IROS

Home/Tag: IROS

Laser-only road-vehicle localization with dual 2D push-broom LIDARS and 3D priors

In this paper we consider long-term navigation using fixed 2D LIDARs. We consider how localization algorithms based on scan-matching - commonly used in indoor environments - are prone to failure when exposed to a challenging real-world outdoor environment. The driving motivation behind this work is to produce a simple, robust system that can be utilized repeatedly over a long period, rather than [...]

By |2016-10-22T19:49:35+01:00October 6th, 2014|Localisation, News Feed|Comments Off on Laser-only road-vehicle localization with dual 2D push-broom LIDARS and 3D priors

Non-parametric Learning for Natural Plan Generation

We present a novel way to learn sampling distributions for sampling-based motion planners by making use of expert data. We learn an estimate (in a non-parametric setting) of sample densities around semantic regions of interest, and incorporate these learned distributions into a sampling-based planner to produce natural plans. Our motivation is that certain aspects of [...]

By |2016-10-22T19:51:02+01:00October 13th, 2010|News Feed, Perception, Planning|Comments Off on Non-parametric Learning for Natural Plan Generation

Semantic Categorization of Outdoor Scenes with Uncertainty Estimates using Multi-Class Gaussian Process Classification

Abstract— This paper presents a novel semantic categorization method for 3D point cloud data using supervised, multi-class Gaussian Process (GP) classification. In contrast to other approaches, and particularly Support Vector Machines, which probably are the most used method for this task to date, GPs have the major advantage of providing informative uncertainty estimates about the [...]

By |2016-10-22T19:51:02+01:00October 13th, 2010|News Feed, Perception, Topics|Comments Off on Semantic Categorization of Outdoor Scenes with Uncertainty Estimates using Multi-Class Gaussian Process Classification

Using Text-Spotting to Query the World

Abstract—The world we live in is labeled extensively for the benefit of humans. Yet, to date, robots have made little use of human readable text as a resource. In this paper we aim to draw attention to text as a readily available source of semantic information in robotics by implementing a system which allows robots [...]

By |2016-10-22T19:51:02+01:00October 6th, 2010|News Feed, Perception, Topics|Comments Off on Using Text-Spotting to Query the World
Go to Top