AI

This is a category for all research topics / papers done within A2I.
For general A2I content (for pages and news posts), use the A2I category.

Hierarchical Attentive Recurrent Tracking

Hierarchical Attentive Recurrent Tracking Abstract – Class-agnostic object tracking is particularly difficult in cluttered environments as target specific discriminative models cannot be learned a priori. Inspired by how the human visual cortex employs spatial attention and separate “where” and “what” processing pathways to actively suppress irrelevant visual features, this work develops a hierarchical attentive recurrent model [...]

Mutual Alignment Transfer Learning from Simulation to the Real World

Abstract - Training robots for operation in the real world is a complex, time consuming and potentially expensive task. Despite significant success of reinforcement learning in games and simulations, research in real robot applications has not been able to match similar progress. While sample complexity can be reduced by training policies in simulation, these can [...]

Adversarial Domain Adaptation

Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation Abstract – Appearance changes due to weather and seasonal conditions represent a strong impediment to the robust implementation of machine learning systems in outdoor robotics. While the model is optimised for the training domain it will deliver degraded performance in application domains that underlie distributional shifts [...]

Deep Inverse Reinforcement Learning

Large-Scale Cost Function Learning for Path Planning using Deep Inverse Reinforcement Learning Abstract - We present an approach for learning spatial traversability maps for driving in complex, urban environments based on an extensive dataset demonstrating the driving behaviour of human experts. The direct end-to-end mapping from raw input data to cost bypasses the effort of [...]

Deep Tracking

Deep tracking in the wild: End-to-End Tracking and Semantic Segmentation Using Recurrent Neural Networks Abstract – This paper presents a novel approach for tracking static and dynamic objects for an autonomous vehicle operating in complex urban environments. Whereas traditional approaches to tracking often feature numerous hand-engineered stages, this method is learned end-to-end and can directly predict [...]

Weakly-Supervised Path Proposals for Urban Autonomy

Find Your Own Way: Weakly-Supervised Segmentation of Path Proposals for Urban Autonomy Abstract – We present a weakly-supervised approach to segmenting proposed drivable paths in images with the goal of autonomous driving in complex urban environments. Using recorded routes from a data collection vehicle, our proposed method generates vast quantities of labelled images containing proposed paths [...]

Auditory perception

Abstract - Urban environments are characterised by the presence of distinctive audio signals which alert the drivers to events that require prompt action. The detection and interpretation of these signals would be highly beneficial for smart vehicle systems, as it would provide them with complementary information to navigate safely in the environment. In this paper, we [...]

Probabilistic Prediction of Perception Performance

Learn from Experience: Probabilistic Prediction of Perception Performance to Avoid Failure Abstract –Despite the significant advances in machine learning and perception over the past few decades, perception algorithms can still be unreliable when deployed in challenging, time-varying environments. When these systems are used for autonomous decision-making, such as in self-driving vehicles, the impact of their [...]

Introspection

In the context of decision making in robotics, the use of a classification framework which produces scores with inappropriate confidences will ultimately lead to the robot making dangerous decisions. In order to select a framework which will make the best decisions, we should pay careful attention to the ways in which it generates scores. Precision [...]