Видео

Postdoc Frederike Duembgen talks about our progress on global optimality for robotic state estimation during a recent visit to MIT.

This paper details a Doppler lidar odometry algorithm that is able to handle geometrically degenerate situations such as long tunnels by exploiting lidar velocity information. It is associated with this paper: "Picking Up Speed: Continuous-Time Lidar-Only Odometry using Doppler Velocity Measurements" arxiv.org/abs/2209.03304

This video shows some field tests of local obstacle avoidance incorporated into a lidar version of teach and repeat. It is associated with the below paper: "Off the Beaten Track: Laterally Weighted Motion Planning for Local Obstacle Avoidance" arxiv.org/abs/2309.09334

This paper details a fast doppler lidar odometry algorithm that avoids data correspondences by using velocity information. It is associated with the below paper: "Need for Speed: Fast Correspondence-Free Lidar-Inertial Odometry Using Doppler Velocity" arxiv.org/abs/2303.06511

This video shows highlights of some Unmanned Surface Vessel (USV) testing targeted at water-quality monitoring applications. It is associated with the below paper: "Field Testing of a Stochastic Planner for ASV Navigation Using Satellite Images" arxiv.org/abs/2309.14657

This video shows how we can use an FMCW Doppler lidar to estimate motion reliably even in places with degenerate geometry such as long tunnels: Wu Y, Yoon D J, Burnett K, Kammel S, Chen Y, Vhavle H, and Barfoot T D. “Picking Up Speed: Continuous- Time Lidar-Only Odometry using Doppler Velocity Measurements”. IEEE Robotics and Automation Letters (RAL), 8(1):264-271, 2023. arxiv.org/abs/2209.03304

This video discusses the following paper on radar as a substitute for lidar in all-weather mapping and localization: Burnett K, Wu Y, Yoon D J, Schoellig A P, and Barfoot T D. “Are We Ready for Radar to Replace Lidar in All-Weather Mapping and Localization?” IEEE Robotics and Automation Letters (RAL), 7(4):10328-10335, 2022 arxiv.org/abs/2203.10174

A video of our radar-based mapping and localization running on a dataset gathered near UTIAS. We are investigating this as an alternative to lidar mapping and localization for bad weather conditions. This video is related to the following paper: Burnett K, Wu Y, Yoon D J, Schoellig A P, and Barfoot T D. “Should Radar Replace Lidar in All-Weather Localization and Mapping?” arxiv.org/abs/2203.10174

This video shows highlights from a dataset for autonomous driving research comprising lidar, radar, camera, GPS/INS collected over a full year. The following paper provides more details: Burnett K, Yoon D J, Wu Y, Li A, Zhang H, Li S, Qian J, Tseng W, Lambert A, Leung K, Schoellig A P, and Barfoot T D. “Boreas: A Multi-Season Autonomous Driving Dataset" arxiv.org/abs/2203.10168

This video is associated with the paper: Gridseth M and Barfoot T D. “Keeping an Eye on Things: Deep Learned Features for Long-Term Visual Localization”. IEEE Robotics and Automation Letters (RAL), 7(2):1016-1023, 2022.

A short video about Visual Teach and Repeat including deep-learned features for long-term localization. More can be found in this paper: Gridseth M and Barfoot T D. “Keeping an Eye on Things: Deep Learned Features for Long-Term Visual Localization”. IEEE Robotics and Automation Letters (RAL), to appear, 2022. (arXiv:2109.04041 [cs.RO])

IROS 2021 Keynote Talk: Keeping an Eye on Things: Can We Build a Long-Term Navigation System Based on Vision?

This short video shows how to use the Visual Teach & Repeat 3 navigation package for visual path following. It discusses the steps of both teaching and repeating paths from the perspective of a user operating the robot through the provided graphical user interface.

Recording of the following RSS 2021 conference talk: Burnett K, Yoon D, Schoellig A P, and Barfoot T D. “Radar Odometry Combining Probabilistic Estimation and Unsupervised Feature Learning”. In Proceedings of Robotics: Science and Systems (RSS), 2021 arxiv.org/abs/2105.14152

HERO Radar Odometry Demo @ RSS 2021

"Self-Supervised Learning of Lidar Segmentation for Autonomous Indoor Navigation" @ ICRA 2021

"Do We Need to Compensate for Motion Distortion ... in Spinning Radar Navigation?" @ ICRA 2021

"UAV Localization Using Autoencoded Satellite Images" @ ICRA 2021

"MCMC Occupancy Grid Mapping with a Data-Driven Patch Prior" @ ICRA 2021

"Unsupervised Learning of Lidar Features ..." @ ICRA 2021

"Radar, Warts and All: Recent Progress Towards Spinning Radar Navigation" @ ICRA 2021

"Dark, Damp, and Dynamic: Recent Progress on Robotic Localization" @ ICRA 2021

"Relatively Lazy: Indoor-Outdoor Navigation Using Vision and GNSS" @ CRV 2021

Lidar Odometry Demo @ UTIAS (2017)

TSLAM: Tethered Simultaneous Localization and Mapping for Mobile Robots @ UTIAS (IJRR 2017)

Triaged Multi-Experience Localization (MEL) @ UTIAS (ICRA 2017)

Triaged Multi-Experience Localization (MEL) @ UTIAS (ICRA 2017)

Triaged Multi-Experience Localization (MEL) @ UTIAS (ICRA 2017)

TReX Mechanical Design @ UTIAS (2016)