ORI Blog

/ORI Blog

Geometric Multi-Model Extraction For Robotics

The extraction of geometric models has long been of interest to the robotics community. Many interesting applications such as homography,plane estimation and ego-motion estimation demand the ability to fit geometric models onto noisy data. Additionally, these geometric models are often drivers of other algorithms for algorithms  navigation, perception and 3D reconstructions creating an increased desire for [...]

Geometric Multi-Model Extraction For Robotics 2018-05-10T18:03:21+00:00

On Machine Learning and Prior Structure for Mobile Robots – The Summary

Similar to the long-term discussion on how much innate structure is required for artificial general intelligence [1], an important challenge in the short-term lies in the combination of traditional programming and machine learning for more narrow applications e.g. towards more efficient, robust, and safe robots. The question about the limitations or benefits of increased prior [...]

On Machine Learning and Prior Structure for Mobile Robots – The Summary 2018-04-12T13:52:09+00:00

Meshed Up: Learnt Error Correction in 3D Reconstructions

In this blog post, we’ll take a look at our paper “Meshed Up: Learnt Error Correction in 3D Reconstructions”, which will be presented at ICRA 2018, Brisbane, Australia. [arXiv] A lot of our work looks at how to build better maps. There are many ways in which maps can be represented, for example: a graph [...]

Meshed Up: Learnt Error Correction in 3D Reconstructions 2018-04-05T12:46:25+00:00

Watch out for Long-term Autonomous Robot Systems

Long-term autonomous robot systems will play an essential role in many real-world applications in the future. Robots will operate in a broad range of domains including space, marine, air, field, road, and service. They will assist us in our daily routines and perform other dangerous, dirty and dull tasks. However, enabling autonomous robots to successfully [...]

Watch out for Long-term Autonomous Robot Systems 2018-03-28T14:20:14+00:00

Estimation, Search, and Path Planning

ORI is expanding! I'm starting a new research group focused on estimation, search, and path planning. It's a continuation of my previous work developing and deploying theoretically well-founded robotic algorithms here and at the University of Toronto. As is the ORI way, we will be testing the work on a variety of real-world robotic applications. [...]

Estimation, Search, and Path Planning 2018-03-02T14:18:05+00:00

Where did my robot go? Being robust and cautious during Laser-based Localization

Let’s imagine a scenario where a robot, either walking on two or four legs or moving on wheels, is required to explore a cluttered environment containing corridors, constrictions, uneven terrains or staircases. The robot would process proprioceptive inertial and leg/wheel odometry measurements, as well as exteroceptive observations from a 3D laser scanner. The odometry estimate [...]

Where did my robot go? Being robust and cautious during Laser-based Localization 2018-04-24T09:17:56+00:00

Scaling up Neural Networks for Processing 3D Point Clouds

This blog post provides an overview of our paper "Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks" by Martin Engelcke, Dushyant Rao, Dominic Zeng Wang, Chi Hay Tong, and Ingmar Posner which was published at the IEEE International Conference on Robotics and Automation (ICRA) 2017. For a quick overview you [...]

Scaling up Neural Networks for Processing 3D Point Clouds 2018-01-23T10:19:04+00:00