Andrei Jalba

Omar Richardson, Andrei Jalba, Adrian Muntean

We study the evacuation dynamics of a crowd evacuating from a complex geometry in the presence of a fire as well as of a slowly spreading smoke curtain. The crowd is composed of two kinds of individuals: those who know the layout of the building, and those who do not and rely exclusively on potentially informed neighbors to identify a path towards the exit. We aim to capture the effect the knowledge of the environment has on the interaction between evacuees and their residence time in the presence of fire and evolving smoke. Our approach is genuinely multiscale - we employ a two-scale model that is able to distinguish between compressible and incompressible pedestrian flow regimes and allows for micro and macro pedestrian dynamics. Simulations illustrate the expected qualitative behavior of the model. We finish with observations on how mixing evacuees with different levels of knowledge impacts important evacuation aspects.

Haodong Zheng, Andrei Jalba, Raymond H. Cuijpers et al.

As humans can explore and understand the world through active touch, similar capability is desired for robots. In this paper, we address the problem of active tactile object recognition, pose estimation and shape transfer learning, where a customized particle filter (PF) and Gaussian process implicit surface (GPIS) is combined in a unified Bayesian framework. Upon new tactile input, the customized PF updates the joint distribution of the object class and object pose while tracking the novelty of the object. Once a novel object is identified, its shape will be reconstructed using GPIS. By grounding the prior of the GPIS with the maximum-a-posteriori (MAP) estimation from the PF, the knowledge about known shapes can be transferred to learn novel shapes. An exploration procedure based on global shape estimation is proposed to guide active data acquisition and terminate the exploration upon sufficient information. Through experiments in simulation, the proposed framework demonstrated its effectiveness and efficiency in estimating object class and pose for known objects and learning novel shapes. Furthermore, it can recognize previously learned shapes reliably.