Estimation of Absolute Scale in Monocular SLAM Using Synthetic Data

Danila Rukhovich, Daniel Mouritzen, Ralf Kaestner, Martin Rufli, Alexander Velizhev

International Conference on Computer Vision (ICCV) 2019 – Workshop on Computer Vision for Road Scene Understanding and Autonomous Driving

This paper addresses the problem of scale estimation in monocular SLAM by estimating absolute distances between camera centers of consecutive image frames. These estimates would improve the overall performance of classical(not deep) SLAM systems and allow metric feature locations to be recovered from a single monocular camera. We propose several network architectures that lead to an improvement of scale estimation accuracy over the state of the art. In addition, we exploit a possibility to train the neural network only with synthetic data derived from a computer graphics simulator. Our key insight is that, using only synthetic training inputs, we can achieve similar scale estimation accuracy as that obtained from real data. This fact indicates that fully annotated simulated data is a viable alternative to existing deep-learning-based SLAM systems trained on real (unlabeled) data. Our experiments with unsupervised domain adaptation also show that the difference in visual appearance between simulated and real data does not affect scale estimation results. Our method operates with low-resolution images (0.03 MP), which makes it practical for real-time SLAM applications with a monocular camera.

Paper (.pdf)

Deliverable 5.2

First development and integration cycle of lifelong mapping

This deliverable describes the lifelong mapping framework after the first development & integration cycle. All components, notably the metric and semantic map, the metric online localization, the semantic data aggregation and the map summarization are functional and integrated on the vehicles, fulfill their basic purposes and interact with each other in a limited fashion. All components deliver first evaluation results.

pdf

Deliverable 5.1

Specification of the Map Frontend and Storage Concept

This deliverable corresponds to task 5.1, 5.2 and 5.3. It describes the hardware and software requirements and specifications for the mapping and localization frontend and storage concepts in the cloud-based backend.

pdf

A Decentralized Trust-minimized Cloud Robotics Architecture

Alessandro Simovic, Ralf Kaestner and Martin Rufli

International Conference on Intelligent Robots and Systems (IROS) 2017 – Poster Track

We introduce a novel, decentralized architecture facilitating consensual, blockchain-secured computation and verification of data/knowledge. Through the integration of (i) a decentralized content-addressable storage system, (ii) a decentralized communication and time stamping server, and (iii) a decentralized computation module, it enables a scalable, transparent, and semantically interoperable cloud robotics ecosystem, capable of powering the emerging internet of robots.

Paper (.pdf)   Poster (.pdf)