Related papers: Context Discovery for Model Learning in Partially …

This paper addresses the problem of classifying observations when features are context-sensitive, specifically when the testing set involves a context that is different from the training set. The paper begins with a precise definition of…

In this paper, we learn dynamics models for parametrized families of dynamical systems with varying properties. The dynamics models are formulated as stochastic processes conditioned on a latent context variable which is inferred from…

Autonomous operations of robots in unknown environments are challenging due to the lack of knowledge of the dynamics of the interactions, such as the objects' movability. This work introduces a novel Causal Reinforcement Learning approach…

Active learning agents typically employ a query selection algorithm which solely considers the agent's learning objectives. However, this may be insufficient in more realistic human domains. This work uses imitation learning to enable an…

Despite its omnipresence in robotics application, the nature of spatial knowledge and the mechanisms that underlie its emergence in autonomous agents are still poorly understood. Recent theoretical work suggests that the concept of space…

Autonomous navigation in unfamiliar environments often relies on geometric mapping and planning strategies that overlook rich semantic cues such as signs, room numbers, and textual labels. We propose a novel semantic navigation framework…

World modelling, i.e. building a representation of the rules that govern the world so as to predict its evolution, is an essential ability for any agent interacting with the physical world. Despite their impressive performance, many…

In robotic applications, we often face the challenge of discovering new objects while having very little or no labelled training data. In this paper we explore the use of self-supervision provided by a robot traversing an environment to…

This paper presents a novel approach for learning self-awareness models for autonomous vehicles. The proposed technique is based on the availability of synchronized multi-sensor dynamic data related to different maneuvering tasks performed…

In this paper, we confront the problem of applying reinforcement learning to agents that perceive the environment through many sensors and that can perform parallel actions using many actuators as is the case in complex autonomous robots.…

Modelling the behaviours of other agents is essential for understanding how agents interact and making effective decisions. Existing methods for agent modelling commonly assume knowledge of the local observations and chosen actions of the…

Current LLM agents typically lack instance-level context, which comprises concrete facts such as environment structure, system configurations, and local mechanics. Consequently, existing methods are forced to intertwine exploration with…

Automation systems are increasingly being used in dynamic and various operating conditions. With higher flexibility demands, they need to promptly respond to surrounding dynamic changes by adapting their operation. Context information…

Navigating robots through unstructured terrains is challenging, primarily due to the dynamic environmental changes. While humans adeptly navigate such terrains by using context from their observations, creating a similar context-aware…

If a robot is supposed to roam an environment and interact with objects, it is often necessary to know all possible objects in advance, so that a database with models of all objects can be generated for visual identification. However, this…

This contribution comprises the interplay between a multi-modal variational autoencoder and an environment to a perceived environment, on which an agent can act. Furthermore, we conclude our work with a comparison to curiosity-driven…

In this paper we introduce a general estimation methodology for learning a model of human perception and control in a sensorimotor control task based upon a finite set of demonstrations. The model's structure consists of i the agent's…

Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to mathematically formalize these abilities using a neural network…

Learning-based model predictive control has been widely applied in autonomous racing to improve the closed-loop behaviour of vehicles in a data-driven manner. When environmental conditions change, e.g., due to rain, often only the…

We present a novel framework for estimating accident-prone regions in everyday indoor scenes, aimed at improving real-time risk awareness in service robots operating in human-centric environments. As robots become integrated into daily…