Robohub.org
 

Driving, flying, and climbing in a sand and gravel pit

by
18 July 2016



share this:
NCFRN Field Trials 2016. Photo: Tim Barfoot

NCFRN Field Trials 2016. Grizzly in challenging lighting. Photo: Tim Barfoot

In June, the University of Toronto (as part of the NSERC Canadian Field Robotics Network) carried out a set of field trials at an old sand and gravel pit in Sudbury, Ontario, Canada. This involved three main experiments:

  1. A new version of our Visual Teach and Repeat (VT&R) approach to vision-only route following,
  2. Aerial surveys of the site using fixed-wing unmanned aerial vehicles, and
  3. A tethered robot design for mapping steep surfaces such as cliffs.

In the VT&R experiments, we taught our robot a 5 km network of interconnected paths, then carried out 120 km of autonomous repeats on these paths using only stereo vision for feedback. The below video shows some sections being repeated. Our new technique, dubbed VT&R 2.0, is a significant advance over our earlier work in that (i) it uses a Multi­-Experience Localization (MEL) technique to match live images to several previous experience of a path (making it more robust to appearance change), and (ii) is able to do place-­dependent terrain assessment to safeguard the robot and people around it, even in rough terrain with vegetation.

The team also captured some great images of the various experiments.  All images copyright Tim Barfoot or Francois Pomerleau.

grizzly2 grizzly3 grizzly4 grizzly5

All photos can be viewed here.


This video is associated with the following papers:

Paton M, MacTavish K A, Warren M, and Barfoot T D. “Bridging the Appearance Gap: Multi-Experience Localization for Long-Term Visual Teach and Repeat”. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Daejeon, Korea, 9-14 October 2016

Berczi L P and Barfoot T D. “It’s Like Déjà Vu All Over Again: Learning Place-Dependent Terrain Assessment for Visual Teach and Repeat”. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Daejeon, Korea, 9-14 October 2016



tags: , , ,


Tim Barfoot Dr. Timothy Barfoot (Professor, University of Toronto Institute for Aerospace Studies -- UTIAS) holds the Canada Research Chair (Tier II) in Autonomous Space Robotics and works in the area of guidance, navigation, and control of mobile robots for space and terrestrial applications.
Tim Barfoot Dr. Timothy Barfoot (Professor, University of Toronto Institute for Aerospace Studies -- UTIAS) holds the Canada Research Chair (Tier II) in Autonomous Space Robotics and works in the area of guidance, navigation, and control of mobile robots for space and terrestrial applications.





Related posts :



Our future could be full of undying, self-repairing robots – here’s how

Could it be that future AI systems will need robotic “bodies” to interact with the world? If so, will nightmarish ideas like the self-repairing, shape-shifting T-1000 robot from the Terminator 2 movie come to fruition? And could a robot be created that could “live” forever?
01 February 2023, by

Sensing with purpose

Fadel Adib uses wireless technologies to sense the world in new ways, taking aim at sweeping problems such as food insecurity, climate change, and access to health care.
29 January 2023, by

Robot Talk Episode 34 – Interview with Sabine Hauert

In this week's episode of the Robot Talk podcast, host Claire Asher chatted to Dr Sabine Hauert from the University of Bristol all about swarm robotics, nanorobots, and environmental monitoring.
28 January 2023, by

Special drone collects environmental DNA from trees

Researchers at ETH Zurich and the Swiss Federal research institute WSL have developed a flying device that can land on tree branches to take samples. This opens up a new dimension for scientists previously reserved for biodiversity researchers.
27 January 2023, by

The robots of CES 2023

Robots were on the main expo floor at CES this year, and these weren’t just cool robots for marketing purposes. I’ve been tracking robots at CES for more than 10 years, watching the transition from robot toys to real robots.
25 January 2023, by





©2021 - ROBOTS Association


 












©2021 - ROBOTS Association