no code implementations • 16 Sep 2023 • Marvin Chancán, Alex Wong, Ian Abraham
Training with data collected by our approach improves depth completion by an average greater than 18% across four depth completion models compared to existing exploration methods on the MP3D test set.
1 code implementation • 2 Mar 2021 • Marvin Chancán, Michael Milford
Sequential matching using hand-crafted heuristics has been standard practice in route-based place recognition for enhancing pairwise similarity results for nearly a decade.
1 code implementation • 17 Nov 2020 • Marvin Chancán, Michael Milford
Sequence-based place recognition methods for all-weather navigation are well-known for producing state-of-the-art results under challenging day-night or summer-winter transitions.
1 code implementation • 16 Jun 2020 • Marvin Chancán, Michael Milford
Learning visuomotor control policies in robotic systems is a fundamental problem when aiming for long-term behavioral autonomy.
1 code implementation • 2 Mar 2020 • Marvin Chancán, Michael Milford
Our experimental results, on traversals of the Oxford RobotCar dataset with no GPS data, show that MVP can achieve 53% and 93% navigation success rate using VO and RO, respectively, compared to 7% for a vision-only method.
1 code implementation • 15 Oct 2019 • Marvin Chancán, Luis Hernandez-Nunez, Ajay Narendra, Andrew B. Barron, Michael Milford
State-of-the-art algorithms for visual place recognition, and related visual navigation systems, can be broadly split into two categories: computer-science-oriented models including deep learning or image retrieval-based techniques with minimal biological plausibility, and neuroscience-oriented dynamical networks that model temporal properties underlying spatial navigation in the brain.
1 code implementation • 10 Oct 2019 • Marvin Chancán, Michael Milford
While deep reinforcement learning has shown success in solving these perception and decision-making problems in an end-to-end manner, these algorithms require large amounts of experience to learn navigation policies from high-dimensional data, which is generally impractical for real robots due to sample complexity.