DRS posts

Home/DRS posts

VILENS

VILENS - Visual-Inertial Odometry for Legged Robots VILENS (Visual Inertial Legged Navigation System) is a factor-graph based odometry algorithm for legged robots that fuses leg odometry, vision, and IMU data. This algorithm was designed by David Wisth, Marco Camurri, and Maurice Fallon at the Oxford Robotics Institute (ORI). The papers describing this work are listed below. [...]

VILENS2019-11-08T01:17:21+00:00

ORCA Hub Demo – Blyth 2019

In a cold, wet week at the beginning of October, a team from Oxford Robotics Institute headed north to Blyth, near Newcastle, for the ORCA Hub demonstrations. A large warehouse, normally used for testing off-shore wind turbines, hosted teams from a number of different universities, all keen to demonstrate their advances in research in [...]

ORCA Hub Demo – Blyth 20192019-11-23T10:15:08+00:00

DARPA SubT Challenge

DARPA SubT Challenge Marco Camurri describes his recent trip to the DARPA SubT Challenge On Aug 15th to 22nd, 11 teams from all around the world gathered in Pittsburgh for the Tunnel Circuit of the DARPA SubT Challenge, an international robotics  competition dedicated to autonomous underground exploration. Each team had to locate a [...]

DARPA SubT Challenge2019-11-09T10:59:50+00:00

ORI’s Dr. Mathieu Geisert Awarded Best Paper at TAROS 2019

Last week a group from ORI attended the Towards Autonomous Robotic Systems (TAROS) 2019 Conference. The conference this year was held at the newly build Mile End campus of the Queen Mary University of London. Many interesting papers were presented and TAROS this year had an excellent set of keynote talks delivered from leading researchers [...]

ORI’s Dr. Mathieu Geisert Awarded Best Paper at TAROS 20192019-07-22T14:58:21+01:00

Efficient Segment Matching

Learning to See the Wood for the Trees: Deep Laser Localization in Urban and Natural Environments on a CPU Georgi Tinchev, Adrian Penate-Sanchez, Maurice Fallon IEEE Robotics and Automation Letters/IEEE International Conference on Robotics and Automation (RA-L/ICRA) 2019. [arXiv]   Figure 1. PCA visualization of the feature space after training our model. Each sample represents [...]

Efficient Segment Matching2019-11-03T11:55:09+00:00

DPhil students study Dynamic Robot Locomotion

16 first year DPhil students from the AIMS CDT spent a week at ORI studying Dynamic Locomotion led by students from the Dynamic Robot Systems Group (DRS). The hands on course was focused around the ANYmal robot (from ANYbotics) and its simulator. After a series of introductory lectures to ROS and research topics such as [...]

DPhil students study Dynamic Robot Locomotion2019-03-03T08:20:45+00:00

ANYmal goes underground – European Project ‘THING’

Benoit Casseau, Marco Camurri and David Wisth visited Zurich for a meeting of the European project THING (subTerranean Haptic INvestiGator). In a nutshell this project aims to develop new feet for the ANYmal robot to enhance it's mobility and to perceive terrain properties. In comparison to the current feet, the new ones have [...]

ANYmal goes underground – European Project ‘THING’2019-03-03T08:16:09+00:00

ORCA Demo – October 2018

Oxford Robotics Institute is part of two Research Hubs which focus on robotics and artificial intelligence (AI) that can be deployed in extreme environments. The hubs, both funded by UK Research and Innovation as part of the UK’s Industrial Strategy Challenge Fund, are ORCA, targeting applications for the offshore oil and gas industry, and [...]

ORCA Demo – October 20182019-03-03T08:22:10+00:00

Reliable Segmentation and Matching in Urban and Natural Environments

In this work we introduce Natural Segmentation and Matching (NSM), an algorithm for reliable localization, using laser, in both urban and natural environments. Current state-of-the-art global approaches do not generalize well to structure-poor vegetated areas such as forests or orchards where clutter and perceptual aliasing prevents reliable extraction of repeatable and distinctive landmarks to be [...]

Reliable Segmentation and Matching in Urban and Natural Environments2018-09-23T12:27:20+01:00

Look just what walked in: ANYmal delivered to ORI

Recently we welcomed a new robot to the ORI mobile robot menagerie: ANYmal. Built by ANYbotics AG, ANYmal is a 35kg torque-controlled quadruped specifically designed to be rugged and to be used in the field for industrial inspections as well as the basic science of motion planning, control and navigation. Researchers and students from [...]

Look just what walked in: ANYmal delivered to ORI2018-07-25T09:21:10+01:00