activity
20162023
most citedFrom Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence

33 citations · 126 across the 14 of their papers we have counts for

collaborators
Showing 2018Show all

6 papers · 1 filter

cs.RO2018

Probably Unknown: Deep Inverse Sensor Modelling In Radar

Rob Weston, Sarah Cen, Paul Newman +1

Radar presents a promising alternative to lidar and vision in autonomous vehicle applications, able to detect objects at long range under a variety of weather conditions. However,…

cs.CV2018

Dropout Distillation for Efficiently Estimating Model Confidence

Corina Gurau, Alex Bewley, Ingmar Posner

We propose an efficient way to output better calibrated uncertainty scores from neural networks. The Distilled Dropout Network (DDN) makes standard (non-Bayesian) neural networks m…

stat.ML2018

Scrutinizing and De-Biasing Intuitive Physics with Neural Stethoscopes

Fabian B. Fuchs, Oliver Groth, Adam R. Kosiorek +4

Visually predicting the stability of block towers is a popular task in the domain of intuitive physics. While previous work focusses on prediction accuracy, a one-dimensional perfo…

cs.LG2018

Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects

Adam R. Kosiorek, Hyunjik Kim, Ingmar Posner +1

We present Sequential Attend, Infer, Repeat (SQAIR), an interpretable deep generative model for videos of moving objects. It can reliably discover and track objects throughout the…

cs.CV2018

ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking

Oliver Groth, Fabian B. Fuchs, Ingmar Posner +1

Physical intuition is pivotal for intelligent agents to perform complex tasks. In this paper we investigate the passive acquisition of an intuitive understanding of physical princi…

cs.LG2018

TACO: Learning Task Decomposition via Temporal Alignment for Control

Kyriacos Shiarlis, Markus Wulfmeier, Sasha Salter +2

Many advanced Learning from Demonstration (LfD) methods consider the decomposition of complex, real-world tasks into simpler sub-tasks. By reusing the corresponding sub-policies wi…