Related papers: Efficient Supervision for Robot Learning via Imita…

Connecting multiple machine learning models into a pipeline is effective for handling complex problems. By breaking down the problem into steps, each tackled by a specific component model of the pipeline, the overall solution can be made…

Model-based controllers on real robots require accurate knowledge of the system dynamics to perform optimally. For complex dynamics, first-principles modeling is not sufficiently precise, and data-driven approaches can be leveraged to learn…

Imitation learning has unlocked the potential for robots to exhibit highly dexterous behaviours. However, it still struggles with long-horizon, multi-object tasks due to poor sample efficiency and limited generalisation. Existing methods…

Manipulation of deformable objects, such as ropes and cloth, is an important but challenging problem in robotics. We present a learning-based system where a robot takes as input a sequence of images of a human manipulating a rope from an…

Reinforcement Learning (RL) has seen many recent successes for quadruped robot control. The imitation of reference motions provides a simple and powerful prior for guiding solutions towards desired solutions without the need for meticulous…

Artificial intelligence recently had a great advancements caused by the emergence of new processing power and machine learning methods. Having said that, the learning capability of artificial intelligence is still at its infancy comparing…

Machine learning tasks entail the use of complex computational pipelines to reach quantitative and qualitative conclusions. If some of the activities in a pipeline produce erroneous or uninformative outputs, the pipeline may fail or produce…

Machine learning has enabled significant benefits in diverse fields, but, with a few exceptions, has had limited impact on computer architecture. Recent work, however, has explored broader applicability for design, optimization, and…

Building models of the world from observation, i.e., induction, is one of the major challenges in machine learning. In order to be useful, models need to maintain accuracy when used in novel situations, i.e., generalize. In addition, they…

Autonomous inspection is a central problem in robotics, with applications ranging from industrial monitoring to search-and-rescue. Traditionally, inspection has often been reduced to navigation tasks, where the objective is to reach a…

Perceptual understanding of the scene and the relationship between its different components is important for successful completion of robotic tasks. Representation learning has been shown to be a powerful technique for this, but most of the…

In order to achieve state-of-the-art performance, modern machine learning techniques require careful data pre-processing and hyperparameter tuning. Moreover, given the ever increasing number of machine learning models being developed, model…

Planning for robotic manipulation requires reasoning about the changes a robot can affect on objects. When such interactions can be modelled analytically, as in domains with rigid objects, efficient planning algorithms exist. However, in…

The goal of meta-learning is to train a model on a variety of learning tasks, such that it can adapt to new problems within only a few iterations. Here we propose a principled information-theoretic model that optimally partitions the…

Edge robotics involves frequent exchanges of large-volume multi-modal data. Existing methods ignore the interdependency between robotic functionalities and communication conditions, leading to excessive communication overhead. This paper…

Creating a vision pipeline for different datasets to solve a computer vision task is a complex and time consuming process. Currently, these pipelines are developed with the help of domain experts. Moreover, there is no systematic structure…

Line art is arguably one of the fundamental and versatile modes of expression. We propose a pipeline for a robot to look at a grayscale line art and redraw it. The key novel elements of our pipeline are: a) we propose a novel task of…

This work proposes a fast deployment pipeline for visually-servoed robots which does not assume anything about either the robot - e.g. sizes, colour or the presence of markers - or the deployment environment. In this, accurate estimation of…

Imitation learning trains control policies by mimicking pre-recorded expert demonstrations. In partially observable settings, imitation policies must rely on observation histories, but many seemingly paradoxical results show better…

Despite remarkable progress in computer vision, modern recognition systems remain fundamentally limited by their dependence on rich, redundant visual inputs. In contrast, humans can effortlessly understand sparse, minimal representations…