The Applied AI Lab (A2I) explores core challenges in AI and Machine Learning to enable robots to robustly and effectively operate in complex, real-world environments. Our research is guided by our vision to create machines which constantly improve through use in their dedicated workspace. In doing so we explore a number of intellectual challenges at the heart of robot learning such as machine introspection in perception and decision making, data efficient learning from demonstration, task-based and transfer learning and the learning of complex tasks via a curriculum of less complex ones. All the while our intellectual curiosity remains grounded in real-world robotics domains such as autonomous driving, logistics, manipulation or space exploration.
Latest News
Hierarchical Attentive Recurrent Tracking
Hierarchical Attentive Recurrent Tracking Abstract – Class-agnostic object tracking is particularly [...]
Mutual Alignment Transfer Learning from Simulation to the Real World
Abstract - Training robots for operation in the real world [...]
Adversarial Domain Adaptation
Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation [...]
Highlights
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 [...]
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 [...]
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 [...]
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 [...]
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 [...]
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. [...]