Latest From The Blog


Introspective Radar Odometry

How do we know when we don’t know? This is an important question to answer in any situation where we need to navigate through our surroundings, and something any autonomous mobile robot needs to know too. We discuss this introspection capability and its importance to our radar-based navigation algorithms in our paper which is to be presented at ITSC 2019 - “What Could Go Wrong? Introspective Radar Odometry in Challenging Environments” by Roberto Aldera, Daniele De Martini, Matthew Gadd, and Paul Newman. [bibtex key="2019ITSC_aldera"] With introspection, our Radar Odometry (RO) system is now able to operate in environments it finds challenging and produce estimates that are more reliable, shown here in the figure below against some ground truth data from a GNSS/INS receiver. Tall trees and hedges in this example make motion estimation tricky - notice how in the radar scan we observe two parallel [...]

By |July 24th, 2019|Categories: MRG Highlights, MRG News, ORI Blog|Tags: , , , , , |Comments Off on Introspective Radar Odometry

Fast Radar Motion Estimation

Fast Radar Motion Estimation This blog post provides an overview of our paper “Fast Radar Motion Estimation with a Learnt Focus of Attention using Weak Supervision” by Roberto Aldera, Daniele De Martini, Matthew Gadd, and Paul Newman which was recently accepted for publication at the IEEE International Conference on Robotics and Automation (ICRA) 2019. [bibtex key="2019ICRA_aldera"] For a quick overview you can take a look at our video: Why radar? Radar is ideal for ego-motion estimation and localisation tasks as it is good at detecting stable environmental features under adverse weather and lighting conditions. An unfiltered radar scan with returns which are not spatially coherent from multiple viewpoints. However, radar measurements are complex for various reasons: The beam is not narrow and tightly focused, Returns are affected by various noise sources, and The interaction of the electromagnetic wave in the environment is more complex [...]

By |April 10th, 2019|Categories: MRG Highlights, ORI Blog|Tags: , |Comments Off on Fast Radar Motion Estimation

ORI Volunteer at St Paul’s Girls’ School as Robotics Mentor

Over the past few months, one of our 2nd year DPhil students, Mark Finean, has been volunteering as a robotics mentor to a group of girls pursuing their A levels at St Paul’s Girls’ School (SPGS) in London. For a school project, they wished to learn more about robots and investigate how they could be used in schools as well as the ways that students could interact with and use them to learn. To help learn more about the current state of modern robotics and gain some hands-on-experience, they spent a day in the ORI where they were introduced to some of the research we conduct as well as tried their hands at programming the Toyota HSR. They were given a series of mini-challenges, teaching them how to programme the HSR to perform movements and tasks. This culminated in them getting the robot to approach and pick up a bottle followed [...]

By |March 29th, 2019|Categories: ORI Blog|Comments Off on ORI Volunteer at St Paul’s Girls’ School as Robotics Mentor

ShapeStacks: Giving Robots a Physical Intuition

TLDR: Physical intuition is a human super-power. It enables our superior object manipulation skills which we apply in countless scenarios - from playing with toys to using tools. The ShapeStacks project aims to equip robots with a similar intuition by providing a virtual playground in which robots can acquire physical experiences.     [ Paper · Code · Data ]   Most of us have probably played a game of Jenga before, dealt with stacks of dirty dishes in their kitchen or used a hammer to hit a nail into a piece of wood. The inherent complexity of these simple everyday tasks becomes immediately clear when we try to build a machine which is capable of doing the same thing. Robots are essentially computers integrating sensing, locomotion and manipulation. And like all computers, they are first and foremost fast and exact calculators. Yet, despite their number-crunching [...]

By |January 16th, 2019|Categories: ORI Blog|Comments Off on ShapeStacks: Giving Robots a Physical Intuition

Laser Localization

What's the problem? Motivation This is a blog post designed for non-technical people to understand the basics of localization. As such we are not going to touch any code but rather interactively present you with examples how these systems run and what makes them tick. Localization is an essential part of any autonomous vehicle. Nowadays any self-driving car would use a combination of AI-driven tools to understand where it is, given some previously obtained map. But how do you obtain a map? Using sensors, of course - all autonomous cars have multiple cameras and lasers that record the environment around them. Think of these as a collection of pictures as the one on the left, or a collection of points in space (right). These pictures or clouds are stored on the on-board computers of each vehicle and processed.   Okay I got the map, but we [...]

By |November 30th, 2018|Categories: ORI Blog|Comments Off on Laser Localization
Load More Posts