Modelling and simulation for autonomous systems : 6th International Conference, MESAS 2019, Palermo, Italy, October 29-31, 2019, revised selected papers
3 UAVs Swarm Simulation Environment -- 4 Simulation Experiments -- 4.1 Collision Avoidance Mechanism Experiments -- 4.2 Combined Leadership Mechanism -- 4.3 Combined Formations Mechanism -- 5 Conclusion -- References -- Kinematic Model of a Specific Robotic Manipulator -- 1 Introduction -- 1.1 Rigid Motion -- 1.2 Homogeneous Representation -- 1.3 Exponential Coordinates for Rigid Motion and Twists -- 2 Model of the Manipulator -- 3 Forward Kinematics -- 4 Inverse Kinematics -- 4.1 Denavit-Hartenberg Parameters -- 5 Conclusion -- References
Low-Cost RGB-D-SLAM Experimental Results for Real Building Interior Mapping -- 1 Introduction -- 2 Low-Cost Mapping -- 2.1 The SLAM Loop -- 2.2 The Sensor: Microsoft Kinect for Windows v1 -- 2.3 The Localization Algorithm: RGB-D-SLAM -- 2.4 The Closing: g2o Algorithm -- 2.5 The Representation: 3D Point Cloud -- 3 Application to the Mapping of the Interior of a Building -- 3.1 Overview -- 3.2 Caveats -- 3.3 Post-processing -- 4 Experimental Results -- 5 Conclusion and Future Work -- References
Deep Learning Algorithms for Vehicle Detection on UAV Platforms: First Investigations on the Effects of Synthetic Training -- 1 Introduction -- 2 Object of Research -- 3 State of the Art: Datasets, Simulation Testbed and Algorithms -- 3.1 Natural Datasets for UAV Vehicle Detection -- 3.2 Presagis M&S Suite for Training and Testing in Synthetic Environments -- 3.3 Algorithms for UAV Vehicle Detection -- 4 Generation and Analysis of the Synthetic Data Set -- 4.1 Bounding Box and Ground Truth Generation for Synthetic Environments
4.2 Image Generation Scheme, Parameter Distribution and Explorative Data Analysis -- 5 Experimental Setup and Results -- 5.1 Metrics for Evaluation -- 5.2 Training -- 5.3 Natural Training Data and Influence of the Learning Rate -- 5.4 Performance on Synthetic Test Data for Natural Training -- 5.5 Training with the Virtual Training Data Set -- 5.6 Training with Mixed Data Set -- 6 Conclusion and Future Work -- References -- Building a Generic Simulation Model for Analyzing the Feasibility of Multi-Robot Task Allocation (MRTA) Problems -- 1 Introduction