Abstract-Objects are integral to a robot's understanding of space. Various tasks such as semantic mapping, pick-andcarry missions or manipulation involve interaction with objects. Previous work in the field largely builds on the assumption that the object in question starts out within the ready sensory reach of the robot. In this work we aim to relax this assumption by providing the means to perform robust and large-scale active visual object search. Presenting spatial relations that describe topological relationships between objects, we then show how to use these to create potential search actions. We introduce a method for efficiently selecting search strategies given probabilities for those relations. Finally we perform experiments to verify the feasibility of our approach.

Abstract-There are many different approaches to building a system that can engage in autonomous mental development. In this paper, we present an approach based on what we term self-understanding, by which we mean the explicit representation of and reasoning about what a system does and does not know, and how that knowledge changes under action. We present an architecture and a set of representations used in two robot systems that exhibit a limited degree of autonomous mental development, which we term self-extension. The contributions include: representations of gaps and uncertainty for specific kinds of knowledge, and a goal management and planning system for setting and achieving learning goals.

No abstract

In this work we describe a novel deep reinforcement learning architecture that allows multiple actions to be selected at every time-step in an efficient manner. Multi-action policies allow complex behaviours to be learnt that would otherwise be hard to achieve when using single action selection techniques. We use both imitation learning and temporal difference (TD) reinforcement learning (RL) to provide a 4x improvement in training time and 2.5x improvement in performance over single action selection TD RL. We demonstrate the capabilities of this network using a complex in-house 3D game. Mimicking the behavior of the expert teacher significantly improves world state exploration and allows the agents vision system to be trained more rapidly than TD RL alone. This initial training technique kick-starts TD learning and the agent quickly learns to surpass the capabilities of the expert.

No abstract

No abstract

No abstract

This work describes the automatic segmentation of 2-dimensional indoor maps into semantic units along lines of spatial function, such as connectivity or objects used for certain tasks. Using a conceptually simple and readily extensible energy maximization framework, segmentations similar to what a human might produce are demonstrated on several real-world datasets.In addition, it is shown how the system can perform reference resolution by adding corresponding potentials to the energy function, yielding a segmentation that responds to the context of the spatial reference.