit…
As collaborative robots enter industrial shop floors, logistics, and manufacturing, rapid and flexible evaluation of human-machine interaction has become more important. The availability of consumer headsets for virtual and augmented…