AI News, A framework for depth estimation and relative localization in ground robots

A framework for depth estimation and relative localization in ground robots

In recent years, researchers have carried out a growing number of studies aimed at developing solutions to effectively coordinate multiple robots within a decentralized architecture.

This pose-related data, known as relative pose information, allows an agent to optimize the function of a given goal, re-plan its trajectories and avoid collisions with other robots.

With this in mind, the team of researchers from the University of Porto and KTH set out to develop a framework that could enhance the 3-D depth estimation and relative pose estimation of ground robots that are working together towards a common goal.

Most existing solutions for depth estimation and relative localization in robots work by analyzing a disconnected set of data, without taking into account the chronological order of events.

the robots are in each others' field of view or have the ability of sensing the bearing-information about each others' positions), we propose a framework that shares a set of common observations of the environment in the respective local frame of each robot (3-D point features are employed),' the researchers write.

RI Seminar: David Held: Robots Learning to Understand Environmental Changes

David Held Assistant Professor, Robotics Institute, Carnegie Mellon Abstract Robots today are typically confined to operate in relatively simple, controlled ...

Real-Time Object Pose Estimation with Pose Interpreter Networks

To appear at 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018) Preprint: Code: ..

Estimation of Camera Position without Markers for both Indoor and Outdoor Environments

Estimation of Camera Position without Markers for both Indoor and Outdoor Environments Kunihiro Nishimura, Ph.D., Satomi Sakata, IPA Mitoh 2011 Program.

Real-time SLAM Relocalisation

Position of the camera is tracked in real time while making a sparse 3D map of the scene. Relocalisation is possible after tracking failure. This work was ...

ObjectDetection Pose Estimation

The Object Detection and pose estimation relative to camera is done in MATLAB

Data-Efficient Decentralized Visual SLAM (ICRA18 Video Teaser)

Decentralized visual simultaneous localization and mapping (SLAM) is a powerful tool for multi-robot applications in environments where absolute positioning is ...

Data-Efficient Decentralized Visual SLAM

ICRA 2018 Spotlight Video Interactive Session Tue PM Pod U.1 Authors: Cieslewski, Titus; Choudhary, Siddharth; Scaramuzza, Davide Title: Data-Efficient ...

Mutual Localization in Multi-robot Systems using Anonymous Relative Measurements

"Mutual Localization in Multi-robot Systems using Anonymous Relative Measurements" by Antonio Franchi, Giuseppe Oriolo, and Paolo Stegagno International ...

Mutual localization with anonymous relative position measures

Mutual Localization with Position Measures (MLPM) is the problem of determining all the robot-to-robot relative locations (position and orientation) within a ...

Lecture 8.2: John Leonard - Mapping, Localization and Self Driving Vehicles

MIT RES.9-003 Brains, Minds and Machines Summer Course, Summer 2015 View the complete course: Instructor: John ..