IPAB Workshop - 25/04/2019

 

James Garforth

Abstract:  Monocular simultaneous localisation and mapping (SLAM) is a cheap and energy efficient way to enable Unmanned Aerial Vehicles (UAVs) to safely navigate managed forests and gather data crucial for monitoring tree health. SLAM research, however, has mostly been conducted in structured human environments, and as such is poorly adapted to unstructured forests. We compare the performance of state of the art monocular SLAM systems on forest data and use visual appearance statistics to characterise the differences between forests and other environments, including a photorealistic simulated forest.

 

He Zhang

Title: Multi-Phase Neural Networks for Goal-Directed Character Control

Abstract: I will talk about a data-driven framework to guide characters to achieve goal-directed movements with scene interactions. Such auto-regressive framework enables modeling of multi-modal scene interaction behaviors purely from motion capture data. We adopt a volume representation to recognize the geometry around the character and predict the corresponding motions. We also propose a control scheme that combines the egocentric inference and the world-centric inference to improve the interaction accuracy.

 

 

Apr 25 2019 -

IPAB Workshop - 25/04/2019

James Garforth, He Zhang

IF, 4.31/33