This paper presents an optimized algorithm for robot localization which increases the correctness and accuracy of the estimating position of mobile robot to more than 150% of the past methods [1] in the uncertain and noisy environment. In this method the odometry and vision sensors are combined by an adapted wellknown discrete kalman filter [2]. This technique also decreased the computation pro...

This paper describes extensions to the Kintinuous [1] algorithm for spatially extended KinectFusion, incorporating the following additions: (i) the integration of multiple 6DOF camera odometry estimation methods for robust tracking; (ii) a novel GPU-based implementation of an existing dense RGB-D visual odometry algorithm; (iii) advanced fused realtime surface coloring. These extensions are val...

Disaster recovery robots must operate in unstructured environments where wheeled or tracked motion may not be feasible or where it may be subject to extreme slip. Many industrial disaster scenarios also preclude reliance on GNSS or other external signals as robots are deployed indoors or underground. Two of the candidates for precise positioning in these scenarios are visual odometry and inerti...

Most map building methods employed by mobile robots are based on the assumption that an estimate of the position of the robots can be obtained from odometry readings. In this paper we propose methods to build a global geometrical map by integrating partial maps without using any odometry information. This approach increases the flexibility in data collection. Robots do not need to see each othe...

Just to explain a little about the motivation for this topic, the project I was working on was called “PROSPECT: Wide Area Prospecting Using Supervised Autonomous Robots.” Our goal was to develop a semi-autonomous mutli-robot supervision architecture. One of the major issues for rover navigation is knowing attitude and position. Our initial idea was to use a combination of IMU, GPS and odometry...

In this work, we propose an interoceptive-only state estimation system for a quadrotor with deep neural network processing, where the dynamics is considered as perceptive supplement of inertial kinematics. To improve precision multi-sensor fusion, train cascaded networks on real-world flight data to learn IMU kinematic properties, dynamic characteristics, and motion states along their uncertain...