Abel González Garcia, Andreea Radulescu, Yiming Yang will be speaking

SPEAKER: Abel González García

TALK TITLE: An Active Search Strategy for Efficient Object Detection

TALK ABSTRACT:  Object class detectors typically apply a window classifier to all the windows in a large set, either in a sliding window manner or using object proposals. In this work, we develop an active search strategy that sequentially chooses the next window to evaluate based on all the information gathered before. This results in a substantial reduction in the number of classifier evaluations and in a more elegant approach in general. Our search strategy is guided by two forces. First, we exploit context as the statistical relation between the appearance of a window and its location relative to the object, as observed in the training set. This enables to jump across distant regions in the image (e.g. observing a sky region suggests that cars might be far below) and is done efficiently in a Random Forest framework. Second, we exploit the score of the classifier to attract the search to promising areas surrounding a highly scored window, and to keep away from areas near low scored ones. In experiments on the challenging SUN 2012 dataset, our method matches the detection accuracy of evaluating all windows independently, while evaluating 9x fewer windows. It even outperforms it when evaluating 3x fewer windows.

 

 

SPEAKER: Andreea Radulescu

TALK TITLE: "Brachiation robot control: Preliminary work on online dynamics adaptation"

TALK ABSTRACT:  "This talk will give an overview of the previously developed optimal control framework for robotic systems in domains with contacts possessing impedance modulation capabilities. It will introduce the motivation for model accuracy improvement and present the selected methodology for learning dynamics. The current state of the investigation and issues encountered will be described."

 

 

SPEAKER: Yiming  Yang

TALK TITLE: "Real-Time Motion Adaptation using Relative Distance Space Representation"

TALK ABSTRACT:  Reacting to environment changes is a big challenge for real world robot applications. We present a novel approach that allows the robot to quickly adapt to changes, particularly in the presence of moving targets and dynamic obstacles. Typically, a configuration space replanning or adaptation is required if the environment is changed. Rather, our method aims to maintain a plan, in a relative distance space rather than configuration space, that can be valid in different environments. In addition, we introduce an incremental planning structure that allows us to handle unexpected obstacles that may appear during execution. The main contribution is that the relative distance space representation encodes pose re-targeting, reaching and avoiding tasks within one unified cost term that can be solved in real-time to achieve a fast implementation for high degree of freedom (DOF) robots. We evaluate our method on a 7 DOF LWR robot arm, and a 14 DOF dual-arm Baxter robot.