Get Out of My Lab: Large-scale, Real-Time Visual-Inertial Localization

Abstract

Abstract-Accurately estimating a robot's pose relative to a global scene model and precisely tracking the pose in real-time is a fundamental problem for navigation and obstacle avoidance tasks. Due to the computational complexity of localization against a large map and the memory consumed by the model, state-ofthe-art approaches are either limited to small workspaces or rely on a server-side system to query the global model while tracking the pose locally. The latter approaches face the problem of smoothly integrating the server's pose estimates into the trajectory computed locally to avoid temporal discontinuities.In this paper, we demonstrate that large-scale, real-time pose estimation and tracking can be performed on mobile platforms with limited resources without the use of an external server. This is achieved by employing map and descriptor compression schemes as well as efficient search algorithms from computer vision. We derive a formulation for integrating the global pose information into a local state estimator that produces much smoother trajectories than current approaches. Through detailed experiments, we evaluate each of our design choices individually and document its impact on the overall system performance, demonstrating that our approach outperforms state-of-the-art algorithms for localization at scale.

Joining the dots: reconstructing 3D environments and movement paths using animal-borne devices

“…Therefore, future work may also attempt to use visual feature tracking algorithms in order to recognise areas that have been revisited (i.e. within an animal's home range) to perform drift correction or loop closure [72][73][74]. Such a feature, known as ' Area Learning' on the Tango platform, could allow researchers to visit and 'learn' an area in advance to produce area description files that correct errors in trajectory data.…”

Collaborative navigation for flying and walking robots

“…To this end, we propose the use of a framework based on [14]. The idea is to provide a statistically consistent interface between visualinertial odometry and a mapping backend.…”

“…[12]). The discussed localization and mapping framework provides an accurate pose estimation (see [14] for an evaluation), but the obtained bandwidth (5 Hz) is insufficient for the feedback controller for stabilizing the system. In order to overcome the above shortcoming, an EKFbased state estimator is implemented on the legged robot as presented in [17].…”

Enhancement Strategies for Frame-to-Frame Uas Stereo Visual Odometry

“…In contrast to traditional structure-frommotion techniques, where features between all frames exhaustively are attempted to match, (Warren, 2015) utilizes the vocabulary-tree-based openFABMAP (Glover et al, 2012) library for loop closing. Recently (Lynen et al, 2015) demonstrated that large-scale, real-time pose estimation and tracking can be performed on mobile platforms by employing map and descriptor compression schemes together with efficient search algorithms.…”