PGRs meeting and Research Presentations – April 2016

The monthly PGRs Research Presentations was held on Wed. 13th April, 2pm, Room MC3108.

This session we had the following presentations:


PGRs Monthly meeting_April2016  (Slides )



  • Speaker –>
  • A quick look at the new “PGRs Management System”,PGR-MS1


  • PGRs Blog.


  • Discussion of the activities plan.
  • Update and plan for the “Showcase Event”
  • Announcements, AOB, & closing



Title: Life-long Spatio-temporal Exploration of Dynamic Environments: An overview.

By: Joao Santos


 Abstract: The primary purpose of robotic exploration is to autonomously acquire a complete and precise model of the robot’s operational environment. To explore efficiently, the robot has to direct its attention to environment areas that are currently unknown. If the world was static, these areas would simply correspond to previously unvisited locations. In the case of dynamic environments, visiting all locations only once is not enough, because they may change over time. Thus, dynamic exploration requires that the environment locations are revisited and their (re-) observations are used to update a dynamic environment model. However, revisiting the individual locations with the same frequency and on a regular basis is not efficient because the environment dynamics will, in general, not be homegeneous, (i.e. certain areas change more often and the changes occur only at certain times).

Similarly to the static environment exploration, the robot should revisit only the areas whose states are unknown at the time of the planned visits. Thus, the robot has to use its environment model to predict the uncertainty of the individual locations over time and use these predictions to plan observations that from a theoretical point of view improve its knowledge about the world’s dynamics. Hence, the observations are scheduled in order to obtain information about the environment changes, which are mainly caused by human-activity. As a consequence, using schedules motivated by the changes in metric maps increases the chance to extract  dynamics that are essential for object learning and activity recording tasks.






PGRs meeting and Research Presentations – March 2015

The monthly PGRs Research Presentations was held on Wed. 11th March, 2pm, Room MC3108.

This session we had the following presentations:

Title: “Retinal Vascular Measurement“. Title:   “4D Lifelong Exploration of Dynamic Environments

By: Francesco Caliva

By: Joao Santos

Abstract: Several studies have shown that systemic diseases affect blood vessels’ geometry. Retina is a window in the vascular system, thus fundus images can be adopted to diagnose or evaluate pathological conditions. Segmentation algorithms are not able to completely segment blood vessels. This failure results in a set of disconnected vascular segments. Reconstructing the whole network has crucial importance. At this aim, in this work, implicit neural cost functions have been adopted to evaluate how the segments can be joined. In this talk I will present my current and future work. Abstract:  We present a novel 4D lifelong exploration method for dynamic, human populated environments. In contrast to other exploration methods that model the environment as being static, our spatio-temporal exploration method creates and maintains a world model that not only represents the environment’s 3D structure, but also its dynamics over time.The predictive ability of the 4D spatio-temporal model allows the exploration method not only where, but also when to make environment observations.
To validate our method, a mobile robot was deployed over 5 days in an office environment, and the proposed method was compared against a static approach. The results show that through understanding of the environment dynamics, the spatio-temporal exploration algorithm could predict which locations were going to change at a specific time and used this knowledge to guide the robot. This allowed our spatio-temporal exploration method to gather more information that the exploration method that relied on a static environment model.